Sequential Determination of Personality Attributes from the Face Image Based on Ranked LBP-Features
Keywords:
machine learning, classification by sex, race and age, local binary patterns, support vector method, bootstrapping, support vector based regression
Abstract
An approach to determining personality attributes (sex, race, and age) from the face image is proposed. A distinctive feature of the proposed approach is the use of a sequential procedure, in which the human face images are classified first by sex, then by race within each sex group, and only after that by age within each selected sex-race group. Local binary patterns are used as image description features. The approach implies using only half of the face image in combination with the Adaboost algorithm for identifying the most significant binary patterns, due to which it becomes possible to reduce the space dimensionality of image features by almost an order of magnitude. The face images are classified by sex and race using the standard method of support vectors from the selected most significant features augmented with the a bootstrapping procedure (i.e., learning on "hard" examples). The bootstrapping procedure involves (i) splitting the training set into two parts, (ii) preliminarily shaping the decision function for the first part, (iii) classifying the images in the second part, (iv) highlighting all incorrectly classified objects, and (v) adding the latter to the first part with subsequent re-training. For determining the age more accurately, it is proposed to combine the idea of using cumulative features, the two-stage scheme for restoring regression on the basis of support vectors, and the bootstrapping procedure. In the second stage of constructing the regression, a loss function is used, the sensitivity of which is not constant but may depend on the age value determined in the first stage of regression. Owing to the use of the proposed approach, the classification accuracy has been improved as compared with the known algorithms by 12% for sex, by 15% for race in terms of the Accuracy criterion, and by 2 years for age in terms of the Mean Absolute Error criterion. The accuracy of the proposed approach was studied using both the well-known databases of human face images and using the own database of images set up from the open sources in the Internet.
References
1. Fu Y., Xu Y., Huang T.S. Estimating Human Ages by Manifold Analisys of Face Pictures and Regression On Aging Features // Proc. IEEE Conf. Multimedia and Expo. 2007. Pp. 1383—1386.
2. Cootes T., Edwards G., Taylor C. Active Appearance Models // IEEE Trans. Pattern Analysis and Machine Intelligence. 2001. V. 23 (6). Pp. 681—685.
3. Montillo A., Ling H. Age Regression from Faces Using Random Forests // Proc. IEEE Intern. Conf. Image Proc. 2009. Pp. 2437—2440.
4. Lian H.C., Lu B.L. Multi-view Gender Classification Using Local Binary Patterns and Support Vector Machi- nes // Intern. J. Neural Syst. 2008. V. 17 (6). Pp. 479—487.
5. Shan C. Learning Local Binary Patterns for Gender Classification on Real-world Face Images // Pattern Recognition Lett. 2012. V. 33 (4). Pp. 431—437.
6. Yilionias J., Hadid A., Hong X., Pietikainen M. Age Estimation Using Local Binary Patterns Kernel Density Estimate // Proc. IEEE Intern. Conf. on Image Analysis and Proc. 2013. Pp. 141—150.
7. Hadid A., Pietikainen M. Combining Appearance and Motion for Face and Gender Recognition from Videos// Pattern Recognition Lett. 2009. V. 42 (11). Pp. 2818—2827.
8. Makinen E., Raisamo R. Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces // IEEE Trans. on Pattern Analysis and Machine Intelligence. 2008. V. 30 (3). Pp. 541—548.
9. Moghaddam B., Yang M. Learning Gender with Support Faces // IEEE Trans. on Pattern Analysis and Machine Intelligence. 2002. V. 24 (5). Pp. 707—711.
10. Baluja S., Rowlay H. Boosting Sex Identification Performance // Computer Vision. 2007. V. 71 (1). Pp. 11—19.
11. Han H., Jain A. Age, Gender and Race Estimation from Unconstrained Face Images // MSU Tech. Rep. 2014. MSU-CSE-14-5.
12. Guo G., Mu G., Fu Y., Huang T. Human Age Estimation Using Bio-inspired Features // Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition.2009. Pp. 112—119.
13. Chang K.Y., Chen C.S., Hung Y.P. A Ranking Approach for Human Age Estimation Based on Face Images // Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2010. Pp. 3396—3399.
14. Chang K.Y., Chen C.S., Hung Y.P. Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation // IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2011. Pp. 585—593.
