Skip to main content
SpringerLink
Log in

Pedestrian gender classification on imbalanced and small sample datasets using deep and traditional features

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In this manuscript, imbalanced and small sample space (IB-SSS) dataset problems for pedestrian gender classification using fusion of selected deep and traditional features (PGC-FSDTF) are considered. In this regard, data preparation is first done through data augmentation and preprocessing steps to handle imbalanced classification problem and environmental effects, respectively. The proposed approach follows different types of feature extraction schemes, for instance, pyramid histogram of oriented gradients, hue saturation value histogram, deep visual features of DenseNet201 and InceptionResNetV2-based convolutional neural network architectures. The parallel fusion method computes the maximum and average values-based features from the learned features of both deep networks. Features are selected through features selection methods such as entropy and principal component analysis (PCA). The subsets of features are serially fused and provided to multiple classifiers to perform gender classification on IB-SSS datasets. Resultantly, the proposed PGC-FSDTF method shows better results in terms of different accuracies (overall, mean, and balanced), and area under curve on selected datasets. Further, improved results are achieved on applied datasets using PCA-based selected features and medium Gaussian support vector machine (M-SVM) classifier. These results on different datasets confirm that the selected feature combination provides a way to handle IB-SSS issues for PGC effectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Data availability

The datasets generated during and/or analyzed during the current study are available in the [http://mmlab.ie.cuhk.edu.hk/projects/PETA.html and https://github.com/charliememory/PKU-Reid-Dataset] repositories.

References

  1. Chen Y, Duffner S, Stoian A, Dufour J-Y, Baskurt A (2018) Deep and low-level feature based attribute learning for person re-identification. Image Vis Comput 79:25–34

    Google Scholar 

  2. Sun Y, Zhang M, Sun Z, Tan T (2017) Demographic analysis from biometric data: Achievements, challenges, and new frontiers. IEEE Trans Pattern Anal Mach Intell 40:332–351

    Google Scholar 

  3. Azzopardi G, Greco A, Saggese A, Vento M (2018) Fusion of domain-specific and trainable features for gender recognition from face images. IEEE Access 6:24171–24183

    Google Scholar 

  4. Geetha A, Sundaram M, Vijayakumari B (2019) Gender classification from face images by mixing the classifier outcome of prime, distinct descriptors. Soft Comput 23:2525–2535

    Google Scholar 

  5. Cai L, Zhu J, Zeng H, Chen J, Cai C, Ma K-K (2018) Hog-assisted deep feature learning for pedestrian gender recognition. J Frankl Inst 355:1991–2008

    Google Scholar 

  6. Yaghoubi E, Alirezazadeh P, Assunção E, Neves JC, Proençaã H (2019) Region-based CNNs for pedestrian gender recognition in visual surveillance environments. International Conference of the Biometrics Special Interest Group (BIOSIG) 2019:1–5

    Google Scholar 

  7. Guo G, Mu G, Fu Y (2009) Gender from body: a biologically-inspired approach with manifold learning. In: Asian Conference on Computer Vision, pp 236–245

  8. Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3586–3593

  9. Ali-Gombe A, Elyan E, Jayne C (2019) Multiple fake classes GAN for data augmentation in face image dataset. International joint conference on neural networks (IJCNN) 2019:1–8

    Google Scholar 

  10. Wijayanto I, Rizal A, Hadiyoso S (2018) Multilevel wavelet packet entropy and support vector machine for epileptic EEG classification. In: 4th International conference on science and technology (ICST), pp 1–6

  11. Raza M, Zonghai C, Rehman SU, Zhenhua G, Jikai W, Peng B (2017) Part-wise pedestrian gender recognition via deep convolutional neural networks

  12. Zhao C, Wang X, Wong WK, Zheng W, Yang J, Miao D (2017) Multiple metric learning based on bar-shape descriptor for person re-identification. Pattern Recognit 1:1

