Journal of Innovative Image Processing
IRO Journals
Volume 8 — Issue 1 — March 2026

A Hybrid Multitasking Cascaded CNN leveraging Xception Architecture for Enhanced Face Recognition

https://doi.org/10.36548/jiip.2026.1.021
Pages: 391-414
PDF
Tamilselvi M.
Department of Electronics and Communication Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, (SIMATS), Chennai, India
March 2026
Volume 8 — Issue 1
Journal of Innovative Image Processing
PDF

How to Cite

M., Tamilselvi. 2026. “A Hybrid Multitasking Cascaded CNN Leveraging Xception Architecture for Enhanced Face Recognition”. Journal of Innovative Image Processing 8 (1): 391-414. https://doi.org/10.36548/jiip.2026.1.021.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Face Recognition
— Xception Based Multitask Cascaded CNN
— XMCCNN
— Convolutional Neural Network
— VGG-16
— Digital Image Processing
— Smart Technologies
Published: 25-03-2026

Abstract

Face recognition technology plays a significant role in surveillance systems, authentication systems, and systems that allow people and computers to communicate with each other. The main aim of face recognition technology is to identify individuals based on their facial features. It is crucial to analyze facial features accurately in today's world, where numerous smart devices and surveillance systems are installed globally. Deep learning algorithms such as CNN, VGG16, and ResNet have shown promising results in improving the accuracy of face recognition technology, but the results are not sufficient in open environments. This paper proposes a new face recognition system that utilizes deep learning concepts. The proposed system aims to perform tasks such as detecting faces, locating landmarks, and recognizing faces. It employs depth-wise separable convolutional networks to reduce the number of parameters and optimize the features. The system is rigorously tested using various datasets, including LFW, CelebA, and CASIA-WebFace, and demonstrates exceptional performance by achieving 98.3% accuracy in face recognition. Additionally, the proposed system achieved 4.8% higher accuracy and 32% lower latency compared to existing face recognition systems.

