An Embedded VGG 22 Model for Gender Classification in Crowd Videos
Keywords:
VGG11, VGG13, VGG16, VGG19, VGG22, Gender, Deep Convolutional Neural NetworkAbstract
This study presents the development and optimization of an embedded VGG model for the purpose of gender classification in crowd videos. Traditional VGG models offer robust feature extraction for image classification but are computationally intensive, rendering them less practical for real-time analysis in embedded systems with limited resources. Addressing this, the research explores the implementation of VGG11 through a VGG22 architecture, analyzing their performance in terms of accuracy, precision, recall, and F1-score. The findings indicate a trend of increasing performance with deeper architectures, with the VGG22 model achieving the highest scores across all metrics. The research methodology involved adapting the VGG architecture to the constraints of embedded systems through model compression techniques such as pruning and quantization, alongside optimization strategies like knowledge distillation. The models were evaluated using standard gender classification datasets, with a particular focus on the challenging conditions of crowd video data. The results confirmed that with careful optimization, it is possible to maintain high accuracy in gender classification while significantly reducing the computational demands of the model.
Downloads
References
Ozbulak G, Aytar Y, Ekenel HK. How transferable are CNN-based features for age and gender classification?. In2016 International Conference of the Biometrics Special Interest Group (BIOSIG) 2016 Sep 21 (pp. 1-6). IEEE.
Rim B, Kim J, Hong M. Gender classification from fingerprint-images using deep learning approach. InProceedings of the international conference on research in adaptive and convergent systems 2020 Oct 13 (pp. 7-12).
Tariq MU, AKRAM A, YAQOOB S, RASHEED M, ALI MS. Real Time Age And Gender Classification Using Vgg19. Adv Mach Lear Art Inte. 2023;4(2):56-65.
Lapuschkin S, Binder A, Muller KR, Samek W. Understanding and comparing deep neural networks for age and gender classification. InProceedings of the IEEE international conference on computer vision workshops 2017 (pp. 1629-1638).
Krishnan A, Almadan A, Rattani A. Understanding fairness of gender classification algorithms across gender-race groups. In2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA) 2020 Dec 14 (pp. 1028-1035). IEEE.
Janahiraman TV, Subramaniam P. Gender classification based on Asian faces using deep learning. In2019 IEEE 9th International Conference on System Engineering and Technology (ICSET) 2019 Oct 7 (pp. 84-89). IEEE.
Yaman D, Eyiokur FI, Sezgin N, Ekenel HK. Age and gender classification from ear images. In2018 International Workshop on Biometrics and Forensics (IWBF) 2018 Jun 7 (pp. 1-7). IEEE.
Tian Q, Arbel T, Clark JJ. Deep lda-pruned nets for efficient facial gender classification. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops 2017 (pp. 10-19).
Islam MK, Habiba SU. Human Age Estimation and Gender Classification Using Deep Convolutional Neural Network. InCyber Security and Computer Science: Second EAI International Conference, ICONCS 2020, Dhaka, Bangladesh, February 15-16, 2020, Proceedings 2 2020 (pp. 503-514). Springer International Publishing.
Mansour AI, Abu-Naser SS. Age and Gender Classification Using Deep Learning-VGG16.
Benkaddour MK, Lahlali S, Trabelsi M. Human age and gender classification using convolutional neural network. In2020 2nd international workshop on human-centric smart environments for health and well-being (IHSH) 2021 Feb 9 (pp. 215-220). IEEE.
Trivedi G, Pise NN. Gender classification and age estimation using neural networks: a survey. International journal of computer Applications. 2020 May;975:8887.
Dhomne A, Kumar R, Bhan V. Gender recognition through face using deep learning. Procedia computer science. 2018 Jan 1;132:2-10.
Marouf M, Siddiqi R, Bashir F, Vohra B. Automated hand X-ray based gender classification and bone age assessment using convolutional neural network. In2020 3rd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET) 2020 Jan 29 (pp. 1-5). IEEE.