    Google Scholar 

  13. Gao X, Gao F, Tao D, Li X (2013) Universal blind image quality assessment metrics via natural scene statistics and multiple kernel learning. IEEE Trans Neural Networks Learn Syst 24:1

    Google Scholar 

  14. Cao L, Dikmen M, Fu Y, Huang TS (2008) Gender recognition from body. In Proceedings of the 16th ACM international conference on Multimedia, pp 725–728

  15. Ng C-B, Tay Y-H, Goi B-M (2019) Pedestrian gender classification using combined global and local parts-based convolutional neural networks. Pattern Anal Appl 22:1469–1480

    MathSciNet  Google Scholar 

  16. Deng Y, Luo P, Loy CC, Tang X (2014) Pedestrian attribute recognition at far distance. In: Proceedings of the 22nd ACM international conference on Multimedia, pp 789–792

  17. Ahmad K, Sohail A, Conci N, De Natale F (2018) A Comparative study of Global and Deep Features for the analysis of user-generated natural disaster related images. In: 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), pp 1–5

  18. Collins M, Zhang J, Miller P, Wang H (2009) Full body image feature representations for gender profiling. In: 2009 IEEE 12th international conference on computer vision workshops, ICCV Workshops, 2009, pp 1235–1242

  19. Geelen CD, Wijnhoven RG, Dubbelman G (2015) Gender classification in low-resolution surveillance video: in-depth comparison of random forests and SVMs. In: Video Surveillance and Transportation Imaging Applications 2015, p 94070M

  20. Antipov G, Berrani S-A, Ruchaud N, Dugelay J-L (2015) Learned vs. hand-crafted features for pedestrian gender recognition. In: Proceedings of the 23rd ACM international conference on Multimedia, pp 1263–1266

  21. Sindagi VA, Patel VM (2018) A survey of recent advances in cnn-based single image crowd counting and density estimation. Pattern Recogn Lett 107:3–16

    Google Scholar 

  22. Li C, Guo J, Porikli F, Pang Y (2018) Lightennet: a convolutional neural network for weakly illuminated image enhancement. Pattern Recogn Lett 104:15–22

    Google Scholar 

  23. Rashid M, Khan MA, Sharif M, Raza M, Sarfraz MM, Afza F (2019) Object detection and classification: a joint selection and fusion strategy of deep convolutional neural network and SIFT point features. Multimed Tools Appl 78:15751–15777

    Google Scholar 

  24. Khan MA, Akram T, Sharif M, Awais M, Javed K, Ali H et al (2018) CCDF: automatic system for segmentation and recognition of fruit crops diseases based on correlation coefficient and deep CNN features. Comput Electron Agric 155:220–236

    Google Scholar 

  25. Sharif M, Attique Khan M, Rashid M, Yasmin M, Afza F, Tanik UJ (2019) Deep CNN and geometric features-based gastrointestinal tract diseases detection and classification from wireless capsule endoscopy images. J Exp Theor Artif Intell 1:1–23

    Google Scholar 

  26. Rashid TA, Fattah P, Awla DK (2018) Using accuracy measure for improving the training of lstm with metaheuristic algorithms. Procedia Comput Sci 140:324–333

    Google Scholar 

  27. Rashid TA (2016) Convolutional neural networks based method for improving facial expression recognition. In: The international symposium on intelligent systems technologies and applications, pp 73–84

  28. Shamsaldin AS, Fattah P, Rashid TA, Al-Salihi NK (2019) A study of the convolutional neural networks applications. UKH J Sci Eng 3:31–40

    Google Scholar 

  29. Uddin MA, Lee Y-K (2019) Feature fusion of deep spatial features and handcrafted spatiotemporal features for human action recognition. Sensors 19:1599

    Google Scholar 

  30. Fan X, Tjahjadi T (2019) Fusing dynamic deep learned features and handcrafted features for facial expression recognition. J Vis Commun Image Represent 65:102659

