Enhanced Semantic Image Segmentation Through Convolutional and Atrous Convolution Techniques

Meghana, H.V. and Ushashree, R. (2024) Enhanced Semantic Image Segmentation Through Convolutional and Atrous Convolution Techniques. Journal of Innovation and Technology, 2024 (41). pp. 1-5. ISSN 2805-5179

	Text joit2024_41.pdf - Published Version Available under License Creative Commons Attribution. Download (194kB)
	Text 630 - Published Version Available under License Creative Commons Attribution. Download (21kB)

Abstract

Enhanced Image content classification has improved dramatically with the advent of CNNs. This paper presents an enhanced method for semantic partitioning through merging traditional convolutional level and atrous (extended) convolution techniques. Our approach takes advantage of the hierarchical feature extraction capabilities of CNNs, while incorporating atrous convolutions to capture multi-scale contextual information without increasing the computational load. The proposed feature combines standard diffraction layers for detailed feature extraction that broadens the perceptive field, thus improving segmentation accuracy, especially on multiscale features Extensive testing on the datasets including PASCAL VOC 2012 and Cityscapes.

Item Type:	Article
Uncontrolled Keywords:	Semantic Image Segmentation, Convolutional Neural Networks (CNNs), Atrous Convolutions, Feature Extraction
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science R Medicine > RA Public aspects of medicine T Technology > T Technology (General)
Depositing User:	Unnamed user with email masilah.mansor@newinti.edu.my
Date Deposited:	12 Dec 2024 09:14
Last Modified:	12 Dec 2024 09:14
URI:	http://eprints.intimal.edu.my/id/eprint/2091

Actions (login required)

View Item