VISVESVARAYA TECHNOLOGICAL UNIVERSITY

"Jnana Sangama", Belgavi

(Academic Year 2022-2023)

An Project Report on

“AI BASED IDENTITY

RECOGNITIO
NUSING FINGER VEIN”
Submitted in fulfillment of the Internship
BACHELOR OF ENGINEERING
IN

ARTIFCIAL INTELLIGENCE & MACHINE LEARNING

Prepared By:
BHAGYESH (3RB20AI010)
Under the guidance of:
Prof .Abhishek Sali

BHEEMANNA KHANDRE INSTITUTE OF TECHNOLOGY

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
 S. V. E. Society's

Bheemanna Khandre Institute of Technology, Bhalki 585328

Artificial Intelligence and Machine Learning

CERTIFICATE
This is to certify that the project entitled “AI based identity recognition
using finger vein” has been successfully carried out by
BHAGYESH(3RB20AI010) fulfillment of the completion of Internship in
Pantech, Hyderabad in Artificial Intelligence, during the academic year 2023-
2024. It is certified that all corrections/suggestions for internal assessment have
been incorporated in report deposited in the department library. The Internship
report has been approved as it satisfies the academic requirements in respect of
Internship work prescribed for the said Degree.

Internal Guide Head of Dept Principal

Prof. Abhishek Dr. Shivkumar A. Dr. N M Biradar
Dept. of AI&ML Dept. of AI&ML BKIT Bhalki

Name of the Examiner Signature with date

1

2
 ACKNOWLEDGEMENTS

We would like to express our gratitude to the following people whose constant
support helped immensely in the successful completion of our Internship.

We are grateful to all those who have helped us in preparing our project.

Our sincere thanks to our project guide Prof. Abhishek Sali for their guidance
in the preparation of the project. Their constant and sincere guidance helped us
in maintaining the tempo and thus helped us to complete the Internship.

We wish to express our sincere thanks Dr. Shivkumar A. (H.O.D Dept of

AIML) and whole of the Artificial Intelligence & Machine Learning for the
constant encouragement during the completion of the Internship.

We would like to thank Dr. N. M. Biradar, principal, BKIT Bhalki, for

providing such a congenial working environment.

Finally we thank all our friends for their help in making our project a grand
success.

Cordinally
BHAGYESH 3RB20AI010
 Artificial Intelligence

ABSTRACT

The finger vein detection is based on convolutional neural

network. Here, requirement is detection of fingers of biometric
weather person finger is matched or not. These are mainly used
at security applications. Use of this finger vein is automatic user
recognition at biometric type.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 4

 Artificial Intelligence

INDEX

Chapter Page No

1.Introduction 6

2.Digital Image Processing 7-17

3.Image compression model 18-21

4.Classification of Images 22-25

5. Convolutional Neural Network 26-29

6.Edge detection 30-35

7.Computer 36-47
vision
8.Algorithm 48-49

9.Process IP, 50
OP & scopes

10.References 51

Dept. of AIML, BKIT Bhalki 2022-2023 Page 5

 Artificial Intelligence

Chapter 1

INTRODUCTION

The main use of this finger print detection for avoiding security
problems. plan of effective biometric distinguishing proof
frameworks, estimating interesting physical or social attributes of
people for their protected acknowledgment, is these days a testing
and important assignment for both the logical and the mechanical
networks. Ordinarily utilized physical biometric characteristics
incorporate face, hand math, unique mark, and iris among the
others, though signature, voice, keystroke design, also, step are
instances of social modalities.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 6

 Artificial Intelligence

Chapter 2

DIGITAL IMAGE PROCESSING

The identification of objects in an image and this process would

probably start with image processing techniques such as noise removal,
followed by (low-level) feature extraction to locate lines, regions and
possibly areas with certain textures.
The clever bit is to interpret collections of these shapes as single
objects, e.g. cars on a road, boxes on a conveyor belt or cancerous cells on
a microscope slide. One reason this is an AI problem is that an object can
appear very different when viewed from different angles or under different
lighting. Another problem is deciding what features belong to what object
and which are background or shadows etc. The human visual system
performs these tasks mostly unconsciously but a computer requires skilful
programming and lots of processing power to approach human
performance. Manipulation of data in the form of an image through
several possible techniques. An image is usually interpreted as a two-
dimensional array of brightness values, and is most familiarly represented
by such patterns as those of a photographic print, slide, television screen,
or movie screen. An image can be processed optically or digitally with a
computer.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 7

 Artificial Intelligence

FUNDAMENTALS OF DIGITAL IMAGE

1.1 IMAGE:
An image is a two-dimensional picture, which has a similar appearance to
some subject usually a physical object or a person.

Image is a two-dimensional, such as a photograph, screen display, and as well

as a three-dimensional, such as a statue. They may be captured by optical devices—
such as cameras, mirrors, lenses, telescopes, microscopes, etc. and natural objects
and phenomena, such as the human eye or water surfaces.

The word image is also used in the broader sense of any two-dimensional
figure such as a map, a graph, a pie chart, or an abstract painting. In this wider sense,
images can also be rendered manually, such as by drawing, painting, carving,
rendered automatically by printing or computer graphics technology, or developed
by a combination of methods, especially in a pseudo-photograph.

Fig: Colour image to Gray scale Conversion Process

Dept. of AIML, BKIT Bhalki 2022-2023 Page 8

 Artificial Intelligence

An image is a rectangular grid of pixels. It has a definite height and a definite width
counted in pixels. Each pixel is square and has a fixed size on a given display.
However different computer monitors may use different sized pixels. The pixels that
constitute an image are ordered as a grid (columns and rows); each pixel consists of
numbers representing magnitudes of brightness and color.