    Google Scholar 

  31. Georgescu M-I, Ionescu RT, Popescu M (2019) Local learning with deep and handcrafted features for facial expression recognition. IEEE Access 7:64827–64836

    Google Scholar 

  32. Hasan AM, Jalab HA, Meziane F, Kahtan H, Al-Ahmad AS (2019) Combining deep and handcrafted image features for MRI brain scan classification. IEEE Access 7:79959–79967

    Google Scholar 

  33. Fayyaz M, Yasmin M, Sharif M, Raza M (2020) J-LDFR: joint low-level and deep neural network feature representations for pedestrian gender classification. Neural Comput Appl

  34. Ng C-B, Tay Y-H, Goi B-M (2013) Comparing image representations for training a convolutional neural network to classify gender. In: 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation, pp 29–33

  35. Raza M, Sharif M, Yasmin M, Khan MA, Saba T, Fernandes SL (2018) Appearance based pedestrians’ gender recognition by employing stacked auto encoders in deep learning. Fut Gener Comput Syst 88:28–39

    Google Scholar 

  36. Ma L, Liu H, Hu L, Wang C, Sun Q (2016) Orientation driven bag of appearances for person re-identification. arXiv preprint arXiv:1605.02464

  37. Wei W-L, Lin J-C, Lin Y-Y, Liao H-YM (2019) What makes you look like you: Learning an inherent feature representation for person re-identification. In: 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2019, pp 1–6

  38. Moctezuma D, Tellez ES, Miranda-Jiménez S, Graff M (2019) Appearance model update based on online learning and soft-biometrics traits for people re-identification in multi-camera environments. IET Image Proc 13:2162–2168

    Google Scholar 

  39. Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6:60

    Google Scholar 

  40. Hou W, Wei Y, Jin Y, Zhu C (2019) Deep features based on a DCNN model for classifying imbalanced weld flaw types. Measurement 131:482–489

    Google Scholar 

  41. Wang X, Zhao C, Miao D, Wei Z, Zhang R, Ye T (2016) Fusion of multiple channel features for person re-identification. Neurocomputing 213:125–136

    Google Scholar 

  42. Georgiou T, Liu Y, Chen W, Lew M (2020) A survey of traditional and deep learning-based feature descriptors for high dimensional data in computer vision. Int J Multimed Inf Retriev 9:135–170

    Google Scholar 

  43. Hussain N, Khan MA, Sharif M, Khan SA, Albesher AA, Saba T et al (2020) A deep neural network and classical features based scheme for objects recognition: an application for machine inspection. Multimed Tools Appl. https://doi.org/10.1007/s11042-020-08852-3

  44. Gour N, Khanna P (2019) Automated glaucoma detection using GIST and pyramid histogram of oriented gradients (PHOG) descriptors. Pattern Recognit Lett

  45. Murtza I, Abdullah D, Khan A, Arif M, Mirza SM (2017) Cortex-inspired multilayer hierarchy based object detection system using PHOG descriptors and ensemble classification. Vis Comput 33:99–112

    Google Scholar 

  46. Sarangi PP, Mishra BSP, Dehuri S (2019) Fusion of PHOG and LDP local descriptors for kernel-based ear biometric recognition. Multimed Tools Appl 78:9595–9623

    Google Scholar 

  47. El-Tarhouni W, Boubchir L, Elbendak M, Bouridane A (2019) Multispectral palmprint recognition using Pascal coefficients-based LBP and PHOG descriptors with random sampling. Neural Comput Appl 31:593–603

    Google Scholar 

  48. Abdullah DA, Akpinar MH, Sengür A (2020) Local feature descriptors based ECG beat classification. Health Inf Sci Syst 8:20

    Google Scholar 

  49. Xu T, Zhang H, Xin C, Kim E, Long LR, Xue Z et al (2017) Multi-feature based benchmark for cervical dysplasia classification evaluation. Pattern Recogn 63:468–475

