JSPM’s

RAJARSHI SHAHU COLLEGE OF ENGINEERING

TATHAWADE, PUNE-33
(An Autonomous Institute Affiliated to Savitribai Phule Pune
University, Pune)
DEPARTMENT OF AUTOMATION AND ROBOTICS

MVS Experiment No. 7 Understanding different techniques of Object recognition

Aim: Understanding different techniques of Object recognition

Theory:
Object Recognition
 Object recognition is the technique of identifying the object present in images and
videos.
 It is one of the most important applications of machine learning and deep learning.
 The goal of this field is to teach machines to understand (recognize) the content of an
image just like humans do.
 Object recognition refers to classifying and locating objects in an image with a certain
degree of accuracy.
 It includes image classification, object localization and object detection in its definition.
 Object recognition and object detection are similar techniques, but they differ in the
way they operate.
 In deep learning, object detection comes under the category of object recognition.
 Object detection focuses more on locating and classifying objects in an image, whereas
object recognition mainly focuses on identifying objects.

How Does Object Recognition Work?

There are multiple approaches which can be used for object recognition.
The main two approaches are :
1. Machine Learning
2. Deep Learning
The output results are more or less the same but they differ in method of execution.
 JSPM’s
RAJARSHI SHAHU COLLEGE OF ENGINEERING
TATHAWADE, PUNE-33
(An Autonomous Institute Affiliated to Savitribai Phule Pune
University, Pune)
DEPARTMENT OF AUTOMATION AND ROBOTICS

1. Machine Learning:

 In machine learning, after the images are taken as input an additional step of feature
engineering is executed compared to deep learning.
 The feature engineering needs manual input. Then the features are sent into machine
learning models as in classification model and model training is executed.
 HOG (Histogram of oriented Gradients) feature Extractor and SVM (Support
Vector Machine) model: Before the era of deep learning, it was a state-of-the-art
method for object detection. It takes histogram descriptors of both positive ( images
that contain objects) and negative (images that does not contain objects) samples
and trains our SVM model on that.
 Bag of features model: Just like bag of words considers document as an orderless
collection of words, this approach also represents an image as an orderless
collection of image features. Examples of this are SIFT, MSER, etc.
 Viola-Jones algorithm: This algorithm is widely used for face detection in the
image or real-time. It performs Haar-like feature extraction from the image. This
generates a large number of features. These features are then passed into a boosting
classifier. This generates a cascade of the boosted classifier to perform image
detection. An image needs to pass to each of the classifiers to generate a positive
(face found) result. The advantage of Viola-Jones is that it has a detection time of
2 fps which can be used in a real-time face recognition system.
 JSPM’s
RAJARSHI SHAHU COLLEGE OF ENGINEERING
TATHAWADE, PUNE-33
(An Autonomous Institute Affiliated to Savitribai Phule Pune
University, Pune)
DEPARTMENT OF AUTOMATION AND ROBOTICS

2. Deep Learning:

• The step of feature engineering is not needed as the model itself includes feature
extraction and classification.

• Deep learning models need lesser human input but require higher resources.

• Convolution Neural Network (CNN) is one of the most popular ways of doing object
recognition. It is widely used and most state-of-the-art neural networks used this
method for various object recognition related tasks such as image classification.

• CNN network takes an image as input and outputs the probability of the different
classes. If the object present in the image then it’s output probability is high else the
output probability of the rest of classes is either negligible or low.

• The advantage of Deep learning is that we don’t need to do feature extraction from data
as compared to machine learning.

Challenges of Object Recognition:

Since we take the output generated by last (fully connected) layer of the CNN model is a single
class label. So, a simple CNN approach will not work if more than one class labels are present
in the image.

If we want to localize the presence of an object in the bounding box, we need to try a different
approach that not only outputs the class label but also outputs the bounding box locations.

Object recognition process:

• Object recognition consists of 4 processes:

1. Image classification
2. Object Localization (Tagging)
3. Object detection
4. Image Segmentation
 JSPM’s
RAJARSHI SHAHU COLLEGE OF ENGINEERING
TATHAWADE, PUNE-33
(An Autonomous Institute Affiliated to Savitribai Phule Pune
University, Pune)
DEPARTMENT OF AUTOMATION AND ROBOTICS

1. Image Classification :
 In Image classification, it takes an image as an input and outputs the
classification label of that image with some metric (probability, loss, accuracy,
etc). For Example: An image of a cat can be classified as a class label “cat” or
an image of Dog can be classified as a class label “dog” with some probability.
 Image Classification involves assigning a label to an entire image or photograph

Image classification Examples:

 Labeling an x-ray as cancer or not.
 Assigning a name to a photograph of a face.
 Classifying a handwritten digit

2. Object Localization (Tagging) :

 Image classification with localization aka Object Localization.
 It locates object in an image and represents its presence by bounding box
(drawing the box around the object).
 JSPM’s
RAJARSHI SHAHU COLLEGE OF ENGINEERING
TATHAWADE, PUNE-33
(An Autonomous Institute Affiliated to Savitribai Phule Pune
University, Pune)
DEPARTMENT OF AUTOMATION AND ROBOTICS

Image Classification - Examples

 Labeling an x-ray as cancer or not.

 Assigning a name to a photograph of a face.
 Classifying a handwritten digit.

3. Object Detection :
 Object Detection is a combination of image classification and object localization.
 This task deals with multi-class classification, localization and also with multiple
occurrences of objects in an image.

4. Image Segmentation:
 Image segmentation is a further extension of object detection in which we mark
the presence of an object through pixel-wise masks generated for each object in
the image.
 JSPM’s
RAJARSHI SHAHU COLLEGE OF ENGINEERING
TATHAWADE, PUNE-33
(An Autonomous Institute Affiliated to Savitribai Phule Pune
University, Pune)
DEPARTMENT OF AUTOMATION AND ROBOTICS

 This technique is more granular than bounding box generation because this can
helps us in determining the shape of each object present in the image because
instead of drawing bounding boxes , segmentation helps to figure out pixels that
are making that object. This granularity helps us in various fields such as
medical image processing, satellite imaging, etc. One of the most popular is
Mask R-CNN proposed by K He et al. in 2017.
 There are primarily two types of segmentation:
i. Semantic Segmentation: All objects of same class form a single
classification ,therefore , all objects of same class are coloured by same
colour.
ii. Instance Segmentation: Multiple instances of same class are separate
segments i.e. objects of same class are treated as different. Therefore,
all the objects are coloured with different colour even if they belong to
same class.

Applications:
The above-discussed object recognition techniques can be utilized in many fields such as:
 Driver-less Cars: Object Recognition is used for detecting road signs, other vehicles,
etc.
 Medical Image Processing: Object Recognition and Image Processing techniques can
help detect disease more accurately. Image segmentation helps to detect the shape of
the defect present in the body . For Example, Google AI for breast cancer detection
detects more accurately than doctors.

 Surveillance and Security: such as Face Recognition, Object Tracking, Activity

Recognition, etc.

Conclusion: