Bütünsel ve Bölge Bazlı Yüz Kalıplarının Birleştirilmesi Yoluyla Cinsiyet Sınıflandırması

Öz

Bu çalışmada, evrensel ve bölgesel yüz görünüşlerini skor seviyesi birleştirme ve öznitelik seviyesi birleştirme yoluyla bir araya getirmek için güçlü bir cinsiyet tahmin sistemi önerilmektedir. Cinsiyet sınıflandırmasında yüz özniteliklerini çıkarmak için, İkili İstatistiksel Görüntü Öznitelikleri (BSIF) yaklaşımı yüz görüntülerine bütünsel ve bölgesel olarak uygulanmıştır. Ardından çıkarılan öznitelikler bölgesel bilgilerin öznitelik seviyesi birleştirmesi düzeyinde bir araya getirilir, Optimize edilmiş öznitelik alt kümesi, Parçacık Sürü Optimizasyonu (PSO) yöntemi kullanılarak seçilir. Son olarak, bütünsel ve bölgesel bilgiler, cinsiyet sınıflandırması için nihai skorları üretmek amacıyla skor seviyesi birleştirme seviyesinde bir araya getirilir. Bu çalışma, skor seviyesi birleştirme için Ağırlıklı Toplam (WS) kuralı stratejisini kullanmaktadır. Deneysel sonuçlar, önerilen cinsiyet sınıflandırma sisteminin geçerliliğini test etmek amacıyla Multiple Biometric Grand Challenge (MBGC) ve CASIA-Iris-Distance veritabanlarında, özne-ayrık eğitim ve test değerlendirmesi dikkate alınarak gerçekleştirilmiştir. Çalışmanın deneysel sonuçları cinsiyet tahmin sisteminin başarılı olduğunu göstermiştir.

Anahtar Kelimeler

• Cinsiyet sınıflandırması
• Bölgesel BSIF
• Bilgi kaynaşımı
• Optimize edilmiş öznitelik seçimi

Gender Classification through Fusion of Holistic and Region-based Facial Patterns

Öz

In this study, a robust gender prediction system is proposed to fuse global and regional facial representations through score and feature level fusion. In order to extract facial features for gender classification, Binarized Statistical Image Features (BSIF) approach is applied on holistic and regional features of face images. The extracted features are then concatenated to combine the region-based information at feature level fusion. Then the optimized sub-set of features is selected using Particle Swarm Optimization (PSO) method. Finally, the holistic and regional features are combined at score level fusion to produce the final set of scores for gender classification. This study applies Weighted Sum (WS) rule strategy for score level fusion. The experimental results are performed on Multiple Biometric Grand Challenge (MBGC) and CASIA-Iris-Distance databases with consideration of subject-disjoint training and testing evaluation to testify the validity of the proposed gender classification system. The experimental results of the study demonstrate the success of the proposed scheme for gender prediction.

Anahtar Kelimeler

• Gender classification
• Region-based BSIF
• Information fusion
• Optimized feature selection

Kaynakça

1. 1. Swaminathan, A., Chaba, M., Sharma, D.K., Chaba, Y., 2020. Gender Classification Using Facial Embeddings: A Novel Approach. Procedia Computer Science. 167, 2634-2642.
2. 2. Khan, A., Gour, B., 2013. Gender Classification Technique Based on Facial Features Using Neural Network. International Journal of Computer Science and Information Technologies, 4(6), 839-843.
3. 3. Zhang, C., Ding, H., Shang, Y., Shao, Z., Fu, X., 2018. Gender Classification Based on Multiscale Facial Fusion Feature. Mathematical Problems in Engineering, 1-6.
4. 4. Khan, A.R., Doosti, F., Karimi, M., Harouni, M., Tariq, U., Fati, S.M., AliBahaj, S., 2021. Authentication Through Gender Classification from Iris Images Using Support Vector Machine. Microscopy Research and Technique, 84(11), 2666-2676.
5. 5. Xie, Z., Guo, Z., Qian, C., 2018. Palmprint Gender Classification by Convolutional Neural Network. IET-Computer Vision, 12(4), 476-483.
6. 6. Kruti, R., Patil, A., Gornale, S.S., 2019. Fusion of Local Binary Pattern and Local Phase Quantization Features Set for Gender Classification Using Fingerprints. International Journal of Computer Sciences and Engineering, 7(1), 22-29.
7. 7. Eskandari, M., Sharifi, O., 2019. Effect of Face and Ocular Multimodal Biometric Systems on Gender Classification. IET-Biometrics, 8(4), 243-248.
8. 8. Mukherjee, R., Bera, A., Bhattacharjee, D., Nasipuri, M., 2021. Human Gender Classification Based on Hand Images Using Deep Learning. In: International Symposium on Artificial Intelligence. Cham: Springer Nature Switzerland, 2022, 314-324.

