Öz
Appearance
based attribute classification has become a popular research topic. Generally,
these attributes are classified or detected individually and independently.
Then, the obtained individual scores are combined to provide a representation.
However, especially in terms of facial attributes, each extracted piece of
information has influence on each other. In order to assess and analyze this
influence, it is important to have a proper benchmark by taking into
consideration the following three criteria: a) Having different subjects in
training and testing sets, b) Equal
distribution of amount of training data among different setups, c) Fairness in
testing sets. With these criteria in mind, we prepared an experimental setup
using MORPH-II and CACD databases to test the influence of age and gender on
each other and their effect to face recognition. Experimental results have shown
that by utilizing the correlation between the face modalities, classification
accuracies can be improved.
Anahtar Kelimeler
Gender Classification Age Estimation Face Recognition Correlation between Face Modalities
Kaynakça
- Wild, H. A., Barrett, S. E., Spence, M. J., O’Toole, A. J., Cheng, Y. D., Brooke, J. 2012. Recognition and sex categorization of adults and childrens faces: examining performance in the absence of sex-stereotyped cues, Journal of Experimental Child Psychology, Cilt 77, s. 269–291.
- Golomb, B., Lawrence, D., Sejnowski, T. 1991. Sexnet: A neural network identifies sex from human faces, Advances in Neural Information Processing Systems 3, s. 572–577.
- Gutta, S., Wechsler, H., Phillips, P. 1998. Gender and ethnic classification, IEEE International Workshop on Automatic Face and Gesture Recognition, s. 194–199.
- Moghaddam, B., Yang, M. H. 2002. Learning gender with support faces, IEEE Transactions on Pattern Analysis and Machine Intelligence, Cilt 25, No. 5, s. 707–711.
- Baluja S., Rowley, H. A. 2007. Boosting sex identification performance, Intl. Journal of Computer Vision, Cilt 71, No. 1, s. 111–119.
- Fu, Y., Huang, T. S. 2009. Human age estimation with regression on discriminative aging manifold, IEEE Transactions on Multimedia, Cilt 10, No. 4, s. 578–584.
- Guo, G., Fu, Y., Dyer, C.R., Huang, T.S. 2008. Image-based human age estimation by manifold learning and locally adjusted robust regression, IEEE Transactions on Image Processing, Cilt 17, No. 7, s. 1178–1188.
- FG-NET websayfası: http://www-prima.inrialpes.fr/FGnet/html/benchmarks.html (Erişim Tarihi: 29.01.2018).
- Ueki, K., Hayashida, T., Kobayashi, T. 2006. Subspace-base age-group classification using facial images under various lighting conditions, IEEE Intl. Conference on Automatic Face and Gesture Recognition.
- Saatci, Y., Town, C. 2006. Cascaded Classification of Gender and Facial Expression using Active Appearance Models, IEEE Intl. Conference on Automatic Face and Gesture Recognition, s. 393-400.
- Gao, W., Ai, H. 2009. Face gender classification on consumer images in a multiethnic environment, Advances in Biometrics, s. 169–178.
- Guo, G., Dyer, C., Fu, Y., Huang, T. S. 2009. Is gender recognition influenced by age?, IEEE Workshop on Human Computer Interaction.
- Guo, G., Mu, G., Fu, Y., Dyer, C., Huang, T. 2009. A study on automatic age estimation using a large database, Intl. Conference on Computer Vision, s. 1986-1991.
- Guo, G., Mu, G. 2010. Human Age Estimation: What is the Influence Across Race and Gender?, IEEE International Workshop on Analysis and Modeling of Faces and Gestures.
- Guo, G., Mu, G. 2010. A Study of Large-Scale Ethnicity Estimation with Gender and Age Variations, IEEE Intl. Workshop on Analysis and Modeling of Faces and Gestures.
- Çanak, B., Ekenel, H.K. 2015. Yüz Kiplerinin Birbirleri Üzerine Etkileşiminin Çözümlenmesi, IEEE Sinyal İşleme ve İletişim Uygulamaları Kurultayı.
- Ricanek, K. Jr ,Tesafaye, T. 2006. MORPH: A Longitudinal Image Database of Normal Adult Age-Progression, IEEE Intl. Conf. on Automatic Face and Gesture Recognition. CACD veri kümesi websayfası: http://bcsiriuschen.github.io/CARC/ (Erişim Tarihi: 29.01.2018).
- Ojala, T., Pietikainen, M., Maenpaa, T. 2002. Multiresolution Gray Scale and Rotation Invariant Texture Classification With Local Binary Patterns, IEEE Trans. on Pattern Analysis and Machine Intelligence. Cilt 24, No. 7, s. 971-987.
- Ekenel, H. K., Stiefelhagen, R. 2006. Analysis of Local Appearance-based Face Recognition: Effects of Feature Selection and Feature Normalization”, Computer Vision and Pattern Recognition Workshop.
