Regularized Hardmining loss for face recognition

Mishra, Nayaneesh Kumar; Singh, Satish Kumar

doi:10.1016/j.imavis.2021.104343

Cited by 5 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…General face images are color images, and composed of RGB models [7] . RGB model, as a color image model, is composed of R, G and B (red, green and blue) image components, and each primary color has a component image.…”

Section: Face Recognition Preprocessingmentioning

confidence: 99%

Design and application of airport face image detection system

Li,

Ding

2024

International Conference on Remote Sensing Technology and Survey Mapping (RSTSM 2024)

View full text Add to dashboard Cite

Section: Face Recognition Preprocessingmentioning

confidence: 99%

Design and application of airport face image detection system

Li,

Ding

2024

International Conference on Remote Sensing Technology and Survey Mapping (RSTSM 2024)

View full text Add to dashboard Cite

“…(4) Expressions: Varied conditions cause multiple human moods, which lead to the display of various emotions and, subsequently, changes in facial expressions. (5) Aging: The appearance of a person's face varies over time and reflects their age, which is a new problem for facial recognition algorithms. Researchers have presented techniques for occluded face recognition [12].…”

Section: Literature Reviewmentioning

confidence: 99%

“…The concept of deep learning (DL) [3][4][5][6][7] is widely utilized in many applications. However, because of the long time required for network training, using DL in a real-time environment was challenging at first.…”

Section: Introductionmentioning

confidence: 99%

“…However, because of the long time required for network training, using DL in a real-time environment was challenging at first. Since then, the recent advances in DL approaches proposed in [4][5][6][7] have motivated other authors to use the advancement of software and hardware in a parallel computing environment. Convolutional Neural Networks (CNN), Deep Belief Networks (DBN), Restricted Boltzmann Machines (RBM), Recursive Neural Networks (RNN), and Stack-Based Auto-Encoders (SAE) are examples of deep learning architectures that are effectively used in a variety of applications such as natural language processing (NLP), bioinformatics, and computer vision [8,9].…”

Section: Introductionmentioning

confidence: 99%

“…ConvMixer's ability to capture complex spatial patterns in face images efficiently makes it a powerful feature extractor, enhancing the model's discrimination and recognition capabilities. 5.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Automatic Face Recognition System Using Deep Convolutional Mixer Architecture and AdaBoost Classifier

Abbas,

Albalawi,

Perumal

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

In recent years, advances in deep learning (DL) techniques for video analysis have developed to solve the problem of real-time processing. Automated face recognition in the runtime environment has become necessary in video surveillance systems for urban security. This is a difficult task due to face occlusion, which makes it hard to capture effective features. Existing work focuses on improving performance while ignoring issues like a small dataset, high computational complexity, and a lack of lightweight and efficient feature descriptors. In this paper, face recognition (FR) using a Convolutional mixer (AFR-Conv) algorithm is developed to handle face occlusion problems. A novel AFR-Conv architecture is designed by assigning priority-based weight to the different face patches along with residual connections and an AdaBoost classifier for automatically recognizing human faces. The AFR-Conv also leverages the strengths of pre-trained CNNs by extracting features using ResNet-50, Inception-v3, and DenseNet-161. The AdaBoost classifier combines these features’ weighted votes to predict labels for testing images. To develop this system, we use the data augmentation method to enhance the number of datasets using human face images. The AFR-Conv method is then used to extract robust features from images. Finally, to recognize human identity, an AdaBoost classifier is utilized. For the training and evaluation of the AFR-Conv model, a set of face images is collected from online data sources. The experimental results of the AFR-Conv approach are presented in terms of precision (PR), recall (RE), detection accuracy (DA), and F1-score metrics. Particularly, the proposed approach attains 95.5% PR, 97.6% RE, 97.5% DA, and 98.5% of F1-score on 8500 face images. The experimental results show that our proposed scheme outperforms advanced methods for face classification.

show abstract