Exploration of image level classification based on semantic segmentation
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 interpre...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | MATEC Web of Conferences |
| Online Access: | https://www.matec-conferences.org/articles/matecconf/pdf/2024/04/matecconf_icmed2024_01165.pdf |
| _version_ | 1797248921013059584 |
|---|---|
| author | Santhosh Kumar Ch.N. Pavan Kumar P. Lakshmi Deepthi N. Aswani Reddy P. Sujana Y. |
| author_facet | Santhosh Kumar Ch.N. Pavan Kumar P. Lakshmi Deepthi N. Aswani Reddy P. Sujana Y. |
| author_sort | Santhosh Kumar Ch.N. |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-24T20:22:16Z |
| format | Article |
| id | doaj.art-ff75467c04aa4f18ab5061fdbed76da7 |
| institution | Directory Open Access Journal |
| issn | 2261-236X |
| language | English |
| last_indexed | 2024-04-24T20:22:16Z |
| publishDate | 2024-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | MATEC Web of Conferences |
| spelling | doaj.art-ff75467c04aa4f18ab5061fdbed76da72024-03-22T08:05:26ZengEDP SciencesMATEC Web of Conferences2261-236X2024-01-013920116510.1051/matecconf/202439201165matecconf_icmed2024_01165Exploration of image level classification based on semantic segmentationSanthosh Kumar Ch.N.0Pavan Kumar P.1Lakshmi Deepthi N.2Aswani Reddy P.3Sujana Y.4Department of Computer Science and Engineering (DS), Institute of Aeronautical EngineeringDepartment of Computer Science and Engineering (DS), Vardhaman College of EngineeringDepartment of Computer Science and Engineering (DS), Institute of Aeronautical EngineeringDepartment of Computer Science and Engineering (DS), Institute of Aeronautical EngineeringDepartment of Computer Science and Engineering (DS), Institute of Aeronautical EngineeringSemantic 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.https://www.matec-conferences.org/articles/matecconf/pdf/2024/04/matecconf_icmed2024_01165.pdf |
| spellingShingle | Santhosh Kumar Ch.N. Pavan Kumar P. Lakshmi Deepthi N. Aswani Reddy P. Sujana Y. Exploration of image level classification based on semantic segmentation MATEC Web of Conferences |
| title | Exploration of image level classification based on semantic segmentation |
| title_full | Exploration of image level classification based on semantic segmentation |
| title_fullStr | Exploration of image level classification based on semantic segmentation |
| title_full_unstemmed | Exploration of image level classification based on semantic segmentation |
| title_short | Exploration of image level classification based on semantic segmentation |
| title_sort | exploration of image level classification based on semantic segmentation |
| url | https://www.matec-conferences.org/articles/matecconf/pdf/2024/04/matecconf_icmed2024_01165.pdf |
| work_keys_str_mv | AT santhoshkumarchn explorationofimagelevelclassificationbasedonsemanticsegmentation AT pavankumarp explorationofimagelevelclassificationbasedonsemanticsegmentation AT lakshmideepthin explorationofimagelevelclassificationbasedonsemanticsegmentation AT aswanireddyp explorationofimagelevelclassificationbasedonsemanticsegmentation AT sujanay explorationofimagelevelclassificationbasedonsemanticsegmentation |