15. Рыбинцев А.В., Лукина Т.М., Конушин В.С., Конушин А.С. Возрастная классификация людей по изображению лица на основе метода ранжирования и локальных бинарных шаблонов // Системы и средства информатики. 2013. T. 23 (2). C. 48—59.
16. Laptev I. Improvements of Object Detection Using Boosted Histograms // Image and Vision Computing. 2009. V. 27 (5). Pp. 535—544.
17. Guo G., Fu Y., Dyer C., Huang T. Image-based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression // IEEE Trans. on Image Proc. 2008. V. 17 (7). Pp. 1178—1188.
18. Рыбинцев А.В., Конушин В.С., Конушин А.С. Последовательная половая и возрастная классификация людей по изображению лица на основе ранжированных локальных бинарных шаблонов // Компьютерная оптика. 2015. T. 39 (5). C. 762—769.
19. Maenpaa T. The Local Binary Pattern Approach to Texture Analysis — Extensions and Applications. Oulu: Oulu University Press, 2003.
20. Рыбинцев А.В. Снижение размерности пространства LBP-признаков в задаче определения атрибутов личности по изображению лица // Вестник МЭИ. 2016. №. 1. C. 33—38.
21. Ling C. X., Huang J., Zhang H. AUC: a Statistically Consistent and More Discriminating Measure Than Accuracy // Proc. Intern. Conf. on Artificial Intelligence. 2003. Pp. 519—524.
22. Вьюгин В.В. Математические основы тео- рии машинного обучения и прогнозирования. М.: МЦМНО, 2013.
23. Chen K., Gong S., Xiang T. Cumulative Attribute Space for Age and Crowd Density Estimation // Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2013. Pp. 2467—2474.
24. Guo G., Zhang C. A Study on Cross-Population Age Estimation // Proc. IEEE Conf. on Computer Vision and Pattern Recognition. 2014. Pp. 4257—4263.
25. Chen C., Ross A. Evaluation of Gender Classification Methods on Thermal and Near-Infrared Face Images // Proc. Intern. Joint Conf. Biometrics (IJCB). 2011. Pp. 367—374.
---
Для цитирования: Рыбинцев А.В. Последовательное определение атрибутов личности по изображению лица на основе ранжированных LBP-признаков // Вестник МЭИ. 2017. № 5. С. 121—129. DOI: 10.24160/1993-6982-2017-5-121-129.
#
1. Fu Y., Xu Y., Huang T.S. Estimating Human Ages by Manifold Analisys of Face Pictures and Regression On Aging Features. Proc. IEEE Conf. Multimedia and Expo. 2007:1383—1386.
2. Cootes T., Edwards G., Taylor C. Active Appearance Models. IEEE Trans. Pattern Analysis and Machine Intelligence. 2001;23 (6):681—685.
3. Montillo A., Ling H. Age Regression from Faces Using Random Forests. Proc. IEEE Intern. Conf. Image Proc. 2009:2437—2440.
4. Lian H.C., Lu B.L. Multi-view Gender Classification Using Local Binary Patterns and Support Vector Machi- nes. Intern. J. Neural Syst. 2008;17 (6):479—487.
5. Shan C. Learning Local Binary Patterns for Gender Classification on Real-world Face Images. Pattern Recognition Lett. 2012;33 (4):431—437.
6. Yilionias J., Hadid A., Hong X., Pietikainen M. Age Estimation Using Local Binary Patterns Kernel Density Estimate. Proc. IEEE Intern. Conf. on Image Analysis and Proc. 2013:141—150.
7. Hadid A., Pietikainen M. Combining Appearance and Motion for Face and Gender Recognition from Videos. Pattern Recognition Lett. 2009;42 (11):2818—2827.
8. Makinen E., Raisamo R. Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces. IEEE Trans. on Pattern Analysis and Machine Intelligence. 2008;30 (3):541—548.
9. Moghaddam B., Yang M. Learning Gender with Support Faces. IEEE Trans. on Pattern Analysis and Machine Intelligence. 2002;24 (5):707—711.
10. Baluja S., Rowlay H. Boosting Sex Identification Performance. Computer Vision. 2007;71 (1):11—19.
11. Han H., Jain A. Age, Gender and Race Estimation from Unconstrained Face Images. MSU Tech. Rep. 2014. MSU-CSE-14-5.
12. Guo G., Mu G., Fu Y., Huang T. Human Age Estimation Using Bio-inspired Features. Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2009:112—119.
