# A Comprehensive Analysis of Deep Learning Based Representation for Face Recognition

arXiv: https://arxiv.org/abs/1606.02894 · HTML: https://mlsanity.com/paper/1606.02894/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2016.

## Built on by (most cited first, 23 of 23)

- [End2End Occluded Face Recognition by Masking Corrupted Features](https://mlsanity.com/paper/2108.09468/) (2021)
- [Neuromorphic Event-based Facial Expression Recognition](https://mlsanity.com/paper/2304.06351/) (2023)
- [On Recognizing Occluded Faces in the Wild](https://mlsanity.com/paper/2109.03672/) (2021)
- [RAILS: A Robust Adversarial Immune-inspired Learning System](https://mlsanity.com/paper/2107.02840/) (2021)
- [Recent Advances in Deep Learning Techniques for Face Recognition](https://mlsanity.com/paper/2103.10492/) (2021)
- [Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition](https://mlsanity.com/paper/2104.02424/) (2021)
- [Assessment Framework for Deepfake Detection in Real-world Situations](https://mlsanity.com/paper/2304.06125/) (2023)
- [Why Don't You Clean Your Glasses? Perception Attacks with Dynamic Optical Perturbations](https://mlsanity.com/paper/2307.13131/) (2023)
- [Forward Learning for Gradient-based Black-box Saliency Map Generation](https://mlsanity.com/paper/2403.15603/) (2024)
- [Analyzing the Effect of Combined Degradations on Face Recognition](https://mlsanity.com/paper/2406.02142/) (2024)
- [Automated Visual Attention Detection using Mobile Eye Tracking in Behavioral Classroom Studies](https://mlsanity.com/paper/2505.07552/) (2025)
- [Immuno-mimetic Deep Neural Networks (Immuno-Net)](https://mlsanity.com/paper/2107.02842/) (2021)
- [Facial Emotion Recognition: A multi-task approach using deep learning](https://mlsanity.com/paper/2110.15028/) (2021)
- [Face recognition via compact second order image gradient orientations](https://mlsanity.com/paper/2201.09246/) (2022)
- [Ensemble Learning using Transformers and Convolutional Networks for Masked Face Recognition](https://mlsanity.com/paper/2210.04816/) (2022)
- [A Perception CNN for Facial Expression Recognition](https://mlsanity.com/paper/2512.06422/) (2025)
- [Towards End-to-End Neural Face Authentication in the Wild -- Quantifying and Compensating for Directional Lighting Effects](https://mlsanity.com/paper/2104.03854/) (2021)
- [Cascaded Asymmetric Local Pattern: A Novel Descriptor for Unconstrained Facial Image Recognition and Retrieval](https://mlsanity.com/paper/2201.00518/) (2022)
- [A Survey on Face Recognition Systems](https://mlsanity.com/paper/2201.02991/) (2022)
- [Advancing Smart Malnutrition Monitoring: A Multi-Modal Learning Approach for Vital Health Parameter Estimation](https://mlsanity.com/paper/2307.16745/) (2023)
- [On the Behavior of Audio-Visual Fusion Architectures in Identity Verification Tasks](https://mlsanity.com/paper/2311.05071/) (2023)
- [CAPM: Fast and Robust Verification on Maxpool-based CNN via Dual Network](https://mlsanity.com/paper/2407.09550/) (2024)
- [Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space](https://mlsanity.com/paper/2508.08808/) (2025)

## Abstract (arXiv)

Deep learning based approaches have been dominating the face recognition field due to the significant performance improvement they have provided on the challenging wild datasets. These approaches have been extensively tested on such unconstrained datasets, on the Labeled Faces in the Wild and YouTube Faces, to name a few. However, their capability to handle individual appearance variations caused by factors such as head pose, illumination, occlusion, and misalignment has not been thoroughly assessed till now. In this paper, we present a comprehensive study to evaluate the performance of deep learning based face representation under several conditions including the varying head pose angles, upper and lower face occlusion, changing illumination of different strengths, and misalignment due to erroneous facial feature localization. Two successful and publicly available deep learning models, namely VGG-Face and Lightened CNN have been utilized to extract face representations. The obtained results show that although deep learning provides a powerful representation for face recognition, it can still benefit from preprocessing, for example, for pose and illumination normalization in order to achieve better performance under various conditions. Particularly, if these variations are not included in the dataset used to train the deep learning model, the role of preprocessing becomes more crucial. Experimental results also show that deep learning based representation is robust to misalignment and can tolerate facial feature localization errors up to 10% of the interocular distance.