Threshold based skin color classification
In this paper, we presented a new formula for skin classification. The proposed formula can overcome sensitivity to noise. Our approach was based multi-skin color Hue, Saturation, and Value color space and multi-level segmentation. Skin regions were extracted using three skin color classes, namely t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Universiti Teknikal Malaysia Melaka
2017
|
| Subjects: |
| _version_ | 1796862536191049728 |
|---|---|
| author | Karamizadeh, S. Abdullah, S. M. Shayan, J. Nooralishahi, P. Bagherian, B. |
| author_facet | Karamizadeh, S. Abdullah, S. M. Shayan, J. Nooralishahi, P. Bagherian, B. |
| author_sort | Karamizadeh, S. |
| collection | ePrints |
| description | In this paper, we presented a new formula for skin classification. The proposed formula can overcome sensitivity to noise. Our approach was based multi-skin color Hue, Saturation, and Value color space and multi-level segmentation. Skin regions were extracted using three skin color classes, namely the Caucasoid, Mongolid and Nigroud. Moreover, in this formula, we adopted Gaussian-based weight k-NN algorithm for skin classification. The experiment result shows that the best result was achieved for Caucasoid class with 84.29 percent fmeasure. |
| first_indexed | 2024-03-05T20:13:06Z |
| format | Article |
| id | utm.eprints-76594 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T20:13:06Z |
| publishDate | 2017 |
| publisher | Universiti Teknikal Malaysia Melaka |
| record_format | dspace |
| spelling | utm.eprints-765942018-04-30T13:36:46Z http://eprints.utm.my/76594/ Threshold based skin color classification Karamizadeh, S. Abdullah, S. M. Shayan, J. Nooralishahi, P. Bagherian, B. T Technology (General) In this paper, we presented a new formula for skin classification. The proposed formula can overcome sensitivity to noise. Our approach was based multi-skin color Hue, Saturation, and Value color space and multi-level segmentation. Skin regions were extracted using three skin color classes, namely the Caucasoid, Mongolid and Nigroud. Moreover, in this formula, we adopted Gaussian-based weight k-NN algorithm for skin classification. The experiment result shows that the best result was achieved for Caucasoid class with 84.29 percent fmeasure. Universiti Teknikal Malaysia Melaka 2017 Article PeerReviewed Karamizadeh, S. and Abdullah, S. M. and Shayan, J. and Nooralishahi, P. and Bagherian, B. (2017) Threshold based skin color classification. Journal of Telecommunication, Electronic and Computer Engineering, 9 (2-3). pp. 131-134. ISSN 2180-1843 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85032980372&partnerID=40&md5=065bf21a14fcdec2c9a73a384535d50a |
| spellingShingle | T Technology (General) Karamizadeh, S. Abdullah, S. M. Shayan, J. Nooralishahi, P. Bagherian, B. Threshold based skin color classification |
| title | Threshold based skin color classification |
| title_full | Threshold based skin color classification |
| title_fullStr | Threshold based skin color classification |
| title_full_unstemmed | Threshold based skin color classification |
| title_short | Threshold based skin color classification |
| title_sort | threshold based skin color classification |
| topic | T Technology (General) |
| work_keys_str_mv | AT karamizadehs thresholdbasedskincolorclassification AT abdullahsm thresholdbasedskincolorclassification AT shayanj thresholdbasedskincolorclassification AT nooralishahip thresholdbasedskincolorclassification AT bagherianb thresholdbasedskincolorclassification |