Robust face recognition based on multi-task convolutional neural network

Ge, Huilin; Dai, Yuewei; Zhu, Zhiyu; Wang, Biao

doi:10.3934/mbe.2021329

Cited by 10 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a datasets consisting of more than 800k images, a K-Fold Cross-Validation was performed on the datasets by taking ten folds and for exhaustive testing, each face image datasets is per-processed to extract features and trained in CNN to classify gestures correctly. An accuracy of 99% is achieved for most of the datasets which outperform present state-of-art and classify faces precisely[23][24][25][26][27][28][29].…”

mentioning

confidence: 85%

See 1 more Smart Citation

Enhancing a Real-time Face Recognition Accuracy With Innovative using Convolutional Neural Networks

Gamal,

Shayboub

2023

Preprint

View full text Add to dashboard Cite

This paper introduces an innovative facial recognition criminal detection system that is at the forefront of technology. Its primary goal is to identify suspects in real-time, using cutting-edge algorithms and live camera technology. By combining these advanced features, the system significantly enhances security measures and helps combat criminal activities. Facial recognition has become a prominent tool in the field of security, revolutionizing surveillance for threat detection. The user-friendly desktop application offers a wide range of features, including the ability to view crime statistics and upload suspect images. With an impressive accuracy rate of 99.38%, the system excels at identifying potential criminals, thanks to its integration with live camera sensors. Administrators benefit from additional privileges, such as direct management of the suspect database, user account control, and system monitoring. An admin dashboard provides efficient oversight of suspects, approval requests, and user management, enabling effective decision-making.

show abstract

mentioning

confidence: 85%

“…Various classifiers come into play to extract diverse facial attributes. Grayscale images derived from this phase serve as the foundation for criminal identification and model training [10][11][12][13][14][15].…”

Section: Unearthing Distinctive Featuresmentioning

confidence: 99%

Enhancing a Real-time Face Recognition Accuracy With Innovative using Convolutional Neural Networks

Gamal,

Shayboub

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We used a facial landmark tracker to locate the facial area ( 13 ). Due to the face that was masked by the aforementioned medical devices might not be detected by the facial landmark tracker, we further used multi-task CNN to locate the facial area if the face was not located by the facial landmark tracker ( 14 ). Given that the area nearby the eyebrow is the key area to interpret pain score, we hence cropped the face between hairline and nose not only to focus on the eyebrow area, but also to avoid the confounding of the aforementioned medical devices.…”

Section: Methodsmentioning

confidence: 99%

Deep Learning-Based Pain Classifier Based on the Facial Expression in Critically Ill Patients

Liu

et al. 2022

Front. Med.

View full text Add to dashboard Cite

ObjectivePain assessment based on facial expressions is an essential issue in critically ill patients, but an automated assessment tool is still lacking. We conducted this prospective study to establish the deep learning-based pain classifier based on facial expressions.MethodsWe enrolled critically ill patients during 2020–2021 at a tertiary hospital in central Taiwan and recorded video clips with labeled pain scores based on facial expressions, such as relaxed (0), tense (1), and grimacing (2). We established both image- and video-based pain classifiers through using convolutional neural network (CNN) models, such as Resnet34, VGG16, and InceptionV1 and bidirectional long short-term memory networks (BiLSTM). The performance of classifiers in the test dataset was determined by accuracy, sensitivity, and F1-score.ResultsA total of 63 participants with 746 video clips were eligible for analysis. The accuracy of using Resnet34 in the polychromous image-based classifier for pain scores 0, 1, 2 was merely 0.5589, and the accuracy of dichotomous pain classifiers between 0 vs. 1/2 and 0 vs. 2 were 0.7668 and 0.8593, respectively. Similar accuracy of image-based pain classifier was found using VGG16 and InceptionV1. The accuracy of the video-based pain classifier to classify 0 vs. 1/2 and 0 vs. 2 was approximately 0.81 and 0.88, respectively. We further tested the performance of established classifiers without reference, mimicking clinical scenarios with a new patient, and found the performance remained high.ConclusionsThe present study demonstrates the practical application of deep learning-based automated pain assessment in critically ill patients, and more studies are warranted to validate our findings.

show abstract

“…Zhang et al used MTCNN to jointly perform face detection and alignment by coarsely to finely predicting the positions of faces and landmarks [ 17 ]. Consequently, the accuracy of real-time face detection and positioning improved, MTCNN had the best comprehensive performance in face recognition [ 25 ], and MTCNN enabled rapid face detection. The trained method [ 26 ] can classify facial expressions after face detection with the MTCNN [ 27 ].…”

Section: Methodsmentioning

confidence: 99%

Comparison of Subjective Facial Emotion Recognition and “Facial Emotion Recognition Based on Multi-Task Cascaded Convolutional Network Face Detection” between Patients with Schizophrenia and Healthy Participants

et al. 2022

View full text Add to dashboard Cite

Patients with schizophrenia may exhibit a flat affect and poor facial expressions. This study aimed to compare subjective facial emotion recognition (FER) and FER based on multi-task cascaded convolutional network (MTCNN) face detection in 31 patients with schizophrenia (patient group) and 40 healthy participants (healthy participant group). A Pepper Robot was used to converse with the 71 aforementioned participants; these conversations were recorded on video. Subjective FER (assigned by medical experts based on video recordings) and FER based on MTCNN face detection was used to understand facial expressions during conversations. This study confirmed the discriminant accuracy of the FER based on MTCNN face detection. The analysis of the smiles of healthy participants revealed that the kappa coefficients of subjective FER (by six examiners) and FER based on MTCNN face detection concurred (κ = 0.63). The perfect agreement rate between the subjective FER (by three medical experts) and FER based on MTCNN face detection in the patient, and healthy participant groups were analyzed using Fisher’s exact probability test where no significant difference was observed (p = 0.72). The validity and reliability were assessed by comparing the subjective FER and FER based on MTCNN face detection. The reliability coefficient of FER based on MTCNN face detection was low for both the patient and healthy participant groups.

show abstract

Robust face recognition based on multi-task convolutional neural network

Cited by 10 publications

References 33 publications

Enhancing a Real-time Face Recognition Accuracy With Innovative using Convolutional Neural Networks

Enhancing a Real-time Face Recognition Accuracy With Innovative using Convolutional Neural Networks

Deep Learning-Based Pain Classifier Based on the Facial Expression in Critically Ill Patients

Comparison of Subjective Facial Emotion Recognition and “Facial Emotion Recognition Based on Multi-Task Cascaded Convolutional Network Face Detection” between Patients with Schizophrenia and Healthy Participants

Contact Info

Product

Resources

About