Abstract

Face sketch recognition is a crucial field with applications in identifying suspects and criminals based on verbal descriptions (face sketches) provided by eyewitnesses. Although deep convolutional neural networks (DCNNs) have significantly advanced face recognition from photos, recognizing faces from sketches remains challenging due to texture differences and limited training samples. To overcome these challenges, an innovative methodology that integrates the shearlet transform as a pre-processing layer within the DCNN was proposed. This combination aims to establish a robust learning foundation for identifying individuals from face photos using their corresponding face sketches. Experimental evaluations showcase the effectiveness of our approach, achieving a remarkably high recognition rate. The incorporation of the shearlet transform enhances the DCNN's capability to handle texture disparities between face photos and sketches, resulting in improved performance. Our research marks the first instance of combining DCNN with the shearlet transform for face sketch recognition. Our approach proves highly effective in addressing sketch recognition challenges, as evidenced by an impressively low error rate of only 0.7%. This leads to minimized false positives, a crucial factor in law enforcement applications. A flawless recall score and an F1-score of 100% demonstrate exceptional performance in correctly identifying matches. This advancement carries promising implications for sensitive applications, such as recognizing suspects and criminals based on eyewitness descriptions, ultimately enhancing overall security and law enforcement efforts.

Keyword

Face sketch, CNN, Shearlet transform, Face recognition.

Cite this article

Ziani C, Sadiq A

Refference

[1][1]Liu L, Shen F, Shen Y, Liu X, Shao L. Deep sketch hashing: fast free-hand sketch-based image retrieval. In proceedings of the conference on computer vision and pattern recognition 2017 (pp. 2862-71). IEEE.

[2][2]Cao B, Wang N, Li J, Hu Q, Gao X. Face photo-sketch synthesis via full-scale identity supervision. Pattern Recognition. 2022; 124:108446.

[3][3]Shan C, Gong S, Mcowan PW. Facial expression recognition based on local binary patterns: a comprehensive study. Image and Vision Computing. 2009; 27(6):803-16.

[4][4]Yu Q, Liu F, Song YZ, Xiang T, Hospedales TM, Loy CC. Sketch me that shoe. In proceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 799-807).

[5][5]Ziani C, Sadiq A. SH-CNN: shearlet convolutional neural network for gender classification. Advances in Science, Technology and Engineering Systems Journal. 2020; 5(20):1328-34.

[6][6]Ziani C, Sadiq A. Smart approach based on CNN and shearlet transform for age prediction. In proceedings of seventh international congress on information and communication technology: ICICT, London, 2022 (pp. 143-52). Singapore: Springer Nature Singapore.

[7][7]Kutyniok G, Lim WQ. Image separation using wavelets and shearlets. In curves and surfaces: 7th international conference, Avignon, France, 2012 (pp. 416-30). Springer Berlin Heidelberg.

[8][8]Mutneja V, Singh S. HAAR-features training parameters analysis in boosting based machine learning for improved face detection. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(80):919-31.

[9][9]Ashhar SM, Mokri SS, Abd RAA, Huddin AB, Zulkarnain N, Azmi NA, et al. Comparison of deep learning convolutional neural network (CNN) architectures for CT lung cancer classification. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(74):126-34.

[10][10]Salunke D, Mane D, Joshi R, Peddi P. Customized convolutional neural network to detect dental caries from radiovisiography (RVG) images. International Journal of Advanced Technology and Engineering Exploration. 2022; 9(91):827-38.

[11][11]Senthil T, Rajan C, Deepika J. An efficient CNN model with squirrel optimizer for handwritten digit recognition. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(78):545-59.

[12][12]Patel LK, Patel MI. Feature based image registration using CNN features for satellite images having varying illumination level. International Journal of Advanced Technology and Engineering Exploration. 2023; 10(101):440-57.

[13][13]Chopade PB, Prabhakar N. Human emotion recognition based on block patterns of image and wavelet transform. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(83):1394-409.

[14][14]Bahrum NN, Setumin S, Abdullah MF, Maruzuki MI, Che AAI. A systematic review of face sketch recognition system. Journal of Electrical and Electronic Systems Research (JEESR). 2023; 22:1-10.