Fig: Gray Scale Image Pixel Value Analysis

Each pixel has a color. The color is a 32-bit integer. The first eight bits
determine the redness of the pixel, the next eight bits the greenness, the next eight
bits the blueness, and the remaining eight bits the transparency of the pixel.

Fig: BIT Transferred for Red, Green and Blue plane (24bit=8bit red;8-bit green;8bit blue)

IMAGE FILE SIZES:

Image file size is expressed as the number of bytes that increases with the number of
pixels composing an image, and the color depth of the pixels. The greater the number
of rows and columns, the greater the image resolution, and the larger the file. Also,

Dept. of AIML, BKIT Bhalki 2022-2023 Page 9

 Artificial Intelligence

each pixel of an image increases in size when its color depth increases, an 8-bit pixel
(1 byte) stores 256 colors, a 24-bit pixel (3 bytes) stores 16 million colors, the latter
known as true color.Image compression uses algorithms to decrease the size of a file.
High resolution cameras produce large image files, ranging from hundreds of
kilobytes to megabytes, per the camera's resolution and the image-storage format
capacity. High resolution digital cameras record 12 megapixel (1MP = 1,000,000
pixels / 1 million) images, or more, in true color. For example, an image recorded by
a 12 MP camera; since each pixel uses 3 bytes to record true color, the uncompressed
image would occupy 36,000,000 bytes of memory, a great amount of digital storage
for one image, given that cameras must record and store many images to be practical.
Faced with large file sizes, both within the camera and a storage disc, image file
formats were developed to store such large images.
IMAGE FILE FORMATS:
Image file formats are standardized means of organizing and storing images. This
entry is about digital image formats used to store photographic and other images.
Image files are composed of either pixel or vector (geometric) data that are rasterized
to pixels when displayed (with few exceptions) in a vector graphic display. Including
proprietary types, there are hundreds of image file types. The PNG, JPEG, and GIF
formats are most often used to display images on the Internet.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 10

 Artificial Intelligence

Fig: Horizontal and Vertical Process

In addition to straight image formats, Metafile formats are portable formats which
can include both raster and vector information. The metafile format is an
intermediate format. Most Windows applications open metafiles and then save them
in their own native format.
IMAGE PROCESSING:
Digital image processing, the manipulation of images by computer, is relatively
recent development in terms of man’s ancient fascination with visual stimuli. In its
short history, it has been applied to practically every type of images with varying
degree of success. The inherent subjective appeal of pictorial displays attracts
perhaps a disproportionate amount of attention from the scientists and also from the
layman. Digital image processing like other glamour fields, suffers from myths, mis-
connect ions, mis-understandings and mis-information. It is vast umbrella under
which fall diverse aspect of optics, electronics, mathematics, photography graphics
and computer technology. It is truly multidisciplinary endeavor ploughed with
imprecise jargon.
Several factor combine to indicate a lively conccc for digital image
processing. A major factor is the declining cost of computer equipment. Several new
technological trends promise to further promote digital image processing. These
include parallel processing mode practical by low cost microprocessors, and the use
of charge coupled devices (CCDs) for digitizing, storage during processing and
display and large low cost of image storage arrays.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 11

 Artificial Intelligence

FUNDAMENTAL STEPS IN DIGITAL IMAGE

PROCESSING:

IMAGE ACQUISITION:
Image Acquisition is to acquire a digital image. To do so requires an image
sensor and the capability to digitize the signal produced by the sensor. The sensor
could be monochrome or color TV camera that produces an entire image of the
problem domain every 1/30 sec. the image sensor could also be line scan camera that
produces a single image line at a time. In this case, the objects motion past the line.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 12

 Artificial Intelligence

Fig: Digital camera

Scanner produces a two-dimensional image. If the output of the camera or
other imaging sensor is not in digital form, an analog to digital converter digitizes it.
The nature of the sensor and the image it produces are determined by the application.

Fig: Mobile based Camera

IMAGE ENHANCEMENT:
Image enhancement is among the simplest and most appealing areas of
digital image processing. Basically, the idea behind enhancement techniques is to
bring out detail that is obscured, or simply to highlight certain features of interesting
an image. A familiar example of enhancement is when we increase the contrast of
an image because “it looks better.” It is important to keep in mind that enhancement
is a very subjective area of image processing.

Fig: Image enhancement process for Gray Scale Image and Colour Image using Histogram
Bits

Dept. of AIML, BKIT Bhalki 2022-2023 Page 13

 Artificial Intelligence

IMAGE RESTORATION:

Image restoration is an area that also deals with improving the appearance of
an image. However, unlike enhancement, which is subjective, image restoration is
objective, in the sense that restoration techniques tend to be based on mathematical
or probabilistic models of image degradation.

Fig: Noise image Image Enhancement

Enhancement, on the other hand, is based on human subjective preferences

regarding what constitutes a “good” enhancement result. For example, contrast
stretching is considered an enhancement technique because it is based primarily on
the pleasing aspects it might present to the viewer, where as removal of image blur
by applying a deblurring function is considered a restoration technique .

COLOR IMAGE PROCESSING:

The use of color in image processing is motivated by two principal factors.
First, color is a powerful descriptor that often simplifies object identification and
extraction from a scene. Second,

Dept. of AIML, BKIT Bhalki 2022-2023 Page 14

 Artificial Intelligence

humans can discern thousands of color shades and intensities, compared to

about only two dozen shades of gray. This second factor is particularly important in
manual image analysis.

