Project Report: Name: Deepali Tripathi Class: 10 B Roll Number: 7

PROJECT REPORT
ARTIFICIAL INTELLIGENCE
DATA SCIENCE AND COMPUTER VISION (CV)
Name: DEEPALI TRIPATHI

Class: 10th B
Roll number: 7
What is COMPUTER VISION?
----> Computer Vision is about helping machine iterpret
images and videos. It’s the science of interacting with an
object through a digital medium and using sensors to
analyze and understand what it sees. It’s a board
discipline that’s useful for machine translation, pattern
recognition, robotics positioning, 3D reconstruction,
driverless cars, and much.
COMPUTER VISION Today
----> Computer Vision has become a relatively standard
technology in recent years due the advancement of AI.
Many companies use it for product development, sales
operations, marketing campaigns, access control,
security, and more.
Computer Vision has plenty of applications in
healthcare (including pathology), industrial
automations, military use, cybersecurity, automotive
engineering, drone navigation.
How does Computer Vision work?
---->The computer recognizes patterns in images using a
neural network built with many layers.
The first layer takes pixel value and tries to identify the
edges. The next few layers will try to detect simple
shapes with the help of edges. In the end, all of it is put
together to understand the image.
Understanding Convolution operator and CNN
----> What is convolution operation?
Convolution is the process of transforming an image by
applying a similar effect through a special array namely
kernel over each pixel and its local neighbours, across the
entire image.
----> Convolutional Nueral Network (CNN)
The CNN architecture consist of mainly following layers:
i) Convolutional Layer
ii) ReLU Layer (Rectified Linear Activation Function)
iii) Pooling Layer
iv) Fully Connected Layer
.
 Convolutional Layer uses convolution operation on the

images with the help of kernels to produce several features
such as edges, colour, gradient orientations etc.
 ReLU layer rectified activation function that removes the

inputs falling in negative range.
 Pooling Layer down-samples the information of each feature

from each featurefrom each convolutional layer by limited
them to only containing the most necessary data.
 Fully connected layer pre-forms classification based on the

features layer by image flattening, assigning weights,
predicting labels and then finally classifying the images based
What is Data Science?
Data Science is a field that uses scientific methods,
processes, algorithms and system to extract knowledge
and insights from any structural and unstructured data
to apply in AI applications. It combines concept and
methods from various fields of statistics , mathematics,
data analysis, machine learning, computer science and so
forth. Data science uses data analytics to analyse and
gather insights from past.
Applications of Data Science:
 Fraud and Risk Detection
 Health
 Internet search
 Targeted advertising
 Recommender System (RS)
 Airline route planning
 Weather prediction in Agriculture Sector
Data formats/Types used in Data Science:
 CSV (Comma-separated value)
 Spreadsheets
 XLSX
 JSON (JavaScript Object Notation)
 SQL ( Structured Query Language)
 XML (eXtensible Markup Language)
Python Libraries:
1. NumPy Arrays
A numpy array is a table of elements (usually numbers), all of the
same type, indexed by a tuple of integers.NumPy arrays are also
called ndarrays. The ndarrays can be 1-dimensional, 2-
dimensional and multi dimensional.
2. Pandas
Panda is a software library written for the python programming
language for data manipulation and analysis, and is popular
choice for data analysis.
3. Matplotlib
Matplotlib is a python library used for data visualization. Data
visualization is an essential component of data sciences.
KNN (K-Nearest Nieghbour)
KNN algorithm is a supervised learning algorithm that
classifies a new data point into the target class, counting on
the features of its neighbouring data points.
---->KNN modelling works around four parameters:
i) FEATURES. The variables based on which similarity
between two points is calculated.
ii) DISTANCE FUNCTION. Distance metric to be used for
computing similarity between points.
iii) NIEGHBOURHOOD (K). Number of neighbours to
search for.
iv) SCORING FUNCTION. The function which finds the
majority score and class for the query point.
Applications of KNN models
 For Recommender System
 For Looking For Similar Documents
 For Text Categorisation
 For Detecting Frauds
 In Health and Medicine
 For Estimating Soil Water Parameters

Project Report: Name: Deepali Tripathi Class: 10 B Roll Number: 7

Uploaded by

Copyright:

Available Formats

Project Report: Name: Deepali Tripathi Class: 10 B Roll Number: 7

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Project Report: Name: Deepali Tripathi Class: 10 B Roll Number: 7

Uploaded by

Copyright:

Available Formats

PROJECT REPORT

DATA SCIENCE AND COMPUTER VISION (CV)

Name: DEEPALI TRIPATHI

 Convolutional Layer uses convolution operation on the

 ReLU layer rectified activation function that removes the

 Pooling Layer down-samples the information of each feature

 Fully connected layer pre-forms classification based on the

You might also like