An Optimized Semantic Segmentation Framework for Human Skin Detection
The study incorporating optimization strategy in semantic segmentation is underexplored in dermatology. Existing approaches used complex and various heuristic designs of image processing algorithms and deep models customized for skin detection problems. This paper demonstrates Particle Swarm Optimi...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
uthm
2024
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/12375/1/J17834_a00eabd7f0cf339e5495770d13767f7f.pdf http://eprints.uthm.edu.my/12375/ https://doi.org/10.30880/ijie.2024.16.01.024 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833419778033713152 |
|---|---|
| author | Huong, Audrey Ngu, Xavier |
| author_facet | Huong, Audrey Ngu, Xavier |
| author_sort | Huong, Audrey |
| building | UTHM Library |
| collection | Institutional Repository |
| content_provider | Universiti Tun Hussein Onn Malaysia |
| content_source | UTHM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | The study incorporating optimization strategy in semantic
segmentation is underexplored in dermatology. Existing approaches used complex and various heuristic designs of image processing algorithms and deep models customized for skin detection problems. This paper demonstrates Particle Swarm Optimization (PSO)- incorporated AlexNet framework for the skin segmentation task. The results from testing the trained model are promising. The model produced satisfactory performances even with a strict split of 50 %,
confirming the high efficiency of the proposed framework. The mean Jaccard index and Dice similarity measures evaluated between the annotated and predicted mask ranged from 0.80 to 0.93 in the binary classification of pixels as “skin” versus “background”. This work identified that the location and color variability of skin pixels in the training data are crucial to obtaining a good skin segmentation performance. Further works that can be explored in this area include adopting a robust preprocessing strategy to increase data variability and improve model generalization or implementing an optimizationenhanced strategy on the existing segmentation models for comparison. |
| format | Article |
| id | my.uthm.eprints-12375 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | en |
| publishDate | 2024 |
| publisher | uthm |
| record_format | eprints |
| spelling | my.uthm.eprints-123752025-05-05T04:55:13Z http://eprints.uthm.edu.my/12375/ An Optimized Semantic Segmentation Framework for Human Skin Detection Huong, Audrey Ngu, Xavier QA Mathematics The study incorporating optimization strategy in semantic segmentation is underexplored in dermatology. Existing approaches used complex and various heuristic designs of image processing algorithms and deep models customized for skin detection problems. This paper demonstrates Particle Swarm Optimization (PSO)- incorporated AlexNet framework for the skin segmentation task. The results from testing the trained model are promising. The model produced satisfactory performances even with a strict split of 50 %, confirming the high efficiency of the proposed framework. The mean Jaccard index and Dice similarity measures evaluated between the annotated and predicted mask ranged from 0.80 to 0.93 in the binary classification of pixels as “skin” versus “background”. This work identified that the location and color variability of skin pixels in the training data are crucial to obtaining a good skin segmentation performance. Further works that can be explored in this area include adopting a robust preprocessing strategy to increase data variability and improve model generalization or implementing an optimizationenhanced strategy on the existing segmentation models for comparison. uthm 2024 Article PeerReviewed text en http://eprints.uthm.edu.my/12375/1/J17834_a00eabd7f0cf339e5495770d13767f7f.pdf Huong, Audrey and Ngu, Xavier (2024) An Optimized Semantic Segmentation Framework for Human Skin Detection. INTERNATIONAL JOURNAL OF INTEGRATED ENGINEERING, 16 (1). pp. 293-300. ISSN 2600-7916 https://doi.org/10.30880/ijie.2024.16.01.024 |
| spellingShingle | QA Mathematics Huong, Audrey Ngu, Xavier An Optimized Semantic Segmentation Framework for Human Skin Detection |
| title | An Optimized Semantic Segmentation Framework for
Human Skin Detection |
| title_full | An Optimized Semantic Segmentation Framework for
Human Skin Detection |
| title_fullStr | An Optimized Semantic Segmentation Framework for
Human Skin Detection |
| title_full_unstemmed | An Optimized Semantic Segmentation Framework for
Human Skin Detection |
| title_short | An Optimized Semantic Segmentation Framework for
Human Skin Detection |
| title_sort | optimized semantic segmentation framework for
human skin detection |
| topic | QA Mathematics |
| url | http://eprints.uthm.edu.my/12375/1/J17834_a00eabd7f0cf339e5495770d13767f7f.pdf http://eprints.uthm.edu.my/12375/ https://doi.org/10.30880/ijie.2024.16.01.024 |
| url_provider | http://eprints.uthm.edu.my/ |