Joint Face Detection and Facial Expression Recognition with MTCNN

Jia, Xiang; Zhu, Guorong

doi:10.1109/icisce.2017.95

Cited by 211 publications

(65 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To extract the representations that were generated by the DCNNs, we ran the trained models in evaluation mode on a predefined set of image stimuli (see section 3.1 above). The face images were first aligned using the MTCNN face alignment algorithm (Xiang & Zhu, 2017). Following alignment, the images were normalized with the standard ImageNet normalization ( M = [0.485,0.456,0.406], SD = [0.229,0.224,0.225]).…”

Section: Methodsmentioning

confidence: 99%

Face Recognition Depends on Specialized Mechanisms Tuned to View‐Invariant Facial Features: Insights from Deep Neural Networks Optimized for Face or Object Recognition

Abudarham

Grosbard

2021

Cognitive Science

View full text Add to dashboard Cite

Face recognition is a computationally challenging classification task. Deep convolutional neural networks (DCNNs) are brain‐inspired algorithms that have recently reached human‐level performance in face and object recognition. However, it is not clear to what extent DCNNs generate a human‐like representation of face identity. We have recently revealed a subset of facial features that are used by humans for face recognition. This enables us now to ask whether DCNNs rely on the same facial information and whether this human‐like representation depends on a system that is optimized for face identification. In the current study, we examined the representation of DCNNs of faces that differ in features that are critical or non‐critical for human face recognition. Our findings show that DCNNs optimized for face identification are tuned to the same facial features used by humans for face recognition. Sensitivity to these features was highly correlated with performance of the DCNN on a benchmark face recognition task. Moreover, sensitivity to these features and a view‐invariant face representation emerged at higher layers of a DCNN optimized for face recognition but not for object recognition. This finding parallels the division to a face and an object system in high‐level visual cortex. Taken together, these findings validate human perceptual models of face recognition, enable us to use DCNNs to test predictions about human face and object recognition as well as contribute to the interpretability of DCNNs.

show abstract

Section: Methodsmentioning

confidence: 99%

Face Recognition Depends on Specialized Mechanisms Tuned to View‐Invariant Facial Features: Insights from Deep Neural Networks Optimized for Face or Object Recognition

Abudarham

Grosbard

2021

Cognitive Science

View full text Add to dashboard Cite

show abstract

“…Besides, some preprocessing algorithm may also offer the ROI information for generating corresponding face masks. For example, we can use the facial landmark detection model [ 41 ] to predict an accurate center point of the ROI region, and generate the corresponding mask for face images.…”

Section: Methodsmentioning

confidence: 99%

Mask Attention-SRGAN for Mobile Sensing Networks

Huang

Chang

2021

Sensors

View full text Add to dashboard Cite

Biometrics has been shown to be an effective solution for the identity recognition problem, and iris recognition, as well as face recognition, are accurate biometric modalities, among others. The higher resolution inside the crucial region reveals details of the physiological characteristics which provides discriminative information to achieve extremely high recognition rate. Due to the growing needs for the IoT device in various applications, the image sensor is gradually integrated in the IoT device to decrease the cost, and low-cost image sensors may be preferable than high-cost ones. However, low-cost image sensors may not satisfy the minimum requirement of the resolution, which definitely leads to the decrease of the recognition accuracy. Therefore, how to maintain high accuracy for biometric systems without using expensive high-cost image sensors in mobile sensing networks becomes an interesting and important issue. In this paper, we proposed MA-SRGAN, a single image super-resolution (SISR) algorithm, based on the mask-attention mechanism used in Generative Adversarial Network (GAN). We modified the latest state-of-the-art (nESRGAN+) in the GAN-based SR model by adding an extra part of a discriminator with an additional loss term to force the GAN to pay more attention within the region of interest (ROI). The experiments were performed on the CASIA-Thousand-v4 dataset and the Celeb Attribute dataset. The experimental results show that the proposed method successfully learns the details of features inside the crucial region by enhancing the recognition accuracies after image super-resolution (SR).

show abstract

“…MORPH contains 55,000 face images of 13,617 identities from 16 to 77 years old. Following the prior works [10,11,17], we first extract facial regions of 200 × 200 pixels using MTCNN [18], and then resize them to 128 × 128 resolution. We split the dataset into training and test set in a ratio of 90:10 respectively.…”

Section: Methodsmentioning

confidence: 99%

Continuous Face Aging Generative Adversarial Networks

Jeon

Lee

Hong

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Face aging is the task aiming to translate the faces in input images to designated ages. To simplify the problem, previous methods have limited themselves only able to produce discrete age groups, each of which consists of ten years. Consequently, the exact ages of the translated results are unknown and it is unable to obtain the faces of different ages within groups. To this end, we propose the continuous face aging generative adversarial networks (CFA-GAN). Specifically, to make the continuous aging feasible, we propose to decompose image features into two orthogonal features: the identity and the age basis features. Moreover, we introduce the novel loss function for identity preservation which maximizes the cosine similarity between the original and the generated identity basis features. With the qualitative and quantitative evaluations on MORPH, we demonstrate the realistic and continuous aging ability of our model, validating its superiority against existing models. To the best of our knowledge, this work is the first attempt to handle continuous target ages.

show abstract

Joint Face Detection and Facial Expression Recognition with MTCNN

Cited by 211 publications

References 6 publications

Face Recognition Depends on Specialized Mechanisms Tuned to View‐Invariant Facial Features: Insights from Deep Neural Networks Optimized for Face or Object Recognition

Face Recognition Depends on Specialized Mechanisms Tuned to View‐Invariant Facial Features: Insights from Deep Neural Networks Optimized for Face or Object Recognition

Mask Attention-SRGAN for Mobile Sensing Networks

Continuous Face Aging Generative Adversarial Networks

Contact Info

Product

Resources

About