[15][15]Bae S, Din NU, Park H, Yi J. Face photo-sketch recognition using bidirectional collaborative synthesis network. In 16th international conference on ubiquitous information management and communication 2022 (pp. 1-8). IEEE.

[16][16]Radman A, Sallam A, Suandi SA. Deep residual network for face sketch synthesis. Expert Systems with Applications. 2022; 190:115980.

[17][17]Yan L, Zheng W, Gou C, Wang FY. IsGAN: Identity-sensitive generative adversarial network for face photo-sketch synthesis. Pattern Recognition. 2021; 119:108077.

[18][18]Bhoir M, Gosavi C, Gade P, Alte B. A decision-making tool for creating and identifying face sketches. In ITM web of conferences 2022 (pp. 1-6). EDP Sciences.

[19][19]Alhashash KM, Samma H, Suandi SA. Fine-tuning of pre-trained deep face sketch models using smart switching slime mold algorithm. Applied Sciences. 2023; 13(8):1-36.

[20][20]Navuluri C, Jukanti S, Allapuram RR. Semantic neural model approach for face recognition from sketch. arXiv preprint arXiv:2305.01058. 2023.

[21][21]Peng C, Zhang C, Liu D, Wang N, Gao X. Face photo–sketch synthesis via intra-domain enhancement. Knowledge-Based Systems. 2023; 259:110026.

[22][22]Zhong K, Chen Z, Liu C, Wu QJ, Duan S. Unsupervised self-attention lightweight photo-to-sketch synthesis with feature maps. Journal of Visual Communication and Image Representation. 2023; 90:103747.

[23][23]Wan W, Gao Y, Lee HJ. Transfer deep feature learning for face sketch recognition. Neural Computing and Applications. 2019; 31:9175-84.

[24][24]Lakshmi N, Arakeri MP. A novel sketch based face recognition in unconstrained video for criminal investigation. International Journal of Electrical & Computer Engineering (2088-8708). 2023; 13(2):1499-1509.

[25][25]Devakumar S, Sarath G. Forensic sketch to real image using DCGAN. Procedia Computer Science. 2023; 218:1612-20.

[26][26]Jacquet M, Champod C. Automated face recognition in forensic science: review and perspectives. Forensic Science International. 2020; 307:110124.

[27][27]Kazemi H, Soleymani S, Dabouei A, Iranmanesh M, Nasrabadi NM. Attribute-centered loss for soft-biometrics guided face sketch-photo recognition. In proceedings of the conference on computer vision and pattern recognition workshops 2018 (pp. 499-507). IEEE.

[28][28]Iranmanesh SM, Kazemi H, Soleymani S, Dabouei A, Nasrabadi NM. Deep sketch-photo face recognition assisted by facial attributes. In 9th international conference on biometrics theory, applications and systems 2018 (pp. 1-10). IEEE.

[29][29]Liu D, Gao X, Wang N, Li J, Peng C. Coupled attribute learning for heterogeneous face recognition. IEEE Transactions on Neural Networks and Learning Systems. 2020; 31(11):4699-712.

[30][30]Liu D, Gao X, Wang N, Peng C, Li J. Iterative local re-ranking with attribute guided synthesis for face sketch recognition. Pattern Recognition. 2021; 109:107579.

[31][31]Peng C, Wang N, Li J, Gao X. DLFace: deep local descriptor for cross-modality face recognition. Pattern Recognition. 2019; 90:161-71.

[32][32]Fan L, Sun X, Rosin PL. Attention-modulated triplet network for face sketch recognition. IEEE Access. 2021; 9:12914-21.

[33][33]Easley GR, Labate D, Patel VM. Directional multiscale processing of images using wavelets with composite dilations. Journal of Mathematical Imaging and Vision. 2014; 48:13-34.

[34][34]Viola P, Jones M. Rapid object detection using a boosted cascade of simple features. In proceedings of the computer society conference on computer vision and pattern recognition. CVPR 2001. IEEE.

[35][35]Bradski G, Kaehler A. Learning OpenCV: computer vision with the OpenCV library. OReilly Media, Inc.; 2008.

[36][36]Wang X, Tang X. Face photo-sketch synthesis and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008; 31(11):1955-67.