Scribd
Upload
9 views25 pages

Explo PPT

The document presents an overview of image segmentation, a crucial operation in computer vision that involves dividing an image into meaningful parts based on criteria like color or texture. It discusses various segmentation algorithms, including traditional methods and advanced deep learning techniques, highlighting architectures such as SegNet, FCN, and U-Net. The goal of segmentation is to simplify image representation for easier analysis and object localization.

Uploaded by

Mukhram yadav
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views25 pages

Explo PPT

The document presents an overview of image segmentation, a crucial operation in computer vision that involves dividing an image into meaningful parts based on criteria like color or texture. It discusses various segmentation algorithms, including traditional methods and advanced deep learning techniques, highlighting architectures such as SegNet, FCN, and U-Net. The goal of segmentation is to simplify image representation for easier analysis and object localization.

Uploaded by

Mukhram yadav
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 25

Project

presentation

Presented by Mukhram yadav


22075049
What is image Segmentation ?

One of the most important operations in Computer Vision is


Segmentation. Image segmentation is the process of dividing an image
into multiple parts or regions that belong to the same class. This task
of clustering is based on specific criteria, for example, color or texture.
This process is also called pixel-level classification. In other words, it
involves partitioning images (or video frames) into multiple segments
or objects.
Objectives
The goal of
segmentation is to
simplify and/or change
the representation of an
image into something
that is more meaningful
and easier to analyze.
Image segmentation is
typically used to locate
objects and boundaries
(lines, curves, etc.) in
images.
Ideal mask image
Semantic image segmentation of aerial drone images. The scene is
parted with every pixel belonging to a specific class, such as
“building”, “road”, or “tree”.
Image Segmentation and
Deep LearniING
Multiple image segmentation algorithms have been developed. Earlier
methods include thresholding, histogram-based bundling, region
growing, k-means clustering, or watersheds. However, more advanced
algorithms are based on active contours, graph cuts, conditional and
Markov random fields, and sparsity-based methods.

Over the last few years, Deep Learning models have introduced a new
segment of image segmentation models with remarkable performance
improvements. Deep Learning based image segmentation models often
achieve the best accuracy rates on popular benchmarks, resulting in a
SEGNEt
SegNet is a convolutional neural network (CNN)
architecture designed for semantic segmentation
in computer vision. Semantic segmentation is the
task of classifying each pixel in an image into a
specific category or class, such as identifying
objects and their boundaries. SegNet is one of the
many deep-learning architectures developed to
tackle this problem.
At the decoder, upsampling and
convolutions are performed. At
the end, there is softmax classifier
for each pixel.
During upsampling, the max
pooling indices at the
corresponding encoder layer are
recalled to upsample as shown
above.
Finally, a K-class softmax
classifier is used to predict the
class for each pixel.
FCN
FCN SUMMARY
1. Replacing all fully-connected leyers with
convolution
2. Upsampling by Backwards convolution , a.k.a
deconvolution (and bilinear upsampling)
3. Applied skip connection to use local ,apperence
information in final layer
UNET
U-Net gets its name from its
architecture. The “U” shaped
model comprises convolutional
layers and two networks. First is
the encoder, which is followed
by the decoder.
Thank
You

You might also like