Decoding Innocence: Advancing Forensic Facial Discrimination through Comparative Analysis of Conventional CNN and Advanced Architectures

Mirza Jamal Ahmed - Universiti Tun Hussein Onn Malaysia, Johor, Malaysia
Nurul Azma Abdullah - Universiti Tun Hussein Onn Malaysia, Johor, Malaysia


Citation Format:



DOI: http://dx.doi.org/10.62527/joiv.8.2.2755

Abstract


The field of Digital Image Forensics (DIF) faces a critical issue in accurately identifying children in digital images, notably in cases involving the proliferation of child sexual abuse content. Existing techniques face hurdles due to model architecture limitations, dataset suitability concerns, and classification imbalance, impeding their ability to recognize children to deter pornographic images. Addressing this challenge, this study introduces Implicit Feature Extraction (IFE), a specialized approach for distinguishing child and adult images in object detection. Leveraging Convolutional Neural Networks (CNNs), the IFE method automates the extraction of discriminative facial features, surpassing the constraints of Explicit Feature Extraction (EFE) methods, which achieve an accuracy of around 70%. The research focuses on three core objectives introducing IFE for detailed face feature detection in DIF's child and adult image identification, implementing IFE with CNNs to enhance image classification, and conducting a thorough evaluation of the proposed technique's performance using key metrics like accuracy and balanced classification results and comparing the result with a basic CNN model’s performance. This research's significance lies in its notable contributions to digital image forensics, particularly in combatting child exploitation. The fusion of IFE with CNNs showcases 92% accuracy in distinguishing child and adult images, promising advancements with practical implications in child protection and forensic investigations. The comprehensive evaluation using the UTKFace dataset underscores the proposed technique's efficacy, marking a substantial improvement in child image identification within digital image forensics.

Keywords


Facial feature extraction; object detection; child identification; image forensics; digital image analysis

Full Text:

PDF

References


H. K. Tu, L. T. Thuong, H. V. U. Synh, H. T. San, and H. Van Khoa, “Develop an algorithm for image forensics using feature comparison and sharpness estimation,” in Proceedings - 2017 International Conference on Recent Advances in Signal Processing, Telecommunications and Computing, SigTelCom 2016, 2017, pp. 82–87, doi: 10.1109/SIGTELCOM.2017.7849800.

V. Chatzis, F. Panagiotopoulos, and V. Mardiris, “Face to Iris Area Ratio as a feature for children detection in digital forensics applications,” in 2016 Digital Media Industry and Academic Forum, DMIAF 2016 - Proceedings, 2016, pp. 121–124, doi: 10.1109/DMIAF.2016.7574915.

A. Ulges and A. Stahl, “Automatic detection of child pornography using color visual words,” 2011 IEEE Int. Conf. Multimed. Expo, pp. 1–6, 2011, doi: 10.1109/ICME.2011.6011977.

C. Chen, S. Member, and J. Ni, “Blind Forensics of Successive Geometric Transformations in Digital Images Using Spectral Method : Theory and Applications,” vol. 26, no. 6, pp. 2811–2824, 2017.

P. Kruchten, “Certification 1, 2, 3,” IEEE Softw., vol. 27, no. 3, pp. 92–94, 2010, doi: 10.1109/MS.2010.70.

S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1149, 2017, doi: 10.1109/TPAMI.2016.2577031.

O. F. Ince, I. F. Ince, J. S. Park, J. K. Song, and B. W. Yoon, “Child and adult classification using biometric features based on video analytics,” ICIC Express Lett. Part B Appl., vol. 8, no. 5, pp. 819–825, 2017, doi: 10.5281/zenodo.890713.

L. Cuimei, Q. Zhiliang, J. Nan, and W. Jianhua, “Human face detection algorithm via Haar cascade classifier combined with three additional classifiers,” 2017.

C. Raghavachari, V. Aparna, S. Chithira, and V. Balasubramanian, “A Comparative Study of Vision Based Human Detection Techniques in People Counting Applications,” Procedia Comput. Sci., vol. 58, pp. 461–469, 2015, doi: 10.1016/j.procs.2015.08.064.

R. Hussin, M. R. Juhari, N. W. Kang, R. C. Ismail, and A. Kamarudin, “Digital image processing techniques for object detection from complex background image,” Procedia Engineering, vol. 41. pp. 340–344, 2012, doi: 10.1016/j.proeng.2012.07.182.

C. R. Kumar, S. N, M. Priyadharshini, D. G. E, and K. R. M, “Face recognition using CNN and siamese network,” Meas. Sensors, vol. 27, no. March, p. 100800, 2023, doi: 10.1016/j.measen.2023.100800.

S. Biswas, D. Chambers, W. D. Hairston, and S. Bhattacharya, “Head pose classification for passenger with CNN,” Transp. Eng., vol. 11, no. October 2022, p. 100157, 2023, doi: 10.1016/j.treng.2022.100157.

A. A. Solanke, “Explainable digital forensics AI: Towards mitigating distrust in AI-based digital forensics analysis using interpretable models,” Forensic Sci. Int. Digit. Investig., vol. 42, p. 301403, 2022, doi: 10.1016/j.fsidi.2022.301403.

X. Wang, F. Cheng, S. Wang, H. Sun, G. Liu, and C. Zhou, “Adult Image Classification,” 2018 25th IEEE Int. Conf. Image Process., pp. 2989–2993, 2018.

H. Amroun, M. Clinic, and M. Ammi, “Best feature for CNN classification of Human Activity using IOT network,” 2017, doi: 10.1109/iThings-GreenCom-CPSCom-SmartData.2017.145.