13. Chang K.Y., Chen C.S., Hung Y.P. A Ranking Approach for Human Age Estimation Based on Face Images. Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2010:3396—3399.
14. Chang K.Y., Chen C.S., Hung Y.P. Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2011:585—593.
15. Rybintsev A.V., Lukina T.M., Konushin V.S., Konushin A.S. Vozrastnaya Klassifikatsiya Lyudey po Izobrazheniyu Litsa na Osnove Metoda Ranzhirovaniya i Lokal'nyh Binarnyh Shablonov. Sistemy i Sredstva Informatiki. 2013;23 (2):48—59. (in Russian).
16. Laptev I. Improvements of Object Detection Using Boosted Histograms. Image and Vision Computing.2009;27 (5):535—544.
17. Guo G., Fu Y., Dyer C., Huang T. Image-based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression. IEEE Trans. on Image Proc.2008;17 (7):1178—1188.
18. Rybintsev A.V., Konushin V.S., Konushin A.S. Posledovatel'naya Polovaya i Vozrastnaya Klassifikatsiya Lyudey po Izobrazheniyu Litsa na Osnove Ranzhirovannyh Lokal'nyh Binarnyh Shablonov. Komp'yuternaya Optika. 2015;39 (5):762—769. (in Russian).
19. Maenpaa T. The Local Binary Pattern Approach to Texture Analysis — Extensions and Applications. Oulu: Oulu University Press, 2003.
20. Rybintsev A.V. Snizhenie Razmernosti Prostranstva LBP-priznakov v Zadache Opredeleniya Atributov Lichnosti po Izobrazheniyu Litsa. Vestnik MPEI. 2016;1:33—38. (in Russian).
21. Ling C. X., Huang J., Zhang H. AUC: a Statistically Consistent and More Discriminating Measure Than Accuracy. Proc. Intern. Conf. on Artificial Intelligence. 2003:519—524.
22. V'yugin V.V. Matematicheskie Osnovy Teorii Mashinnogo Obucheniya i Prognozirovaniya. M.: MTSMNO, 2013. (in Russian).
23. Chen K., Gong S., Xiang T. Cumulative Attribute Space for Age and Crowd Density Estimation. Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2013: 2467—2474.
24. Guo G., Zhang C. A Study on Cross-Population Age Estimation. Proc. IEEE Conf. on Computer Vision and Pattern Recognition. 2014:4257—4263.
25. Chen C., Ross A. Evaluation of Gender Classification Methods on Thermal and Near-Infrared Face Images. Proc. Intern. Joint Conf. Biometrics (IJCB).2011:367—374.
---
For citation: Rybintsev A.V. Sequential Determination of Personality Attributes from the Face Image Based on Ranked LBP-Features. MPEI Vestnik. 2017;5: 121—129. (in Russian). DOI: 10.24160/1993-6982-2017-5-121-129.
2. Cootes T., Edwards G., Taylor C. Active Appearance Models // IEEE Trans. Pattern Analysis and Machine Intelligence. 2001. V. 23 (6). Pp. 681—685.
3. Montillo A., Ling H. Age Regression from Faces Using Random Forests // Proc. IEEE Intern. Conf. Image Proc. 2009. Pp. 2437—2440.
4. Lian H.C., Lu B.L. Multi-view Gender Classification Using Local Binary Patterns and Support Vector Machi- nes // Intern. J. Neural Syst. 2008. V. 17 (6). Pp. 479—487.
5. Shan C. Learning Local Binary Patterns for Gender Classification on Real-world Face Images // Pattern Recognition Lett. 2012. V. 33 (4). Pp. 431—437.
6. Yilionias J., Hadid A., Hong X., Pietikainen M. Age Estimation Using Local Binary Patterns Kernel Density Estimate // Proc. IEEE Intern. Conf. on Image Analysis and Proc. 2013. Pp. 141—150.
7. Hadid A., Pietikainen M. Combining Appearance and Motion for Face and Gender Recognition from Videos// Pattern Recognition Lett. 2009. V. 42 (11). Pp. 2818—2827.