Fig: gray Scale image  Colour Image

SEGMENTATION:

Segmentation procedures partition an image into its constituent parts or

objects. In general, autonomous segmentation is one of the most difficult tasks in
digital image processing. A rugged segmentation procedure brings the process a long
way toward successful solution of imaging problems that require objects to be
identified individually.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 15

 Artificial Intelligence

Fig: Image Segment Process

On the other hand, weak or erratic segmentation algorithms almost always

guarantee eventual failure. In general, the more accurate the segmentation, the more
likely recognition is to succeed.
Digital image is defined as a two dimensional function f(x, y), where x and y
are spatial (plane) coordinates, and the amplitude of f at any pair of coordinates (x,
y) is called intensity or grey level of the image at that point. The field of digital image
processing refers to processing digital images by means of a digital computer. The
digital image is composed of a finite number of elements, each of which has a
particular location and value. The elements are referred to as picture elements, image
elements, pels, and pixels. Pixel is the term most widely used.
IMAGE COMPRESSION

In image compression, three basic data redundancies can be identified and

exploited: Coding redundancy, interpixel redundancy, and phychovisal redundancy.
Image compression is achieved when one or more of these redundancies are reduced
or eliminated. The image compression is mainly used for image transmission and
storage. Image transmission applications are in broadcast television; remote sensing
via satellite, air-craft, radar, or sonar; teleconferencing; computer communications;
and facsimile transmission. Image storage is required most commonly for
educational and business documents,

Dept. of AIML, BKIT Bhalki 2022-2023 Page 16

 Artificial Intelligence

medical images that arise in computer tomography (CT), magnetic resonance

imaging (MRI) and digital radiology, motion pictures, satellite images, weather
maps, geological surveys, and so on.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 17

 Artificial Intelligence

Chapter 3

IMAGE COMPRESSION MODEL

Fig:1.1b) Decompression Process for Image

IMAGE COMPRESSION TYPES

There are two types’ image compression techniques.
I. Lossy Image compression
II.Lossless Image compression
I. Lossy Image compression :
Lossy compression provides higher levels of data reduction but result in a less than
perfect reproduction of the original image. It provides high compression ratio. lossy
image compression is useful in applications such as broadcast television,
videoconferencing, and facsimile transmission, in which a certain amount of error is
an acceptable trade-off for increased compression performance. Originally, PGF has
been designed to quickly and progressively decode lossy compressed aerial images.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 18

 Artificial Intelligence

A lossy compression mode has been preferred, because in an application like a terrain
explorer texture data (e.g., aerial orthophotos) is usually mid-mapped filtered and
therefore lossy mapped onto the terrain surface. In addition, decoding lossy
compressed images is usually faster than decoding lossless compressed images.
In the next test series we evaluate the lossy compression efficiency of PGF. One of
the best competitors in this area is for sure JPEG 2000. Since JPEG 2000 has two
different filters, we used the one with the better trade-off between compression
efficiency and runtime. On our machine the 5/3 filter set has a better trade-off than
the other. However, JPEG 2000 has in both cases a remarkable good compression
efficiency for very high compression ratios but also a very poor encoding and
decoding speed. The other competitor is JPEG. JPEG is one of the most popular
image file formats.

It is very fast and has a reasonably good compression efficiency for a wide range of
compression ratios. The drawbacks of JPEG are the missing lossless compression
and the often missing progressive decoding.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 19

 Artificial Intelligence

Fig. 4 depicts the average rate-distortion behavior for the images in the Kodak test
set when fixed (i.e., nonprogressive) lossy compression is used. The PSNR of PGF
is on average 3% smaller than the PSNR of JPEG 2000, but 3% better than JPEG.

II.Lossless Image compression :

Lossless Image compression is the only acceptable amount of data reduction.
It provides low compression ratio while compared to lossy. In Lossless Image
compression techniques are composed of two relatively independent operations: (1)
devising an alternative representation of the image in which its interpixel
redundancies are reduced and (2) coding the representation to eliminate coding
redundancies.
Lossless Image compression is useful in applications such as medical
imaginary, business documents and satellite images.Table 2 summarizes the lossless
compression efficiency and Table 3 the coding times of the PGF test set. For WinZip
we only provide average runtime values, because of missing source code we have to
use an interactive testing procedure with runtimes measured by hand. All other
values are measured in batch mode.

Fig. 3 shows the averages of the compression ratios (ratio), encoding (enc),
Dept. of AIML, BKIT Bhalki 2022-2023 Page 20
 Artificial Intelligence

and decoding (dec) times over all eight images. JPEG 2000 shows in this test set the
best compression efficiency followed by PGF, JPEG-LS, PNG, and WinZip. In
average PGF is eight percent worse than JPEG 2000. The fact that JPEG 2000 has a
better lossless compression ratio than PGF does not surprise,
because JPEG 2000 is more quality driven than PGF.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 21

 Artificial Intelligence

Chapter 4

CLASSIFICATION OF IMAGES:

There are 3 types of images used in Digital Image Processing. They are

1. Binary Image
2. Gray Scale Image
3. Colour Image

BINARY IMAGE:

A binary image is a digital image that has only two possible values for
each pixel. Typically the two colors used for a binary image are black and white
though any two colors can be used. The color used for the object(s) in the image is
the foreground color while the rest of the image is the background color.
Binary images are also called bi-level or two-level. This means that each pixel
is stored as a single bit (0 or 1).This name black and white, monochrome or
monochromatic are often used for this concept, but may also designate any images
that have only one sample per pixel, such as grayscale images
Binary images often arise in digital image processing as masks or as the result
of certain operations such as segmentation, thresholding, and dithering. Some
input/output devices, such as laser printers, fax machines, and bi-level computer
displays, can only handle bi-level images

