Exploration of image level classification based on semantic segmentation

Author:

Santhosh Kumar Ch.N.,Pavan Kumar P.,Lakshmi Deepthi N.,Aswani Reddy P.,Sujana Y.

Abstract

Semantic segmentation is a fundamental computer vision task where an image is divided into segments, with each segment assigned a class label based on its visual content. The objective is to achieve a pixel-level understanding of the image, enhancing machines' ability to comprehend and interpret visual scenes. This technique finds utility across diverse domains such as autonomous driving, medical image analysis, scene comprehension, and image editing, among others. Traditional per-pixel classification methods often encounter challenges related to class imbalances within segmentation datasets. To address this, a novel approach has been proposed, leveraging human-provided hints or auxiliary training signals derived from contextual modeling in segmentation. Human-in-the-loop techniques are employed to validate subtasks, correcting segmentation errors and enhancing mean Intersection over Union (mIoU) metrics without the need for additional trained parameters.

Publisher

EDP Sciences

Reference18 articles.

1. Badrinarayanan V., Kendall A., and R. Cipolla. Segnet: A deep convolutional encoderdecoder architecture for image segmentation, 2015.

2. Chen C., Papandreou G., Kokkinos I., Murphy K., and Yuille A. L.. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, 2016.

3. A. P, A. Sharma, S. B. M, P. Pavankumar, N. K. Darwante and D. G. V, “Performance Monitoring and Dynamic Scaling Algorithm for Queue Based Internet of Things,” 2022

4. International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), Chennai, India, 2022, pp. 1-7.

5. Deng J., Dong W., Socher R., Li L.-J., Li K., and Fei-Fei L.. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255, 2009.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3