    Google Scholar 

  50. Liu P, Guo J-M, Chamnongthai K, Prasetyo H (2017) Fusion of color histogram and LBP-based features for texture image retrieval and classification. Inf Sci 390:95–111

    Google Scholar 

  51. Mistry Y, Ingole D, Ingole M (2018) Content based image retrieval using hybrid features and various distance metric. J Electr Syst Inf Technol 5:874–888

    Google Scholar 

  52. Danapur N, Dizaj SAA, Rostami V (2020) An efficient image retrieval based on an integration of HSV, RLBP, and CENTRIST features using ensemble classifier learning. Multimedia Tools Appl 1–24

  53. Toğaçar M, Ergen B, Cömert Z, Özyurt F (2019) A deep feature learning model for pneumonia detection applying a combination of mRMR feature selection and machine learning models. IRBM

  54. Yuan B, Han L, Gu X, Yan H (2020) Multi-deep features fusion for high-resolution remote sensing image scene classification. Neural Comput Appl 1–17

  55. Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2016) Inception-v4, inception-resnet and the impact of residual connections on learning. arXiv preprint arXiv:1602.07261

  56. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708

  57. Fayyaz M, Yasmin M, Sharif M, Shah JH, Raza M, Iqbal T (2019) Person re-identification with features-based clustering and deep features. Neural Comput Appl 1:1–22

    Google Scholar 

  58. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297

    MATH  Google Scholar 

  59. Lizarazo I (2008) SVM-based segmentation and classification of remotely sensed data. Int J Remote Sens 29:7277–7283

    Google Scholar 

  60. Bhati BS, Rai C (2020) Analysis of Support Vector Machine-based Intrusion Detection Techniques. Arab J Sci Eng 45:2371–2383

    Google Scholar 

  61. Abdullah DA, Akpınar MH, Şengür A (2020) Local feature descriptors based ECG beat classification. Health information science and systems 8:1–10

    Google Scholar 

  62. Khamparia A, Singh SK, Luhach AK (2021) SVM-PCA based handwritten devanagari digit character recognition. Recent Adv Comput Sci Commun (Formerly: Recent Patents Comput Sci) 14:48–53

  63. Ali-Gombe A, Elyan E (2019) MFC-GAN: class-imbalanced dataset classification using multiple fake class generative adversarial network. Neurocomputing 361:212–221

    Google Scholar 

  64. Ng C-B, Tay Y-H, Goi B-M (2017) Training strategy for convolutional neural networks in pedestrian gender classification. In: Second International Workshop on Pattern Recognition, 2017, p 104431A

  65. Cai L, Zeng H, Zhu J, Cao J, Wang Y, Ma K-K (2020) Cascading scene and viewpoint feature learning for pedestrian gender recognition. IEEE Internet Things J 1:1

    Google Scholar 

  66. Abbas F, Yasmin M, Fayyaz M, Elaziz MA, Lu S, El-Latif AAA (2021) Gender Classification Using Proposed CNN-Based Model and Ant Colony Optimization. Mathematics 9:2499

    Google Scholar 

  67. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556

  68. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

  69. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan

    Muhammad Fayyaz, Mussarat Yasmin, Muhammad Sharif, Tasswar Iqbal & Mudassar Raza

  2. Department of Computer Science, FAST - National University of Computer and Emerging Sciences, Chiniot-Faisalabad Campus, Chiniot, Pakistan

    Muhammad Imran Babar

Authors
  1. Muhammad Fayyaz
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mussarat Yasmin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Muhammad Sharif
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tasswar Iqbal
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mudassar Raza
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Muhammad Imran Babar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Muhammad Fayyaz.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fayyaz, M., Yasmin, M., Sharif, M. et al. Pedestrian gender classification on imbalanced and small sample datasets using deep and traditional features. Neural Comput & Applic 35, 11937–11968 (2023). https://doi.org/10.1007/s00521-023-08331-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-023-08331-4

Keywords

Search

Navigation