You are on page 1of 12

IMAGE

SEGMENTATION
Under the guidance of: By:
Mr. M Sai Prasad B.Pragnya -19QK1A0518
CSE Dept D.Sahithya-19QK1A0533
K.Pranay-19QK1A0539
K.Avinash-19QK1A0546
M.Pradeep-19QK1A0548
CONTENTS
 ABSTRACT
 LITERATURE SURVEY
 ANALYSIS
 METHODOLOGIES
 MODULE DESCRIPITION
 SYSTEM ARCHITECTURE
 CONCLUSION
 QUESTIONS AND ANSWERS
ABSTRACT
 Segmentation is considered as one of the main steps in image processing.
 It divides a digital image into multiple regions in order to analyze them.
 It is also used to distinguish different objects in the image.
 Several image segmentation techniques have been developed by the researchers
in order to make images smooth and easy to evaluate.
 Image segmentation is a method in which a digital image is broken down into
various subgroups called Image Segments which helps in reducing the complexity
of the image to make further processing or analysis of the image simpler.
 Segmentation in simple terms is assigning labels to pixels. All picture elements or
pixels belonging to the same category have a common label assigned to them.
LITERATURE SURVEY
S.NO TITLE AUTHOR YEAR 1. ALGORITHM
1. Edge Based Image Fernando C. 2008
Segmentation Monteiro 1. K-Means
Clustering

2. Region Based Image D. Barbosa 2012 1.Morphological


Segmentation algorithm

2. Multi Class
Normalized Cut
Method

3. Threshold Based Image Shiping Zhu 2010 1. Fast Marching


Segmentation Method
METHODOLOGIES
Mask R-CNN :
 Mask R-CNN is a state of the art model for instance segmentation, developed on
top of Faster R-CNN.
  Faster R-CNN is a region-based convolutional neural networks, that returns
bounding boxes for each object and its class label with a confidence score.
 Object Instance Segmentation is a recent approach that gives us best of both
worlds.
 It integrates object detection task where the goal is to detect object class along
with bounding box prediction in an image and semantic segmentation task, which
classifies each pixel into pre-defined categories.
 Thus, it enables us to detect objects in an image while precisely segmenting a
mask for each object instance.
K-Means Clustering :
 Image segmentation is the classification of an image into different groups.
 Many kinds of research have been done in the area of image segmentation using
clustering.
 K-means is a centroid-based clustering algorithm, where we calculate the distance
between each data point and a centroid to assign it to a cluster.
 The goal is to identify the K number of groups in the dataset.
MODULE DESCRIPTION:
 To understand Mask R-CNN, let's first discus architecture of Faster R-CNN that
works in four modules:
1. Backbone Network:
There are two kinds of backbone networks .They are ResNet architecture
(ResNet-C4) another is ResNet with feature pyramid network.  The standard ResNet
architecture was similar to that of Faster R-CNN but the ResNet-FPN has proposed
some modification. This consists of a multi-layer RoI generation.
2. Region Proposal Network:
All the convolution feature map that is generated by the previous layer is passed
through a 3*3 convolution layer. The output of this then passed into two parallel
branches that determine the objectness score and regress the bounding box
coordinates.
3. Mask Representation:
A mask contains spatial information about the object. Thus, unlike the classification and
bounding box regression layers, we could not collapse the output to fully connected
layer to improve since it requires pixel-to-pixel correspondence from the above layer. 
4. RoI Align:
RoI align has same motive as of RoI pool, to generate the fixed size regions of interest
from region proposals.
SYSTEM ARHITECTURE
CONCLUSION

We used a pre-trained model and applied a mask R-CNN to it, our findings are that this is the
best model for instance segmentation. K-means clustering has been employed and we were
able to detect the clusters present in the grayscale image after a modification which has been
shown above. This is the best algorithm to segment a desired object from its background in
the image. Since there are a vast number of resources in this growing field of deep learning,
we have many options to choose a perfect model which best suits our requirements. There is
a lot of scope to research and explore.
QUESTION AND ANSWERS
THANK YOU

You might also like