O. Uparkar, J. Bharti, R. K. Pateriya, R. K. Gupta, and A. Sharma, “Vision Transformer Outperforms Deep Convolutional Neural Network-based Model in Classifying X-ray Images,” Procedia Comput. Sci., vol. 218, no. 2022, pp. 2338–2349, 2023, doi: 10.1016/j.procs.2023.01.209.

W. H. Yun, D. Lee, C. Park, J. Kim, and J. Kim, “Automatic Recognition of Children Engagement from Facial Video Using Convolutional Neural Networks,” IEEE Trans. Affect. Comput., vol. 11, no. 4, pp. 696–707, 2020, doi: 10.1109/TAFFC.2018.2834350.

B. Liu, C. M. Pun, and X. C. Yuan, “Digital image forgery detection using JPEG features and local noise discrepancies,” Sci. World J., vol. 2014, 2014, doi: 10.1155/2014/230425.

J. Waleed and T. M. Hasan, “Techniques ( AFTs ) Based Compressed Image,” no. March, pp. 7–9, 2017.

V. Kate and P. Shukla, “A 3 Tier CNN model with deep discriminative feature extraction for discovering malignant growth in multi-scale histopathology images,” Informatics Med. Unlocked, vol. 24, no. April, p. 100616, 2021, doi: 10.1016/j.imu.2021.100616.

P. Kuppusamy and V. C. Bharathi, “Human abnormal behavior detection using CNNs in crowded and uncrowded surveillance – A survey,” Meas. Sensors, vol. 24, no. October, p. 100510, 2022, doi: 10.1016/j.measen.2022.100510.

A. Shah et al., “A comprehensive study on skin cancer detection using artificial neural network (ANN) and convolutional neural network (CNN),” Clin. eHealth, vol. 6, pp. 76–84, 2023, doi: 10.1016/j.ceh.2023.08.002.

A. Kamel, B. Sheng, P. Yang, P. Li, R. Shen, and D. D. Feng, “Deep Convolutional Neural Networks for Human Action Recognition Using Depth Maps and Postures,” pp. 1–14, 2018.

Y. Zhang, J. Gao, and H. Zhou, “Breeds Classification with Deep Convolutional Neural Network,” ACM Int. Conf. Proceeding Ser., pp. 145–151, 2020, doi: 10.1145/3383972.3383975.

R. Chikkala, S. Edara, and P. Bhima, “Human facial image age group classification based on third order four pixel pattern (TOFP) of wavelet image,” Int. Arab J. Inf. Technol., vol. 16, no. 1, pp. 30–40, 2019.

K. Kärkkäinen and J. Joo, “FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age,” 2019, [Online]. Available: http://arxiv.org/abs/1908.04913.

V. Mirjalili, S. Raschka, and A. Ross, “PrivacyNet: Semi-Adversarial Networks for Multi-Attribute Face Privacy,” IEEE Trans. Image Process., vol. 29, pp. 9400–9412, 2020, doi: 10.1109/TIP.2020.3024026.

B. Johnston and P. de Chazal, “A review of image-based automatic facial landmark identification techniques,” Eurasip J. Image Video Process., vol. 2018, no. 1, 2018, doi: 10.1186/s13640-018-0324-4.

A. Nurhadiyatna, S. Cahyadi, F. Damatraseta, and Y. Rianto, “Adult content classification through deep convolution neural network,” in Proceedings - 2017 International Conference on Computer, Control, Informatics and its Applications: Emerging Trends In Computational Science and Engineering, IC3INA 2017, 2017, vol. 2018-Janua, pp. 106–110, doi: 10.1109/IC3INA.2017.8251749.

C. Gautam and K. . Seeja, “Facial emotion recognition using Handcrafted features and CNN,” Procedia Comput. Sci., vol. 218, no. 2022, pp. 1295–1303, 2023, doi: 10.1016/j.procs.2023.01.108.

L. F. de J. Silva, O. A. C. Cortes, and J. O. B. Diniz, “A novel ensemble CNN model for COVID-19 classification in computerized tomography scans,” Results Control Optim., vol. 11, no. December 2022, p. 100215, 2023, doi: 10.1016/j.rico.2023.100215.

G. Liang, H. Hong, W. Xie, and L. Zheng, “Combining Convolutional Neural Network With Recursive Neural Network for Blood Cell Image Classification,” vol. 6, 2018.

Y. Nie, S. Xia, and Y. Wu, “Wheel classification using convolutional neural networks,” in Proceedings - 2018 33rd Youth Academic Annual Conference of Chinese Association of Automation, YAC 2018, 2018, vol. 1, no. C, pp. 515–520, doi: 10.1109/YAC.2018.8406429.

P. Zhou, X. Han, V. I. Morariu, and L. S. Davis, “Two-Stream Neural Networks for Tampered Face Detection,” pp. 1831–1839, 2017, doi: 10.1109/CVPRW.2017.229.

H. Han, C. Otto, X. Liu, and A. K. Jain, “Demographic estimation from face images: Human vs. machine performance,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 6, pp. 1148–1161, 2015, doi: 10.1109/TPAMI.2014.2362759.

N. N. Prakash, V. Rajesh, D. L. Namakhwa, S. Dwarkanath Pande, and S. H. Ahammad, “A DenseNet CNN-based liver lesion prediction and classification for future medical diagnosis,” Sci. African, vol. 20, 2023, doi: 10.1016/j.sciaf.2023.e01629.