9. 9. Xie, J., Zhang, L., You, J., Zhang, D., Qu, X., 2012. A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification. Sensors, 12(7), 8691-8709.
10. 10. Gornale, S.S., Patil, A., Ramchandra, K., 2020. Multimodal Biometrics Data Analysis for Gender Estimation Using Deep Learning. International Journal of Data Science and Analysis, 6(2), 64-68.
11. 11. AlShaye, N., AlMoajil, L., Abdullah-Al-Wadud, M., 2022. A Gender Recognition System Based on Facial Image. 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC), IEEE. 10-12 May 2022, Cairo, Egypt, 21-25.
12. 12. SheikhFathollahi, M., Heidari, R., 2022. Gender Classification from Face Images Using Central Difference Convolutional Networks. International Journal of Multimedia Information Retrieval 11(4), 695-703.
13. 13. Ramya, R., Anandh, A., Muthulakshmi, K., Venkatesh, S., 2022. Gender Recognition from Facial Images Using Multichannel Deep Learning Framework. Machine Learning for Biometrics. Academic Press, 105-128.
14. 14. Kannala, J., Rahtu, E., 2012. Bsif: Binarized Statistical Image Features. In Proceedings of the 21st International Conference on Pattern Recognition (ICPR), IEEE, 11-15 November 2012, Tsukuba, Japan, 1363- 1366.
15. 15. Kennedy, J., Eberhart, R., 1995. Particle Swarm Optimization. In: Proceedings of ICNN'95-International Conference on Neural Networks. IEEE, 4, 1942-1948, 27 November-01 December 1995, Perth, WA, Australia.
16. 16. Phillips, P.J., Flynn, P.J.J., Beveridge, R., Scruggs, W.T., O’toole, A.J., Bolme, D., Bowyer, K.W., Draper, B.A., Givens G.H., Lui, M., Sahibzada, H., Scallan III, A.J., Weimer, S., 2009. Overview of the Multiple Biometrics Grand Challenge. Advances in Biometrics: Third International Conference (ICB 2009), 2-5 June 2009, Alghero, Italy, 705-714.
17. 17. Biometrics Ideal Test, http://www.cbsr.ia.ac.cn /china/Iris%20Databases%20CH.asp, Access date: 12.05.2014.
18. 18. Hyvarinen, A., Oja. E., 2000. Independent Component Analysis: Algorithms and Applications. Neural Networks, 13(4-5), 411-430.
19. 19. Jain, A.K., Ross, A., 2002. Learning User-Specific Parameters in a Multibiometric System. International Conference on Image Processing. IEEE. 22-25 September 2002, Rochester, NY, USA, 1, 1.
20. 20. NASA, 2022. https://www.nasa.gov/mission_ pages/landsat/overview/index.html, Access date: 05.01.2022.
21. 21. Ogashawara, I., Curtarelli, M.P., Ferreira, C.M., 2013. The use of Optical Remote Sensing for Mapping Flooded Areas. Int. Journal of Engineering Research and Application, 3(5), 1956-1960.
22. 22. Suwarsono Nugroho, J.T., Wiweka, 2013. Identification of Inundated Area Using Normalized Difference Water Index (NDWI) on Lowland Region of Java Island. International Journal of Remote Sensing and Earth Sciences, 10(2), 114-121.
23. 23. Rotjanakusol, T., Laosuwan, T., 2018. Inundation Area Investigation Approach Using Remote Sensing Technology on 2017 Flooding in Sakon Nakhon Province Thailand. Studia Universitatis Vasile Goldis, Seria Stiintele Vietii (Life Sciences Series), 28(4), 159-166.
24. 24. Silas, M.Y., Taofeek, S.A., Adewale, A.K., Adeyemi, S.S., Victor, D., 2019. Flood Inundation and Monitoring Mapping in Nigeria Using Modis Surface Reflectance. Journal of Scientific Research & Reports, 22(1), 1-12.
25. 25. Kashyap, M., Bhatt, C.M., Rawat, J.S., Suthar, K., 2021. Application of Sentinel 2 Data for Extraction of Flood Inundation Along Ganga River, Bihar. International Journal of Engineering Research in Mechanical and Civil Engineering (IJERMCE), 10(3), 47-52.
26. 26. McFeeters, S., 1996. The use of Normalized Difference Water Index (NDWI) in the Delineation of Open Water Features. International Journal of Remote Sensing, 17(7), 1425-1432.