Dept. of AIML, BKIT Bhalki 2022-2023 Page 22

 Artificial Intelligence

GRAY SCALE IMAGE

A grayscale Image is digital image is an image in which the value of
each pixel is a single sample, that is, it carries only intensity information. Images of
this sort, also known as black-and-white, are composed exclusively of shades
of gray(0-255), varying from black(0) at the weakest intensity to white(255) at the
strongest.
Grayscale images are distinct from one-bit black-and-white images, which in
the context of computer imaging are images with only the two colors, black,
and white (also called bi-level or binary images). Grayscale images have many
shades of gray in between. Grayscale images are also called monochromatic,
denoting the absence of any chromatic variation.

Grayscale images are often the result of measuring the intensity of light at each
pixel in a single band of the electromagnetic spectrum (e.g. infrared, visible
light, ultraviolet, etc.), and in such cases they are monochromatic proper when only
a given frequency is captured. But also they can be synthesized from a full color
image; see the section about converting to grayscale.

COLOUR IMAGE:
A (digital) color image is a digital image that includes color information for
each pixel. Each pixel has a particular value which determines its appearing color.
This value is qualified by three numbers giving the decomposition of the color in the
three primary colors Red, Green and Blue. Any color visible to human eye can be
represented this way. The decomposition of a color in the three primary colors is
quantified by a number between 0 and 255. For example, white will be coded as R =
255, G = 255, B = 255; black will be known as (R,G,B) = (0,0,0); and say, bright
pink will be : (255,0,255).

Dept. of AIML, BKIT Bhalki 2022-2023 Page 23

 Artificial Intelligence

In other words, an image is an enormous two-dimensional array of color

values, pixels, each of them coded on 3 bytes, representing the three primary colors.
This allows the image to contain a total of 256x256x256 = 16.8 million different
colors. This technique is also known as RGB encoding, and is specifically adapted
to human vision

Fig.1 Hue Saturation Process of RGB SCALE Image

From the above figure, colors are coded on three bytes representing their
decomposition on the three primary colors.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 24

 Artificial Intelligence

It sounds obvious to a mathematician to immediately interpret colors as vectors in a

three dimension space where each axis stands for one of the primary colors.
Therefore we will benefit of most of the geometric mathematical concepts to deal
with our colors, such as norms, scalar product, projection, rotation or distance.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 25

 Artificial Intelligence

Chapter 5

CONVOLUTIONAL NEURAL NETWORK

5.1 CONVENTIONAL NEURAL NETWORKS

A CNN contains a sequence of convolutional and max-pooling layers,

activation layer and each layer has connected with its previous layer. It is a general,
hierarchical feature extractor that will map input image pixel intensities into a feature
vector. This was classified by several fully connected layers in the next step [8]. All
adjustable parameters are optimized by minimizing the misclassification by reducing
the error over the training set. Each convolutional layer performs a 2D convolution
with a filter of different size 3 x 3, 5 x 5, 7 x 7. The subsequent activations of the
output maps are given by the total of the past convolutional responses which are gone
through a nonlinear activation function. Max pooling layer was performing the
dimensionality reduction.

The output of a thin-layer was given by the most extreme activation over non-
covering rectangular areas. Max-pooling makes location invariance and down-
samples the image along every direction over a bigger neighbourhood. Filter size of
convolutional and max-pooling layers are selected in such a way that a fully
connected layer can combine the output into a one-dimensional vector. The last layer
always be a fully connected layer which contains one output unit for all classes. Here
rectification linear unit was used as the activation function. Furthermore, it was
deciphered as the likelihood of a specific input image having a place with that class.
Adam optimization algorithm that can be used instead of the classical stochastic
gradient descent procedure to update network weights iterative based in training data.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 26

 Artificial Intelligence

5.2 IMAGE CLASSIFICATION BASED ON CNN

Image Classification was the process of finding instances of real-world objects

such as faces, buildings, and bicycles in images or videos. Thus, the working process
of Alzheimer stages detection and classification based on CNN is shown in Figure
4.1. Image classification algorithms typically use extracted features and learning
algorithms to recognize instances of an object category. It was commonly used in
applications such as image retrieval, security and advanced driver assistance
systems.

Classification of image was an important topic in artificial vision systems and

had drawn a significant amount of interest over the last decades. After that, feature
detection methods in built on this pre-defined model to training and testing of our
project. By using those features extraction methods some parameters values of
features are calculated. However, when a lot of images were given, it was too
difficult problem to find features from it. This was one of the reasons that a deep
neural network model is used. To extract the features from Alex net that are trained
on Alzheimer stages dataset. CNN uses over each image and adjust the kernel as per
the propagation in the network. A kernel was then convolved over the entire image
to produces feature maps. As the layers become deeper, the network acquires the
knowledge of larger feature extraction. The initial layers take care of the smaller
details of the image and the deeper layer can identify the more number details from
the image. It was pre-process the images and extract the features by feed-forwarding
through the network, and also specify the layer names that can be extracted and save
them.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 27

 Artificial Intelligence

5.3 TRAINING AND TESTING THE NETWORKS

After the network has been structured for classification application with all
parameters, then it was ready for training. After each iteration, the network
converges by reducing the error rate. The loop was terminating when it reached a
minimum error rate. A learning rate was maintained for each network weight
(parameter) and separately adapted as learning unfolds. The network weight was
adjusted subsequently in each iteration from initial value based on result until it
converges to a value. Weight will decide the convergence. The weight value for each
image is recorded in a neural network after database loaded. Here learning rate is
0.0001. Those defined weights was further used to classify more number of datasets.
Training of normal and abnormal Alzheimer stages images on CNN can be done.