Öz
Görünümden
yaş, cinsiyet gibi kişiler ile ilgili bilgi çıkarımı popüler bir araştırma
konusu haline gelmiştir. Genellikle bilgi çıkarımı, her bir bilgi kipi için
ayrı ve bağımsız bir şekilde yapılmaktadır. Ancak, özellikle yüz görünümünden
yapılan bilgi çıkarımlarında, her bir bilgi kipinin diğerinin üzerinde etkisi
olduğu gözlemlenmiştir. Bu etkiyi ölçmek ve çözümlemek için doğru şekilde
tasarlanmış bir deney düzeneğine ihtiyaç vardır. Böyle bir deney düzeneğinin şu
üç kriteri sağlaması gerekmektedir: a) Eğitim ve test veri kümelerindeki
kişilerin farklı olması, b) Farklı parametrelere göre hazırlanan düzeneklerdeki
eğitim veri miktarının eşit dağılımlı olması, c) Test veri kümelerinin adil bir
şekilde düzenlenmesi. Çalışmamızda bu kriterleri göz önünde bulundurarak,
MORPH-II ve CACD veri kümelerini kullanarak yaş ve cinsiyet bilgilerinin
birbirleri üzerindeki etkilerini ve yüz tanıma üzerindeki etkilerini ölçmek
için bir deney düzeneği hazırladık. Deneyler sonucu bilgi kipleri arasındaki
ilintilerden yararlanmanın başarımı olumlu etkilediğini gözlemledik.
Anahtar Kelimeler
Cinsiyet Tanıma Yaş Tahmini Yüz Tanıma Yüz Kipleri Arasındaki İlinti
Kaynakça
- Wild, H. A., Barrett, S. E., Spence, M. J., O’Toole, A. J., Cheng, Y. D., Brooke, J. 2012. Recognition and sex categorization of adults and childrens faces: examining performance in the absence of sex-stereotyped cues, Journal of Experimental Child Psychology, Cilt 77, s. 269–291.
- Golomb, B., Lawrence, D., Sejnowski, T. 1991. Sexnet: A neural network identifies sex from human faces, Advances in Neural Information Processing Systems 3, s. 572–577.
- Gutta, S., Wechsler, H., Phillips, P. 1998. Gender and ethnic classification, IEEE International Workshop on Automatic Face and Gesture Recognition, s. 194–199.
- Moghaddam, B., Yang, M. H. 2002. Learning gender with support faces, IEEE Transactions on Pattern Analysis and Machine Intelligence, Cilt 25, No. 5, s. 707–711.
- Baluja S., Rowley, H. A. 2007. Boosting sex identification performance, Intl. Journal of Computer Vision, Cilt 71, No. 1, s. 111–119.
- Fu, Y., Huang, T. S. 2009. Human age estimation with regression on discriminative aging manifold, IEEE Transactions on Multimedia, Cilt 10, No. 4, s. 578–584.
- Guo, G., Fu, Y., Dyer, C.R., Huang, T.S. 2008. Image-based human age estimation by manifold learning and locally adjusted robust regression, IEEE Transactions on Image Processing, Cilt 17, No. 7, s. 1178–1188.
- FG-NET websayfası: http://www-prima.inrialpes.fr/FGnet/html/benchmarks.html (Erişim Tarihi: 29.01.2018).
- Ueki, K., Hayashida, T., Kobayashi, T. 2006. Subspace-base age-group classification using facial images under various lighting conditions, IEEE Intl. Conference on Automatic Face and Gesture Recognition.
- Saatci, Y., Town, C. 2006. Cascaded Classification of Gender and Facial Expression using Active Appearance Models, IEEE Intl. Conference on Automatic Face and Gesture Recognition, s. 393-400.
- Gao, W., Ai, H. 2009. Face gender classification on consumer images in a multiethnic environment, Advances in Biometrics, s. 169–178.
- Guo, G., Dyer, C., Fu, Y., Huang, T. S. 2009. Is gender recognition influenced by age?, IEEE Workshop on Human Computer Interaction.
- Guo, G., Mu, G., Fu, Y., Dyer, C., Huang, T. 2009. A study on automatic age estimation using a large database, Intl. Conference on Computer Vision, s. 1986-1991.
- Guo, G., Mu, G. 2010. Human Age Estimation: What is the Influence Across Race and Gender?, IEEE International Workshop on Analysis and Modeling of Faces and Gestures.
- Guo, G., Mu, G. 2010. A Study of Large-Scale Ethnicity Estimation with Gender and Age Variations, IEEE Intl. Workshop on Analysis and Modeling of Faces and Gestures.
- Çanak, B., Ekenel, H.K. 2015. Yüz Kiplerinin Birbirleri Üzerine Etkileşiminin Çözümlenmesi, IEEE Sinyal İşleme ve İletişim Uygulamaları Kurultayı.
- Ricanek, K. Jr ,Tesafaye, T. 2006. MORPH: A Longitudinal Image Database of Normal Adult Age-Progression, IEEE Intl. Conf. on Automatic Face and Gesture Recognition. CACD veri kümesi websayfası: http://bcsiriuschen.github.io/CARC/ (Erişim Tarihi: 29.01.2018).
- Ojala, T., Pietikainen, M., Maenpaa, T. 2002. Multiresolution Gray Scale and Rotation Invariant Texture Classification With Local Binary Patterns, IEEE Trans. on Pattern Analysis and Machine Intelligence. Cilt 24, No. 7, s. 971-987.
- Ekenel, H. K., Stiefelhagen, R. 2006. Analysis of Local Appearance-based Face Recognition: Effects of Feature Selection and Feature Normalization”, Computer Vision and Pattern Recognition Workshop.
Ayrıntılar
| Birincil Dil | Türkçe |
|---|---|
| Bölüm | Makaleler |
| Yazarlar | |
| Yayımlanma Tarihi | 21 Mayıs 2019 |
| Yayımlandığı Sayı | Yıl 2019 Cilt: 21 Sayı: 62 |
Kaynak Göster
Dokuz Eylül Üniversitesi, Mühendislik Fakültesi Dekanlığı Tınaztepe Yerleşkesi, Adatepe Mah. Doğuş Cad. No: 207-I / 35390 Buca-İZMİR.