Intelligent Face Detection and Recognition System

Sikder, Juel; Chakma, Rana Joyti; Das, Utpol Kanti

doi:10.1109/conit51480.2021.9498291

Cited by 9 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The presented approach achieves 99.65% accuracy to decide if an individual wearing a mask or not, however, the used dataset (Real-World-Masked-Face-Dataset) does not contain wide variations in mask types, alternation in appearance and viewpoint (frontal faces and view faces), as these variations can have a strong influence on degrading the accuracy. Voila-Jones together with Haar Cascade and Principal Component Analysis (PCA) were used in [31] for achieving improved face detection system. Furthermore, a Masked Facial Recognition (MFR) approach is proposed in [22] for masked and unmasked face detection system.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid ROI Extraction Approach for Mask and Unmask Facial Recognition System using Light-CNN

Ahmed,

S. Alghareb

2024

IJCDS

View full text Add to dashboard Cite

In recent years, deep learning-based algorithms have been immensely employed and tested in a variety of real-world applications. The efficacy of such algorithms has been thoroughly examined in a practical setting. In this paper, CNN-based deep learning approaches are utilized to recognize faces in real-time to identify faces with and without mask. We employ pre-trained algorithms (YOLOv2 and SSD) to identify people wearing a face mask, which enables a machine to perform recognition tasks while evolving through a learning method. Meanwhile, if there is more than one person in the scene, the one with the max score will be selected for classification. Thus, a hybrid approach that combines YOLOv2 and SSD algorithms to work in parallel is developed for masked-face extraction. Likewise, the Viola-Jones algorithm is used here to detect faces without mask and randomly select a single region of interest (ROI) to be stored for classification. All pre-processing algorithms work separately in parallel as reconstruction steps for preprocessing to crop the ROI and store images for training and testing dataset. Followed by developing a lightweight computational complexity CNN model for face mask recognition to identify whether the selected person's face is wearing a mask or not. The dataset contains numerous variations in appearance and viewpoint to capture different scenarios with and without mask faces. On average, the proposed face mask detection architecture realizes recall and F1 score of 98.3% and 98.31%, respectively. The training performance, on the other hand, has improved by 32.1% for training time as compared to AlexNet and 40.43% of storage space (model size) reduction compared to EfficientNet-B0. The presented framework architecture is an efficient face mask and unmask detector and can be employed as a robust medical assistant face detector in the healthcare sector for automated tracking of a patient, visitor, or staff member wearing a mask or not.

show abstract

Section: Related Workmentioning

confidence: 99%

A Hybrid ROI Extraction Approach for Mask and Unmask Facial Recognition System using Light-CNN

Ahmed,

S. Alghareb

2024

IJCDS

View full text Add to dashboard Cite

show abstract

“…In this study, instead of the default CNN classifier, we called a multi-support vector machine (M-SVM) in order to create a classifier. SVM is one of the most widely used algorithms used for regression and classification [17], [18]. Training and calculating weights of M-CNN for all q ← 1 to m do 1.…”

Section: ) Call Multi Support Vector Machinementioning

confidence: 99%

An Approach Based on Deep Learning for Recognizing Emotion, Gender and Age

Nippon

Juel

2022

Preprint

View full text Add to dashboard Cite

At the same time, recognizing the emotions, gender and age of a person is a vital issue in real life. This research focuses on identifying the emotions along with age and gender of different ages male, female, common gender and children. In this study, a modified convolutional neural network (M-CNN) has been proposed for feature extraction where classification is followed by a Multi Support Vector Machine (M-SVM). Instead of detecting the face, a head-detecting technique is also used in the prediction part. To detect the head we proposed a system using the You Only Look Once Version 3 (YOLOV3) network. It helps to extract the feature from the whole head instead of the only face. Three datasets named AR-2022, FER-2022 and GR-2022 are introduced in this study. We also include the common gender in our datasets. In the case of age classification, we categorized the age datasets into 11 categories depending on the similarity of their features, gender into 3 categories and emotions into 7 categories. Our proposed model is compared with other existing models and current research, where the proposed model gives better accuracy and the accuracy of classification of emotions, age and gender are 97.47%, 98.43% and 96.65% respectively.

show abstract