The pre-trained weight which was obtained from the training phase also used
in the testing phase. The input image was allowed to pass through all layers of the
neural network and parameters were obtained [4]. These values were cross-checked

with the pre-trained weight and identify the one which gives maximum
matching with the classes presents in the dataset. The system was considering the
label to which it is closely matched.

SOFTWARE REQUIREMENTS:

• PYTHON IDLE

• ANACONDA

• JUPITER NOTE BOOK

Dept. of AIML, BKIT Bhalki 2022-2023 Page 28

 Artificial Intelligence

Python: Python Is An Object-Oriented, High Level Language, Interpreted,

Dynamic And Multipurpose Programming Language.

Python Is Easy To Learn Yet Powerful And Versatile Scripting Language Which
Makes It Attractive For Application Development.

Python's Syntax And Dynamic Typing With Its Interpreted Nature, Make It An Ideal
Language For Scripting And Rapid Application Development In Many Areas.

Python Supports Multiple Programming Pattern, Including Object Oriented

Programming, Imperative And Functional Programming Or Procedural Styles.

Python Is Not Intended To Work On Special Area Such As Web Programming. That
Is Why It Is Known As Multipurpose Because It Can Be Used With Web, Enterprise,
3d Cad Etc.

We Don't Need To Use Data Types To Declare Variable Because It Is Dynamically

Typed So We Can Write A=10 To Declare An Integer Value In A Variable.

Python Makes The Development And Debugging Fast Because There Is No

Compilation Step Included In Python Development And Edit-Test-Debug Cycle Is

Very Fast.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 29

 Artificial Intelligence

Chapter 6

EDGE DETECTION

DETECTION:

i.Three criteria to measure the quality of the algorithm

a. detect correctly
- The image is not an edge detection operator missed, nor will be marked as non-
edge margin.
b. positioned correctly
- Edge of the image position and the detected position of the edge as close as possible
.
c. edge single response
- A single image edge detection operator as a single response.
ii.Impact of noise on the detection of
a. signal to noise ratio is defined :
Optimal edge detection operator, as the edge of the root -mean-square noise. Let the
(convolution) to achieve the corresponding filter, the filter response range for the
shock affected.
b. noise on location
Optimal positioning depends on the maximization of the formula: impact on the (
wrong ) Multiple response to a single edge of c. detection operator Adjacent local
maximum is: Remains constant as large as possible, you can try to eliminate operator
to respond to a single multi- edge ( error ) phenomenon .

Dept. of AIML, BKIT Bhalki 2022-2023 Page 30

 Artificial Intelligence

iii.Exporting the best one-dimensional convolution kernel case

To simplify the analysis of the step edge , Canny the holding under the same

conditions , the solution of the maximum value . Using the variation method, you
can export conditions a set of best filter for different values of . It is further found
that this filter can be approximated by a series of best -order derivative of the
different values of the Gaussian kernel function .

iv.Two-dimensional case
For the two-dimensional case, Canny edge filter with two horizontal, respectively
vertical, plus the first derivative of Gaussian additive white noise estimation image
function, edge detection. Note: The cross-section of different edges , Canny operator
has different forms of expression should be derived from depending on the
circumstances . Noting the step edge cases, canny operator form of expression and
LOG are similar.
v.Non-maxima suppression
The specific location of the edge set, and the need to find the local maxima along
the gradient direction image convolution. Therefore, the maximum value of the
second derivative along the gradient direction is 0, the Gaussian
function
Special note that there are a lot of people in an 8 - neighbourhood search approach
to non-maximum suppression
vi.Hysteresis thresholding
Due to noise, the image of the edge of the response to a single error , often result
in the continuous edge appears to be brittle. This problem can be solved hysteresis
thresholding.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 31

 Artificial Intelligence

If the response of any pixel on the edge operator exceeds the high threshold, these
pixel tags is the edge ; response than the low threshold of pixels , if already marked
edge pixels 4 - adjacency or 8 - adjacent , then the pixels are labelled as edge , this
iterative process , the rest of the response of isolated pixels than the low threshold is
considered noise , no longer marked as edges. Both the SNR threshold value is
determined by 2.
vii.Synthesis of multi-scale feature
Canny using a coarse by the subtlety of the process of edge detection results of
different scales are synthesized. First mark the smallest scales corresponding
operator edge detection . Then , along the direction perpendicular to the edge of these
small-scale edge detection operators conduct Gaussian convolution , edge detection
results in the synthesis of a large scale. Value and the value of the convolution edge
detection operator under the same large scale . The test results with the large -scale
synthesis result of comparing the operator , if the large- scale edge detection operator
, which far exceeds the response signal synthesis result , these edges will be added
to the small -scale edge detection on Operator . Such iterative process followed every
step of the synthesis of all the steps on the front edges are not detected , so you can
be the edge detection results of different scales better synthesis together.