References

  1. Alhakbani, Noura, Maha Alghamdi, and Abeer Al-Nafjan. "Design and development of an imitation detection system for human action recognition using deep learning." Sensors 23, no. 24 (2023): 9889. https://doi.org/10.3390/s23249889
  2. Berle, Ian. (2020). Face Recognition Technology: Compulsory Visibility and Its Impact on Privacy and the Confidentiality of Personal Identifiable Images. 10.1007/978-3-030-36887-6.
  3. Sujatha, G., Swathi, M., Bugge, B. P., Basha, S. J., Alluri, S., Pavuluri, B. P., Sitha Ram, M., & Borra, S. R. (2025). Multi-CNN Model to Evaluate the Performance of Face Detection and Recognition with Facial Feature Detection and Recognition. Journal of Theoretical and Applied Information Technology, 103(9), 3548-3560. https://doi.org/10.5281/zenodo.17215884
  4. Ramkumar, G., Ahmad Al-Qerem, G. Kalyani, A. Vamsi, and Devolla Manogna. "TinyFaceDL Lightweight Transformer CNN Hybrid Model for Face Recognition on Low Power IoT and Edge Devices." In 2025 7th International Conference on Innovative Data Communication Technologies and Application (ICIDCA), pp. 360-366. IEEE, 2025. https://doi.org/10.1109/ICIDCA66325.2025.11280537
  5. Elharrouss, Omar, Noor Almaadeed, Somaya Al-Maadeed, and Fouad Khelifi. "Pose-invariant face recognition with multitask cascade networks." Neural Computing and Applications 34, no. 8 (2022): 6039-6052. https://doi.org/10.1007/s00521-021-06690-4
  6. Singh, Pancham, Mrignainy Kansal, Rajeev Singh, Sushil Kumar, and Chelsi Sen. "A hybrid approach based on Haar Cascade, Softmax, and CNN for human face recognition: a hybrid approach for human face recognition." Journal of Scientific & Industrial Research (JSIR) 83, no. 4 (2024): 414-423. https://doi.org/10.56042/jsir.v83i4.3167
  7. Matulionyte, Rita, and Monika Zalnieriute, eds. The Cambridge handbook of facial recognition in the modern state. Cambridge University Press, 2024.
  8. Koul, Nimrita. Ultimate Deepfake Detection Using Python: Master Deep Learning Techniques like CNNs, GANs, and Transformers to Detect Deepfakes in Images, Audio, and Videos Using Python (English Edition). Orange Education Pvt Ltd, 2024.
  9. Paul, Anup Kumar. "Facelite: A real-time light-weight facemask detection using deep learning: A comprehensive analysis, opportunities, and challenges for edge computing." Computer Networks and Communications (2024): 83-111.
  10. Mahesh, S., and G. Ramkumar. "Smart face detection and recognition in occluded images using googlenet CNN in comparison with accuracy of SVM." In AIP Conference Proceedings, vol. 2587, no. 1, p. 050020. AIP Publishing LLC, 2023.
  11. Rodrigo, Marcos, Carlos Cuevas, and Narciso García. "Comprehensive comparison between vision transformers and convolutional neural networks for face recognition tasks." Scientific reports 14, no. 1 (2024): 21392.
  12. Russo, Samuele, Imad Eddine Tibermacine, Cristian Randieri, Abdelaziz Rabehi, Amal H. Alharbi, El-Sayed M. El-Kenawy, and Christian Napoli. "Exploiting facial emotion recognition system for ambient assisted living technologies triggered by interpreting the user's emotional state." Frontiers in Neuroscience 19 (2025): 1622194.
  13. Shi, Haiping, Yinqiu Fan, Yu Zhang, Xiaowei Li, Yuling Shu, Xinyuan Deng, Yating Zhang, Yunzi Zheng, and Jun Yang. "Intelligent bell facial paralysis assessment: a facial recognition model using improved SSD network." Scientific Reports 14, no. 1 (2024): 12763.
  14. Talukder, Animesh, and Surath Ghosh. "Facial Image expression recognition and prediction system." Scientific Reports 14, no. 1 (2024): 27760.
  15. Tian, Xue, Yiying Song, and Jia Liu. "Decoding face identity: A reverse-correlation approach using deep learning." Cognition 254 (2025): 106008.
  16. Senthil Sivakumar, M., T. Gurumekala, L. Megalan Leo, and R. Thandaiah Prabu. "Expert System for Smart Virtual Facial Emotion Detection Using Convolutional Neural Network." Wireless Personal Communications 133, no. 4 (2023): 2297-2319
  17. Chitrapu, Pavani, Mahesh Kumar Morampudi, and Hemantha Kumar Kalluri. "Robust Face Recognition Using Deep Learning and Ensemble Classification." IEEE Access (2025). 99957–99969. https://doi.org/10.1109/ACCESS.2025.3575192
  18. Soni, Laxmi Narayan, and Akhilesh A. Waoo. "A Lightweight and Efficient Hybrid CNN Model for Face Detection." International Journal of Environmental Sciences 11, no. 8s (2025): 583-591. https://doi.org/10.64252/edmkva81.
  19. Deng, Jiankang, Jia Guo, Niannan Xue, and Stefanos Zafeiriou. "Arcface: Additive angular margin loss for deep face recognition." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 4690-4699. 2019.
  20. Lee, Yongju, Sungjun Jang, Han Byeol Bae, Taejae Jeon, and Sangyoun Lee. "Multitask Learning Strategy with Pseudo-Labeling: Face Recognition, Facial Landmark Detection, and Head Pose Estimation." Sensors 24, no. 10 (2024): 3212
  21. Kortylewski, Adam, Bernhard Egger, Andreas Schneider, Thomas Gerig, Andreas Morel-Forster, and Thomas Vetter. "Analyzing and reducing the damage of dataset bias to face recognition with synthetic data." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pp. 0-0. 2019.
  22. Zhang, Zhifei, Yang Song, and Hairong Qi. "Age progression/regression by conditional adversarial autoencoder." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5810-5818. 2017.
  23. Terhörst, Philipp, Jan Niklas Kolf, Marco Huber, Florian Kirchbuchner, Naser Damer, Aythami Morales Moreno, Julian Fierrez, and Arjan Kuijper. "A comprehensive study on face recognition biases beyond demographics." IEEE Transactions on Technology and Society 3, no. 1 (2021): 16-30.
  24. Tan, Mingxing, and Quoc Le. "Efficientnetv2: Smaller models and faster training." In International conference on machine learning, pp. 10096-10106. PMLR, 2021.
  25. Rodrigo, Marcos, Carlos Cuevas, and Narciso García. "Comprehensive comparison between vision transformers and convolutional neural networks for face recognition tasks." Scientific reports 14, no. 1 (2024): 21392.