Abstract
In every image processing venture the quality of data sample collected and the processing techniques poses direct impact on the result. This work explains development of these vital phases in the context to exploit it for racial classification. Here we propose a novel Indian regional face database (IRFD) consisting of large set distinctive face images of north, east, west and south regions of India to mitigate the scarcity of regional and labeled face images for future supervised classification process. The face images are collected from different universities and acquired through both online and offline mode. Due to this discrepancy the face database is exposed to challenges like varying dimension size, non-uniform background, low resolution, illumination, and pose variation. In view of addressing these problems we have proposed competent image processing techniques to enhance the quality of images. Varying size and low resolution were the main issues among others encountered while training Convolutional Neural Network (CNN) model. To handle this we have developed an expeditious compression algorithm which would reduce large size of all images to ±97% less in size without compromising the quality. Further to enhance low quality images we have proposed brightness and contrast adjusting algorithm. The efficiency of this quantitative and qualitative data set is evaluated against CNN model which has yielded ±88.21% accuracy under racial classification.
Similar content being viewed by others
References
Abuzneid M, Mahmood A (2018) Improving human face recognition using deep learning based image registration and multi classifier approaches. IEEE. https://doi.org/10.1109/AICCSA.2018.8612896
Akhtar N, Khan S, Siddiqui G (2014) A novel Lossy image compression method. IEEE. https://doi.org/10.1109/CSNT.2014.180
Hussein HK (2002) Towards realistic facial modeling and re-rendering of human skin aging animation. IEEE. https://doi.org/10.1109/SMI.2002.10035547
Bastanfard A, Bastanfard O, Takahashi H, Nakajima M (2004) Toward anthropometrics simulation of face rejuvenation and skin cosmetic. Computer Animation and Virtual Worlds 15:347–352. https://doi.org/10.1002/cav.38
Bastanfard A, Takahashi H, Nakajima M (2004) Toward E-appearance of human face and hair by age, expression and rejuvenation. International Conference on Cyber worlds. https://doi.org/10.1109/CW.2004.65
Bastanfard A, Nik MA et al (2007) Iranian face database with age, pose and expression. IEEE. https://doi.org/10.1109/ICMV.2007.4469272
Beghdadi A, Qureshi MA, Sdiri B et al (2018) CEED-A database for image contrast enhancement evaluation. IEEE. https://doi.org/10.1109/CVCS.2018.8496603.2018
Bhattacharya S, Gupta S et al (2014) Localized image enhancement. IEEE. https://doi.org/10.1109/NCC.2014.6811269
Cao J, Li Y, Zhang Z (2018) Celeb-500k: a large training dataset for face recognition. IEEE. https://doi.org/10.1109/ICIP.2018.8451704
Chaudhari MN, Deshmukh M, Ramrakhiani G et al (2019) Face detection using Viola Jones algorithm and neural networks. IEEE. https://doi.org/10.1109/ICCUBEA.2018.8697768
Dehshibi MM, Bastanfard A (2010) A new algorithm for age recognition from facial images. Signal Process 90:2431–2444. https://doi.org/10.1016/j.sigpro.2010.02.015
Esty A, Frize M, Gilchrist J, Bariciak E (2018) Applying data preprocessing methods to predict premature birth. IEEE. 2018:6096–6099. https://doi.org/10.1109/EMBC.2018.8513681
Harish K, Aruna SP (2018) Are you from north or South India? A hard race classification task reveals systematic representational differences between humans and machines. J Vis. https://doi.org/10.1167/19.7.1
Hiremani VA, Hatture SM (2013) Personal identification with face biometrics using color local texture features. IJACR
Hiremani VA, Senapati KK (2019) Significance of conventional and nonconventional features in classification of face through human intelligence. IEEE. https://doi.org/10.1109/ICSSIT46314.2019.8987756
Hosseini MS, Plataniotis KN et al (2020) Convolutional Deblurring for natural imaging. IEEE. 29:250–264. https://doi.org/10.1109/TIP.2019.2929865
Jeromel A, Žalik B (2019) An efficient lossy cartoon image compression method. Multimed Tools Appl 79:433–451. https://doi.org/10.1007/s11042-019-08126-7
Khanh TLB, Kim SH, Lee G, Yang HJ, Baek ET (2020) Korean video dataset for emotion recognition in the wild. Multimed Tools Appl 80:9479–9492. https://doi.org/10.1007/s11042-020-10106-1
Learned-Miller E et al (2016) Labeled faces in the Wild: A Survey. Advances in Face Detection and Facial Image Analysis, Springer. https://doi.org/10.1007/978-3-319-25958-1_8
Lee DH, Chen KL, Liou KH, Liu CL, Liu JL (2020) Deep learning and control algorithms of direct perception for autonomous driving. Appl Intell 51:237–247. https://doi.org/10.1007/s10489-020-01827-9
Lin YN, Hsieh TY, Huang JJ, Yang CY, Shen VRL, Bui HH (2020) Fast Iris localization using Haar-like features and AdaBoost algorithm. Multimed Tools Appl 79:34339–34362. https://doi.org/10.1007/s11042-020-08907-5
Panetta K, Wan Q, Agaian S, Rajeev S, Kamath S, Rajendran R, Rao SP, Kaszowska A, Taylor HA, Samani A, Yuan X (2020) A comprehensive database for benchmarking imaging systems. IEEE 42:509–520. https://doi.org/10.1109/TPAMI.2018.2884458
Patel R, Kumar V, Tyagi V et al (2016) A fast and improved image compression technique using Huffman coding. IEEE. https://doi.org/10.1109/WiSPNET.2016.7566549
Reecha S, Patterh MS (2015) Indian face age database: a database for face recognition with age variation. IJCA. https://doi.org/10.5120/ijca2015906055
Satone KN, Deshmukh AS, Ulhe PB (2017) A review of image compression techniques. IEEE. https://doi.org/10.1109/ICECA.2017.8203651
Setty S, Husain M, Beham P et al (2013) Indian movie face database: a benchmark for face recognition under wide variations. NCVPRIPG. https://doi.org/10.1109/NCVPRIPG.2013.6776225
Singh KB, Mahendra TV, Kurmvanshi RS et al (2017) Image enhancement with the application of local and global enhancement methods for dark images. IEEE. https://doi.org/10.1109/IESPC.2017.8071892
Somanath G, Rohith MV, Kambhamettu C (2011) VADANA: a dense dataset for facial image analysis. IEEE. https://doi.org/10.1109/ICCVW.2011.6130517
Spahiu CS, Stanescu L, Burdescu DD et al (2009) File storage for a multimedia database server for image retrieval. IEEE. https://doi.org/10.1109/ICCGI.2009.13
Wang R, Chen J, Shan S et al (2006) Enhancing training set for face detection. IEEE. https://doi.org/10.1109/ICPR.2006.493
Wang Y, Liao H, Feng et al (2016) Do they all look the same? Deciphering Chinese, Japanese and Koreans by fine-grained deep learning, in proc. IEEE. https://doi.org/10.1109/MIPR.2018.00015
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix 1
Appendix 1
Rights and permissions
About this article
Cite this article
Hiremani, V.A., Senapati, K.K. Developing real-time training dataset for human racial classification. Multimed Tools Appl 81, 28103–28127 (2022). https://doi.org/10.1007/s11042-022-12947-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12947-4