Applications:
• Security applications

• Industrial applications

• Social media

• Mobile applications

• Civil applications

Dept. of AIML, BKIT Bhalki 2022-2023 Page 32

 Artificial Intelligence

BLOCK DIAGRAM

Input

preprocess

Binary
detection

Region of Data set

interest

trained Data
Feature
extraction matched

Edge algorithm
detection Not
matched

Dept. of AIML, BKIT Bhalki 2022-2023 Page 33

 Artificial Intelligence

Explanation: -
Taking the input from user and applying preprocesses like resize, color conversion,
and filtering techniques then after that it will go for binary detection in this the input
will get converted in binary form machine understanding purpose. And this all
processes will be done on background only while after taking the input it will start
to applying this process. Then after that it will go for Region of interest the name it
self showing what are interested regions, we required for detection of vein that
regions it will detect and extract from the pre-process. Then it will go for feature
extraction method in this it will extract the project regarding requirements features
for vein detection. Then the next and important feature is edge detection because at
this phase only with the help of this technique only we can detect the vein using
edges techniques. Then the next step is to verify with pretrained data set with the
algorithm using CNN. Then it will go to data set and it will verify with our dataset
and gives the results if the person vein is matched or un-matched.

Modules used:
● Digital image processing

● Pre-process

● Edge detection

software used:
Python IDLE any version
Open-CV

Dept. of AIML, BKIT Bhalki 2022-2023 Page 34

 Artificial Intelligence

LANGUAGE USED:

Python is an object-oriented, high level language, interpreted, dynamic and

multipurpose programming language.

Python is easy to learn yet powerful and versatile scripting language which makes it
attractive for Application Development.

Python's syntax and dynamic typing with its interpreted nature, make it an ideal
language for scripting and rapid application development in many areas.

Python supports multiple programming pattern, including object oriented

programming, imperative and functional programming or procedural styles.

Python is not intended to work on special area such as web programming. That is
why it is known as multipurpose because it can be used with web, enterprise, 3D
CAD etc.

We don't need to use data types to declare variable because it is dynamically typed so
we can write a=10 to declare an integer value in a variable.

Python makes the development and debugging fast because there is no compilation
step included in python development and edit-test-debug cycle is very fast.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 35

 Artificial Intelligence

Chapter 7
COMPUTER VISION

Computer Vision is the broad parent name for any computations involving visual
content – that means images, videos, icons, and anything else with pixels involved.
But within this parent idea, there are a few specific tasks that are core building
blocks:

 In object classification, you train a model on a dataset of specific objects, and

the model classifies new objects as belonging to one or more of your training
categories.
 For object identification, your model will recognize a specific instance of an
object – for example, parsing two faces in an image and tagging one as Tom
Cruise and one as Katie Holmes.

A classical application of computer vision is handwriting recognition for digitizing

handwritten content (we’ll explore more use cases below). Outside of just
recognition, other methods of analysis include:

 Video motion analysis uses computer vision to estimate the velocity of

objects in a video, or the camera itself.
 In image segmentation, algorithms partition images into multiple sets of
views.
 Scene reconstruction creates a 3D model of a scene inputted through images
or video (check out Selva).
 In image restoration, noise such as blurring is removed from photos using
Machine Learning based filters.

Any other application that involves understanding pixels through software can safely
be labeled as computer vision.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 36

 Artificial Intelligence

How Computer Vision Works

One of the major open questions in both Neuroscience and Machine Learning is:
how exactly do our brains work, and how can we approximate that with our own
algorithms? The reality is that there are very few working and comprehensive
theories of brain computation; so despite the fact that Neural Nets are supposed to
“mimic the way the brain works,” nobody is quite sure if that’s actually true. Jeff
Hawkins has an entire book on this topic called On Intelligence.

The same paradox holds true for computer vision – since we’re not decided on how
the brain and eyes process images, it’s difficult to say how well the algorithms used
in production approximate our own internal mental processes. For example, studies
have shown that some functions that we thought happen in the brain of frogs actually
take place in the eyes. We’re a far cry from amphibians, but similar uncertainty exists
in human cognition.

Machines interpret images very simply: as a series of pixels, each with their own set
of color values. Consider the simplified image below, and how grayscale values are
converted into a simple array of numbers:

Dept. of AIML, BKIT Bhalki 2022-2023 Page 37

 Artificial Intelligence

Think of an image as a giant grid of different squares, or pixels (this image is a very
simplified version of what looks like either Abraham Lincoln or a Dementor). Each
pixel in an image can be represented by a number, usually from 0 – 255. The series
of numbers on the right is what software sees when you input an image. For our
image, there are 12 columns and 16 rows, which means there are 192 input values
for this image.

When we start to add in color, things get more complicated. Computers usually read
color as a series of 3 values – red, green, and blue (RGB) – on that same 0 – 255
scale. Now, each pixel actually has 3 values for the computer to store in addition to
its position. If we were to colorize President Lincoln (or Harry Potter’s worst fear),
that would lead to 12 x 16 x 3 values, or 576 numbers.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 38

 Artificial Intelligence

For some perspective on how computationally expensive this is, consider this tree:

 Each color value is stored in 8 bits.

 8 bits x 3 colors per pixel = 24 bits per pixel.
 A normal sized 1024 x 768 image x 24 bits per pixel = almost 19M bits, or
about 2.36 megabytes.

That’s a lot of memory to require for one image, and a lot of pixels for an algorithm
to iterate over. But to train a model with meaningful accuracy – especially when
you’re talking about Deep Learning – you’d usually need tens of thousands of
images, and the more the merrier. Even if you were to use Transfer Learning to use
the insights of an already trained model, you’d still need a few thousand images to
train yours on.

With the sheer amount of computing power and storage required just to train deep
learning models for computer vision, it’s not hard to understand why advances in
those two fields have driven Machine Learning forward to such a degree.