8. Makinen E., Raisamo R. Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces // IEEE Trans. on Pattern Analysis and Machine Intelligence. 2008. V. 30 (3). Pp. 541—548.
9. Moghaddam B., Yang M. Learning Gender with Support Faces // IEEE Trans. on Pattern Analysis and Machine Intelligence. 2002. V. 24 (5). Pp. 707—711.
10. Baluja S., Rowlay H. Boosting Sex Identification Performance // Computer Vision. 2007. V. 71 (1). Pp. 11—19.
11. Han H., Jain A. Age, Gender and Race Estimation from Unconstrained Face Images // MSU Tech. Rep. 2014. MSU-CSE-14-5.
12. Guo G., Mu G., Fu Y., Huang T. Human Age Estimation Using Bio-inspired Features // Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition.2009. Pp. 112—119.
13. Chang K.Y., Chen C.S., Hung Y.P. A Ranking Approach for Human Age Estimation Based on Face Images // Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2010. Pp. 3396—3399.
14. Chang K.Y., Chen C.S., Hung Y.P. Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation // IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2011. Pp. 585—593.
15. Рыбинцев А.В., Лукина Т.М., Конушин В.С., Конушин А.С. Возрастная классификация людей по изображению лица на основе метода ранжирования и локальных бинарных шаблонов // Системы и средства информатики. 2013. T. 23 (2). C. 48—59.
16. Laptev I. Improvements of Object Detection Using Boosted Histograms // Image and Vision Computing. 2009. V. 27 (5). Pp. 535—544.
17. Guo G., Fu Y., Dyer C., Huang T. Image-based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression // IEEE Trans. on Image Proc. 2008. V. 17 (7). Pp. 1178—1188.
18. Рыбинцев А.В., Конушин В.С., Конушин А.С. Последовательная половая и возрастная классификация людей по изображению лица на основе ранжированных локальных бинарных шаблонов // Компьютерная оптика. 2015. T. 39 (5). C. 762—769.
19. Maenpaa T. The Local Binary Pattern Approach to Texture Analysis — Extensions and Applications. Oulu: Oulu University Press, 2003.
20. Рыбинцев А.В. Снижение размерности пространства LBP-признаков в задаче определения атрибутов личности по изображению лица // Вестник МЭИ. 2016. №. 1. C. 33—38.
21. Ling C. X., Huang J., Zhang H. AUC: a Statistically Consistent and More Discriminating Measure Than Accuracy // Proc. Intern. Conf. on Artificial Intelligence. 2003. Pp. 519—524.
22. Вьюгин В.В. Математические основы тео- рии машинного обучения и прогнозирования. М.: МЦМНО, 2013.
23. Chen K., Gong S., Xiang T. Cumulative Attribute Space for Age and Crowd Density Estimation // Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2013. Pp. 2467—2474.
24. Guo G., Zhang C. A Study on Cross-Population Age Estimation // Proc. IEEE Conf. on Computer Vision and Pattern Recognition. 2014. Pp. 4257—4263.
25. Chen C., Ross A. Evaluation of Gender Classification Methods on Thermal and Near-Infrared Face Images // Proc. Intern. Joint Conf. Biometrics (IJCB). 2011. Pp. 367—374.
---
Для цитирования: Рыбинцев А.В. Последовательное определение атрибутов личности по изображению лица на основе ранжированных LBP-признаков // Вестник МЭИ. 2017. № 5. С. 121—129. DOI: 10.24160/1993-6982-2017-5-121-129.
#
1. Fu Y., Xu Y., Huang T.S. Estimating Human Ages by Manifold Analisys of Face Pictures and Regression On Aging Features. Proc. IEEE Conf. Multimedia and Expo. 2007:1383—1386.
2. Cootes T., Edwards G., Taylor C. Active Appearance Models. IEEE Trans. Pattern Analysis and Machine Intelligence. 2001;23 (6):681—685.
3. Montillo A., Ling H. Age Regression from Faces Using Random Forests. Proc. IEEE Intern. Conf. Image Proc. 2009:2437—2440.
4. Lian H.C., Lu B.L. Multi-view Gender Classification Using Local Binary Patterns and Support Vector Machi- nes. Intern. J. Neural Syst. 2008;17 (6):479—487.
