Advancements in image segmentation: An analysis of conventional and ANN based methods

View at publisher Summarise with VIRAT
Authors: Toran Lal Sahu, Suman Kumar Swarnkar, Yogesh Kumar Rathore
Cited by: 0
References: 42

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The fundamental techniques of image processing are traditional segmentation methods, which provide a variety of ways to divide images according to shape, intensity, edges, areas, and grouping. Every technique has its advantages and works well for various image kinds and segmentation jobs. This article compares ANN-based segmentation utilizing Convolutional Neural Networks (CNNs) with conventional image segmentation methods like thresholding and edge detection, which are prized for their ease of use and effectiveness. Although ANN-based techniques can be opaque and demand huge datasets and processing resources, they are more effective and versatile, making them perfect for complicated imagery and high-accuracy jobs. These cutting-edge methods are extensively employed in autonomous vehicles, satellite analysis, and medical imaging. They perform particularly well in settings with complicated, high-dimensional data when annotated datasets are accessible.

Fields of Study & Subjects

Advanced Neural Network Applications Medical Image Segmentation Techniques Computer Science and Engineering

Publication details

Journal / source
AIP conference proceedings
Volume
3401
Pages
020033–020033
Publication date
1 January 2026
Language
EN