Business Use Cases for Computer Vision

Computer vision is one of the areas in Machine Learning where core concepts are
already being integrated into major products that we use every day. Google is using
maps to leverage their image data and identify street names, businesses, and office
buildings. Facebook is using computer vision to identify people in photos, and do a
number of things with that information.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 39

 Artificial Intelligence

But it’s not just tech companies that are leverage Machine Learning for image
applications. Ford, the American car manufacturer that has been around literally
since the early 1900’s, is investing heavily in autonomous vehicles (AVs). Much of
the underlying technology in AVs relies on analyzing the multiple video feeds
coming into the car and using computer vision to analyze and pick a path of action.

Another major area where computer vision can help is in the medical field. Much of
diagnosis is image processing, like reading x-rays, MRI scans, and other types of
diagnostics. Google has been working with medical research teams to explore how
deep learning can help medical workflows, and have made significant progress in
terms of accuracy. To paraphrase from their research page:

“Collaborating closely with doctors and international healthcare systems, we

developed a state-of-the-art computer vision system for reading retinal fundus
images for diabetic retinopathy and determined our algorithm’s performance is on
par with U.S. board-certified ophthalmologists. We’ve recently published some of
our research in the Journal of the American Medical Association and summarized
the highlights in a blog post.”

But aside from the groundbreaking stuff, it’s getting much easier to integrate
computer vision into your own applications. A number of high-quality third party
providers like Clarifai offer a simple API for tagging and understanding images,
while Kairos provides functionality around facial recognition. We’ll dive into the
open-source packages available for use below.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 40

 Artificial Intelligence

Computer Vision on Algorithm

Algorithmia makes it easy to deploy computer vision applications as scalable

microservices. Our marketplace has a few algorithms to help get the job done:

 SalNet automatically identifies the most important parts of an image

 Nudity Detection detects nudity in pictures
 Emotion Recognition parses emotions exhibited in images
 DeepStyle transfers next-level filters onto your image
 Face Recognition…recognizes faces.
 Image Memorability judges how memorable an image is.

A typical workflow for your product might involve passing images from a security
camera into Emotion Recognition and raising a flag if any aggressive emotions are
exhibited, or using Nudity Detection to block inappropriate profile pictures on your
web application.

CONVERTING BINARY IMAGE

Converting color image or gray intensity image Thresholding is the simplest method
of image segmentation. From a grayscale image, thresholding can be used to create
binary images (Shapiro, et al. 2001:83).
The simplest thresholding methods replace each pixel in an image with a black pixel
if the image intensity I(I,j) is less than some fixed constant T (that is, I(I,j)<T), or a
white pixel if the image intensity is greater than that constant. In the example image
on the right, this results in the dark tree becoming completely black, and the white
snow becoming completely white.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 41

 Artificial Intelligence

Original image Example of a threshold effect used on an image

INVERTING BINARY IMAGE

In the complement of a binary image, zeros become ones and ones become zeros;
black and white are reversed. In the complement of an intensity or RGB image, each
pixel value is subtracted from the maximum pixel value supported by the class (or
1.0 for double-precision images) and the difference is used as the pixel value in the
output image. In the output image, dark areas become lighter and light areas become
darker. This is the matlab code for inverting any black and white image

Dept. of AIML, BKIT Bhalki 2022-2023 Page 42

 Artificial Intelligence

MEADIAN FILTER
The median filter is a nonlinear digital filtering technique, often used to remove noise
from an image or signal. Such noise reduction is a typical pre-processing step to
improve the results of later processing (for example, edge detection on an image).
Median filtering is very widely used in digital image processing because, under
certain conditions, it preserves edges while removing noise (but see discussion
below), also having applications in signal processing
The main idea of the median filter is to run through the signal entry by entry,
replacing each entry with the median of neighboring entries. The pattern of neighbors
is called the "window", which slides, entry by entry, over the entire signal. For 1D
signals, the most obvious window is just the first few preceding and following
entries, whereas for 2D (or higher-dimensional) signals such as images, more
complex window patterns are possible (such as "box" or "cross" patterns). Note that
if the window has an odd number of entries, then the median is simple to define: it
is just the middle value after all the entries in the window are sorted numerically. For
an even number of entries, there is more than one possible median, see median for
more details.
Typically, by far the majority of the computational effort and time is spent on
calculating the median of each window. Because the filter must process every entry
in the signal, for large signals such as images, the efficiency of this median
calculation is a critical factor in determining how fast the algorithm can run. The
naïve implementation described above sorts every entry in the window to find the
median; however, since only the middle value in a list of numbers is required,
selection algorithms can be much more efficient. Furthermore, some types of signals
(very often the case for images) use whole number representations: in these cases,

Dept. of AIML, BKIT Bhalki 2022-2023 Page 43

 Artificial Intelligence

histogram medians can be far more efficient because it is simple to update the
histogram from window to window, and finding the median of a histogram is not
particularly onerous.