5. Shan C. Learning Local Binary Patterns for Gender Classification on Real-world Face Images. Pattern Recognition Lett. 2012;33 (4):431—437.
6. Yilionias J., Hadid A., Hong X., Pietikainen M. Age Estimation Using Local Binary Patterns Kernel Density Estimate. Proc. IEEE Intern. Conf. on Image Analysis and Proc. 2013:141—150.
7. Hadid A., Pietikainen M. Combining Appearance and Motion for Face and Gender Recognition from Videos. Pattern Recognition Lett. 2009;42 (11):2818—2827.
8. Makinen E., Raisamo R. Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces. IEEE Trans. on Pattern Analysis and Machine Intelligence. 2008;30 (3):541—548.
9. Moghaddam B., Yang M. Learning Gender with Support Faces. IEEE Trans. on Pattern Analysis and Machine Intelligence. 2002;24 (5):707—711.
10. Baluja S., Rowlay H. Boosting Sex Identification Performance. Computer Vision. 2007;71 (1):11—19.
11. Han H., Jain A. Age, Gender and Race Estimation from Unconstrained Face Images. MSU Tech. Rep. 2014. MSU-CSE-14-5.
12. Guo G., Mu G., Fu Y., Huang T. Human Age Estimation Using Bio-inspired Features. Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2009:112—119.
13. Chang K.Y., Chen C.S., Hung Y.P. A Ranking Approach for Human Age Estimation Based on Face Images. Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2010:3396—3399.
14. Chang K.Y., Chen C.S., Hung Y.P. Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2011:585—593.
15. Rybintsev A.V., Lukina T.M., Konushin V.S., Konushin A.S. Vozrastnaya Klassifikatsiya Lyudey po Izobrazheniyu Litsa na Osnove Metoda Ranzhirovaniya i Lokal'nyh Binarnyh Shablonov. Sistemy i Sredstva Informatiki. 2013;23 (2):48—59. (in Russian).
16. Laptev I. Improvements of Object Detection Using Boosted Histograms. Image and Vision Computing.2009;27 (5):535—544.
17. Guo G., Fu Y., Dyer C., Huang T. Image-based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression. IEEE Trans. on Image Proc.2008;17 (7):1178—1188.
18. Rybintsev A.V., Konushin V.S., Konushin A.S. Posledovatel'naya Polovaya i Vozrastnaya Klassifikatsiya Lyudey po Izobrazheniyu Litsa na Osnove Ranzhirovannyh Lokal'nyh Binarnyh Shablonov. Komp'yuternaya Optika. 2015;39 (5):762—769. (in Russian).
19. Maenpaa T. The Local Binary Pattern Approach to Texture Analysis — Extensions and Applications. Oulu: Oulu University Press, 2003.
20. Rybintsev A.V. Snizhenie Razmernosti Prostranstva LBP-priznakov v Zadache Opredeleniya Atributov Lichnosti po Izobrazheniyu Litsa. Vestnik MPEI. 2016;1:33—38. (in Russian).
21. Ling C. X., Huang J., Zhang H. AUC: a Statistically Consistent and More Discriminating Measure Than Accuracy. Proc. Intern. Conf. on Artificial Intelligence. 2003:519—524.
22. V'yugin V.V. Matematicheskie Osnovy Teorii Mashinnogo Obucheniya i Prognozirovaniya. M.: MTSMNO, 2013. (in Russian).
23. Chen K., Gong S., Xiang T. Cumulative Attribute Space for Age and Crowd Density Estimation. Proc. IEEE Intern. Conf. on Computer Vision and Pattern Recognition. 2013: 2467—2474.
24. Guo G., Zhang C. A Study on Cross-Population Age Estimation. Proc. IEEE Conf. on Computer Vision and Pattern Recognition. 2014:4257—4263.
25. Chen C., Ross A. Evaluation of Gender Classification Methods on Thermal and Near-Infrared Face Images. Proc. Intern. Joint Conf. Biometrics (IJCB).2011:367—374.
---
For citation: Rybintsev A.V. Sequential Determination of Personality Attributes from the Face Image Based on Ranked LBP-Features. MPEI Vestnik. 2017;5: 121—129. (in Russian). DOI: 10.24160/1993-6982-2017-5-121-129.
Published
2019-01-18
Issue
Section
Informatics, computer engineering and control (05.13.00)
