Scribd
Upload
19 views

Keywords-Image Segmentation Region-Based Edge Detection Clustering Weakly

Image segmentation is a key technique in computer vision and image processing that is used to partition images into meaningful regions. It helps separate foreground and background regions for accurate analysis and is applied in medical imaging, face recognition, and target tracking. This document provides a survey of various image segmentation techniques, including region-based, edge detection, clustering, and weakly-supervised learning approaches. It also compares different segmentation methods and analyzes them in detail.

Uploaded by

Abhinav Choudhary
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
19 views

Keywords-Image Segmentation Region-Based Edge Detection Clustering Weakly

Image segmentation is a key technique in computer vision and image processing that is used to partition images into meaningful regions. It helps separate foreground and background regions for accurate analysis and is applied in medical imaging, face recognition, and target tracking. This document provides a survey of various image segmentation techniques, including region-based, edge detection, clustering, and weakly-supervised learning approaches. It also compares different segmentation methods and analyzes them in detail.

Uploaded by

Abhinav Choudhary
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Abstract

Image segmentation has a key role in computer vision and image processing. The
technology of image segmentation is widely used in medical image processing,
face recognition, Target Tracking etc[1]. The current image segmentation
techniques include region-based segmentation, edge detection segmentation,
segmentation based on clustering, segmentation based on weakly-supervised
learning in CNN, etc[3]. To be simple, segmentation is nothing but partitioning an
image. An image consists of foreground and background regions. Segmentation
helps in separating these two regions for accurate analysis. Many techniques have
been developed in recent years[4]. This project deals with the detailed survey on
various image segmentation techniques involved in image processing applications.
The comparison between the different image segmentation techniques are also
illustrated

Keywords- image segmentation; region-based; edge detection; clustering; weakly-


supervised; CNN
Introduction

Image segmentation is one of the stepping stone of image processing techniques.


Image processing is to process the image information to meet the human visual
psychological or application needs. In image processing research and applications,
people often only interested in certain parts of the image, these parts are frequently
called target or prospects, which generally correspond to a specific area with the
unique nature in the image. The purpose of image segmentation is to divide the
image into regions with different characteristics and extract the interested goals
every image is a set of pixels and the process of dividing or partitioning that pixel
on the basis of similar characteristics is known as segmentation[6].

There are two categories of image segmentation techniques, i.e., classical and non-
classical approaches. Classical approaches define the filtering and statistical
techniques. Some classical approaches are edge detection based or boundary based
techniques, thresholding based techniques, region-based techniques, morphological
techniques, normalized cut-a graph-theoretic approach, k-means algorithm based
approaches etc. The non-classical approaches define the fuzzy-neuro-genetic
paradigm or its content is used with features for real-time application[5].

There are many commonly used image segmentation algorithms. But at present,
from the international image segmentation method, the specific operation of the
process of segmentation method is very diverse and complex, and there is no
recognized a unified standard. The comparison between the different image
segmentation techniques and there detailed analysis is illustrated in this project.

You might also like