EDGE PRESERVATION PROPERTIES

Median filtering is one kind of smoothing technique, as is linear Gaussian filtering.
All smoothing techniques are effective at removing noise in smooth patches or
smooth regions of a signal, but adversely affect edges. Often though, at the same
time as reducing the noise in a signal, it is important to preserve the edges. Edges are
of critical importance to the visual appearance of images, for example. For small to
moderate levels of (Gaussian) noise, the median filter is demonstrably better than
Gaussian blur at removing noise whilst preserving edges for a given, fixed window
size.[2] However, its performance is not that much better than Gaussian blur for high
levels of noise, whereas, for speckle noise and salt-and-pepper noise (impulsive
noise), it is particularly effective.[3] Because of this, median filtering is very widely
used in digital image processing.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 44

 Artificial Intelligence

SURF(SPEED UP ROBUST FEATURE)

In computer vision, speeded up robust features (SURF) is a patented local feature
detector and descriptor. It can be used for tasks such as object recognition, image
registration, classification or 3D reconstruction. It is partly inspired by the scale-
invariant feature transform (SIFT) descriptor. The standard version of SURF is
several times faster than SIFT and claimed by its authors to be more robust against
different image transformations than SIFT. To detect interest points, SURF uses an
integer approximation of the determinant of Hessian blob detector, which can be
computed with 3 integer operations using a precomputed integral image. Its feature
descriptor is based on the sum of the Haar wavelet response around the point of
interest. These can also be computed with the aid of the integral image.
SURF descriptors have been used to locate and recognize objects, people or faces,
to reconstruct 3D scenes, to track objects and to extract points of interest. SURF was
first presented by Herbert Bay, et al., at the 2006 European Conference on Computer
Vision. An application of the algorithm is patented in the United States. An "upright"
version of SURF (called U-SURF) is not invariant to image rotation and therefore
faster to compute and better suited for application where the camera remains more
or less horizontal. The image is transformed into coordinates,

Dept. of AIML, BKIT Bhalki 2022-2023 Page 45

 Artificial Intelligence

using the multi-resolution pyramid technique, to copy the original image with
Pyramidal Gaussian or Laplacian Pyramid shape to obtain an image with the same
size but with reduced bandwidth. This achieves a special blurring effect on the
original image, called Scale-Space and ensures that the points of interest are scale
invariant.

SIFT(SCALE INVARIANT FEATURE TRANSFORM)

Matching features across different images in a common problem in computer vision.
When all images are similar in nature (same scale, orientation, etc) simple corner
detectors can work. But when you have images of different scales and rotations, you
need to use the Scale Invariant Feature Transform.

Now that's some real robust image matching going on. The big rectangles mark
matched images. The smaller squares are for individual features in those regions.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 46

 Artificial Intelligence

Note how the big rectangles are skewed. They follow the orientation and perspective
of the object in the scene.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 47

 Artificial Intelligence

Chapter 8

STEPS TO THE ALGORITHM

 SIFT is quite an involved algorithm. It has a lot going on and can become confusing,
So I've split up the entire algorithm into multiple parts. Here's an outline of what
happens in SIFT.
 Constructing a scale space This is the initial preparation. You create internal
representations of the original image to ensure scale invariance. This is done by
generating a "scale space".
 LoG Approximation The Laplacian of Gaussian is great for finding interesting
points (or key points) in an image. But it's computationally expensive. So we cheat
and approximate it using the representation created earlier.
 Finding keypoints With the super fast approximation, we now try to find key points.
These are maxima and minima in the Difference of Gaussian image we calculate in
step 2
 Get rid of bad key points Edges and low contrast regions are bad keypoints.
Eliminating these makes the algorithm efficient and robust. A technique similar to
the Harris Corner Detector is used here.
 Assigning an orientation to the keypoints An orientation is calculated for each key
point. Any further calculations are done relative to this orientation. This effectively
cancels out the effect of orientation, making it rotation invariant.
 Generate SIFT features Finally, with scale and rotation invariance in place, one more
representation is generated. This helps uniquely identify features. Lets say you have
50,000 features. With this representation, you can easily identify the feature you're
looking for (say, a particular eye, or a sign board). That was an overview of the
entire algorithm. Over the next few days, I'll go through each step in detail.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 48

 Artificial Intelligence

Problem statement:
The main problem is detection of authentication person enter biometric. So, we
reduce these types of problems by this project.

Objective:
The main objective of the project is detect weather person is thief or not based on
biometric of finger. For the best application we are using region of interest and CNN.
Using this techniques we can detect easily.

Existing methods:
• Support vector machine

• Conversion

• Histogram

Advantages:
• More security

• More accuracy

Dept. of AIML, BKIT Bhalki 2022-2023 Page 49

 Artificial Intelligence

Chapter 9

PROCESS I\P , O\P & SCOPE

Finger Vein Recognition:

• Biometric authentication using finger vein patterns.
• Highly secure and accurate.
• Difficult to replicate or forge.
Non-Invasive and Hygienic:
• Does not require physical contact with a device.
• Offers a hygienic alternative to other biometric methods.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 50

 Artificial Intelligence

Chapter 10

REFERENCES

• S. Marcel, M. S. Nixon, and S. Z. Li, Handbook of Biometric AntiSpoofing:

Trusted Biometrics Under Spoofing Attacks. Springer Publishing Company,
Incorporated, 2014.

• D. Menotti, G. Chiachia, A. Pinto, W. R. Schwartz, H. Pedrini, A. X. Falco,

and A. Rocha, “Deep representations for iris, face, and fingerprint spoofing
detection,” IEEE Transactions on Information Forensics and Security, vol. 10,
no. 4, pp. 864–879, April 2015.

• A. Kumar and Y. Zhou, “Human identification using finger images,” IEEE

Trans. on Image Proc., vol. 21, no. 4, pp. 2228–2244, April 2012.

• A. Kumar and K. V. Prathyusha, “Personal authentication using hand vein

triangulation and knuckle shape,” IEEE Transactions on Image Processing,
vol. 18, no. 9, pp. 2127–2136, Sept 2009.

• Chat-gpt(2.0)

• Google.

Dept. of AIML, BKIT Bhalki 2022-2023 Page 51