Gender classification: a convolutional neural network approach
An approach using a convolutional neural network (CNN) is proposed for real-time gender classification based on facial images. The proposed CNN architecture exhibits a much reduced design complexity when compared with other CNN solutions applied in pattern recognition. The number of processing layer...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Turkiye Klinikleri Journal of Medical Sciences
2016
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/74139/1/ShanSungLiew2016_Genderclassificationaconvolutionalneural.pdf |
| _version_ | 1796862177016020992 |
|---|---|
| author | Liew, Shan Sung Khalil-Hani, Mohamed Ahmad Radzi, Syafeeza Bakhteri, Rabia |
| author_facet | Liew, Shan Sung Khalil-Hani, Mohamed Ahmad Radzi, Syafeeza Bakhteri, Rabia |
| author_sort | Liew, Shan Sung |
| collection | ePrints |
| description | An approach using a convolutional neural network (CNN) is proposed for real-time gender classification based on facial images. The proposed CNN architecture exhibits a much reduced design complexity when compared with other CNN solutions applied in pattern recognition. The number of processing layers in the CNN is reduced to only four by fusing the convolutional and subsampling layers. Unlike in conventional CNNs, we replace the convolution operation with cross-correlation, hence reducing the computational load. The network is trained using a second-order backpropagation learning algorithm with annealed global learning rates. Performance evaluation of the proposed CNN solution is conducted on two publicly available face databases of SUMS and AT&T. We achieve classification accuracies of 98.75% and 99.38% on the SUMS and AT&T databases, respectively. The neural network is able to process and classify a 32 × 32 pixel face image in less than 0.27 ms, which corresponds to a very high throughput of over 3700 images per second. Training converges within less than 20 epochs. These results correspond to a superior classification performance, verifying that the proposed CNN is an effective real-time solution for gender recognition. |
| first_indexed | 2024-03-05T20:07:37Z |
| format | Article |
| id | utm.eprints-74139 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T20:07:37Z |
| publishDate | 2016 |
| publisher | Turkiye Klinikleri Journal of Medical Sciences |
| record_format | dspace |
| spelling | utm.eprints-741392017-11-28T05:01:13Z http://eprints.utm.my/74139/ Gender classification: a convolutional neural network approach Liew, Shan Sung Khalil-Hani, Mohamed Ahmad Radzi, Syafeeza Bakhteri, Rabia TK Electrical engineering. Electronics Nuclear engineering An approach using a convolutional neural network (CNN) is proposed for real-time gender classification based on facial images. The proposed CNN architecture exhibits a much reduced design complexity when compared with other CNN solutions applied in pattern recognition. The number of processing layers in the CNN is reduced to only four by fusing the convolutional and subsampling layers. Unlike in conventional CNNs, we replace the convolution operation with cross-correlation, hence reducing the computational load. The network is trained using a second-order backpropagation learning algorithm with annealed global learning rates. Performance evaluation of the proposed CNN solution is conducted on two publicly available face databases of SUMS and AT&T. We achieve classification accuracies of 98.75% and 99.38% on the SUMS and AT&T databases, respectively. The neural network is able to process and classify a 32 × 32 pixel face image in less than 0.27 ms, which corresponds to a very high throughput of over 3700 images per second. Training converges within less than 20 epochs. These results correspond to a superior classification performance, verifying that the proposed CNN is an effective real-time solution for gender recognition. Turkiye Klinikleri Journal of Medical Sciences 2016 Article PeerReviewed application/pdf en http://eprints.utm.my/74139/1/ShanSungLiew2016_Genderclassificationaconvolutionalneural.pdf Liew, Shan Sung and Khalil-Hani, Mohamed and Ahmad Radzi, Syafeeza and Bakhteri, Rabia (2016) Gender classification: a convolutional neural network approach. Turkish Journal of Electrical Engineering and Computer Sciences, 24 (3). pp. 1248-1264. ISSN 1300-0632 https://www.scopus.com/inward/record.uri?eid=2-s2.0-84963815143&doi=10.3906%2felk-1311-58&partnerID=40&md5=c9581d7d53fd3982f2e0e1cab7554d03 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Liew, Shan Sung Khalil-Hani, Mohamed Ahmad Radzi, Syafeeza Bakhteri, Rabia Gender classification: a convolutional neural network approach |
| title | Gender classification: a convolutional neural network approach |
| title_full | Gender classification: a convolutional neural network approach |
| title_fullStr | Gender classification: a convolutional neural network approach |
| title_full_unstemmed | Gender classification: a convolutional neural network approach |
| title_short | Gender classification: a convolutional neural network approach |
| title_sort | gender classification a convolutional neural network approach |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.utm.my/74139/1/ShanSungLiew2016_Genderclassificationaconvolutionalneural.pdf |
| work_keys_str_mv | AT liewshansung genderclassificationaconvolutionalneuralnetworkapproach AT khalilhanimohamed genderclassificationaconvolutionalneuralnetworkapproach AT ahmadradzisyafeeza genderclassificationaconvolutionalneuralnetworkapproach AT bakhterirabia genderclassificationaconvolutionalneuralnetworkapproach |