Agbo-Ajala O, Viriri S. Face-based age and gender classification using deep learning model. InImage and Video Technology: PSIVT 2019 International Workshops, Sydney, NSW, Australia, November 18–22, 2019, Revised Selected Papers 9 2020 (pp. 125-137). Springer International Publishing.
Smith P, Chen C. Transfer learning with deep CNNs for gender recognition and age estimation. In2018 IEEE International Conference on Big Data (Big Data) 2018 Dec 10 (pp. 2564-2571). IEEE.
Yaman D, Irem Eyiokur F, Kemal Ekenel H. Multimodal age and gender classification using ear and profile face images. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops 2019 (pp. 0-0).
Chen J, Liu S, Chen Z. Gender classification in live videos. In2017 IEEE International Conference on Image Processing (ICIP) 2017 Sep 17 (pp. 1602-1606). IEEE.
Mittal S, Mittal S. Gender recognition from facial images using convolutional neural network. In2019 Fifth International Conference on Image Information Processing (ICIIP) 2019 Nov 15 (pp. 347-352). IEEE.
Jiang Z. Face gender classification based on convolutional neural networks. In2020 International Conference on Computer Information and Big Data Applications (CIBDA) 2020 Apr 17 (pp. 120-123). IEEE.
Viedma I, Tapia J. Deep Gender Classification and Visualization of Near-Infra-Red Periocular-Iris images. In2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS) 2018 Dec 12 (pp. 73-78). IEEE.
Gogate U, Parate A, Sah S, Narayanan S. Real time emotion recognition and gender classification. In2020 International Conference on Smart Innovations in Design, Environment, Management, Planning and Computing (ICSIDEMPC) 2020 Oct 30 (pp. 138-143). IEEE.
Maruthukunnel Jacob J. Binary Gender Classification of African Fingerprints using CNN (Doctoral dissertation, Dublin, National College of Ireland).
Jia S, Lansdall-Welfare T, Cristianini N. Gender classification by deep learning on millions of weakly labelled images. In2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW) 2016 Dec 12 (pp. 462-467). IEEE.
Lee B, Gilani SZ, Hassan GM, Mian A. Facial gender classification—analysis using convolutional neural networks. In2019 Digital Image Computing: Techniques and Applications (DICTA) 2019 Dec 2 (pp. 1-8). IEEE.
Yaman D, Eyiokur FI, Ekenel HK. Multimodal soft biometrics: combining ear and face biometrics for age and gender classification. Multimedia Tools and Applications. 2021 Mar 15:1-9.
İnik Ö, Uyar K, Ülker E. Gender classification with a novel convolutional neural network (CNN) model and comparison with other machine learning and deep learning CNN models. Journal Of Industrial Engineering Research. 2018 Dec;4(4):57-63.
Karthick R. Deep Learning For Age Group Classification System. International Journal Of Advances In Signal And Image Sciences. 2018 Dec 28;4(2):16-22.
Manyala A, Cholakkal H, Anand V, Kanhangad V, Rajan D. CNN-based gender classification in near-infrared periocular images. Pattern Analysis and Applications. 2019 Nov;22:1493-504.
Tilki S, Dogru HB, Hameed AA. Gender classification using deep learning techniques. Manchester journal of Artificial Intelligence and Applied sciences. 2021 May 26;2(2).
Althnian A, Aloboud N, Alkharashi N, Alduwaish F, Alrshoud M, Kurdi H. Face gender recognition in the wild: an extensive performance comparison of deep-learned, hand-crafted, and fused features with deep and traditional models. Applied Sciences. 2020 Dec 24;11(1):89.
Zhang K, Tan L, Li Z, Qiao Y. Gender and smile classification using deep convolutional neural networks. InProceedings of the IEEE conference on computer vision and pattern recognition workshops 2016 (pp. 34-38).
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
