Dynamic Facial Expression Recognition based on Two-Stream-CNN with LBP-TOP

Feng, Duo; Ren, Fuji

doi:10.1109/ccis.2018.8691380

Cited by 24 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These constraint values were chosen to explore how compact a network architecture for facial expression classification can be while still maintaining sufficient classification accuracy for use in real-time embedded scenarios. As such, we use the accuracy of Feng & Ren ( Feng and Ren, 2018 ) as the reference baseline for determining the accuracy constraint in the indicator function.…”

Section: Methodsmentioning

confidence: 99%

EmotionNet Nano: An Efficient Deep Convolutional Neural Network Design for Real-Time Facial Expression Recognition

Lee

Wang

Wong

2021

Front. Artif. Intell.

View full text Add to dashboard Cite

While recent advances in deep learning have led to significant improvements in facial expression classification (FEC), a major challenge that remains a bottleneck for the widespread deployment of such systems is their high architectural and computational complexities. This is especially challenging given the operational requirements of various FEC applications, such as safety, marketing, learning, and assistive living, where real-time requirements on low-cost embedded devices is desired. Motivated by this need for a compact, low latency, yet accurate system capable of performing FEC in real-time on low-cost embedded devices, this study proposes EmotionNet Nano, an efficient deep convolutional neural network created through a human-machine collaborative design strategy, where human experience is combined with machine meticulousness and speed in order to craft a deep neural network design catered toward real-time embedded usage. To the best of the author’s knowledge, this is the very first deep neural network architecture for facial expression recognition leveraging machine-driven design exploration in its design process, and exhibits unique architectural characteristics such as high architectural heterogeneity and selective long-range connectivity not seen in previous FEC network architectures. Two different variants of EmotionNet Nano are presented, each with a different trade-off between architectural and computational complexity and accuracy. Experimental results using the CK + facial expression benchmark dataset demonstrate that the proposed EmotionNet Nano networks achieved accuracy comparable to state-of-the-art FEC networks, while requiring significantly fewer parameters. Furthermore, we demonstrate that the proposed EmotionNet Nano networks achieved real-time inference speeds (e.g., >25 FPS and >70 FPS at 15 and 30 W, respectively) and high energy efficiency (e.g., >1.7 images/sec/watt at 15 W) on an ARM embedded processor, thus further illustrating the efficacy of EmotionNet Nano for deployment on embedded devices.

show abstract

Section: Methodsmentioning

confidence: 99%

EmotionNet Nano: An Efficient Deep Convolutional Neural Network Design for Real-Time Facial Expression Recognition

Lee

Wang

Wong

2021

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…WRNs improved accuracy and reduced the training time compared with thin and very deep counterparts. Feng and Ren [19] proposed a stochastic depth drop-path approach which randomly drops a subset of layers and bypasses them with identity function. Their experiments showed that their method shortened training time substantially and reduced the test errors.…”

Section: Residual Network Variantsmentioning

confidence: 99%

“…The associate editor coordinating the review of this article and approving it for publication was Paolo Napoletano. object detection [14], [15], image segmentation [16], [17], facial expression recognition [18], [19]. Since LeNet [20] introduced the use of deep neural network architectures for computer vision tasks, the advanced architecture AlexNet [21] acquired ground-breaking victory at the Ima-geNet competition in 2012 by a large margin over traditional methods.…”

Section: Introductionmentioning

confidence: 99%

Feature Reuse Residual Networks for Insect Pest Recognition

Ren

Liu

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Insect pests are one of the main threats to the commercially important crops. An effective insect pest recognition method can avoid economic losses. In this paper, we proposed a new and simple structure based on the original residual block and named as feature reuse residual block which combines feature from the input signal of a residual block with the residual signal. In each feature reuse residual block, it enhances the capacity of representation by learning half and reuse half feature. By stacking the feature reuse residual block, we obtained the feature reuse residual network (FR-ResNet) and evaluated the performance on IP102 benchmark dataset. The experimental results showed that FR-ResNet can achieve significant performance improvement in terms of insect pest classification. Moreover, to demonstrate the adaptive of our approach, we applied it to various kinds of residual networks, including ResNet, Pre-ResNet, and WRN, and we tested the performance on a series of benchmark datasets: CIFAR-10, CIFAR-100, and SVHN. The experimental results showed that the performance can be improved obviously than original networks. Based on these experiments on CIFAR-10, CIFAR-100, SVHN, and IP102 benchmark datasets, it demonstrates the effectiveness of our approach. INDEX TERMS Insect pest recognition, feature reuse, residual network.

show abstract

“…The convolutional neural network, CNN, is one of the main networks for image classification and recognition. CNN can be utilized for deep object learning, object detection recognition, and the like [19].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Using CNN's Gait Recognition to Strengthen Laboratory Safety Supervision

2019

Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering

View full text Add to dashboard Cite

In addition to manual management, the security measures of important facilities such as school laboratories mainly rely on human body recognition systems. Gait recognition is non-intrusive, the identification process is fast and simple, and the recognition method is less affected by clothes, which makes it suitable for laboratory's safety monitoring purposes. This paper uses the form of gait energy image to extract the gait information features of the human body. The main contribution of the paper is the improvement of existing CNN models, adding a batch-normalization layer to for better recognition. Two types of experiments were conducted. The first experiment is a comparison with previous methods using the CASIA standard dataset. The second experiment is the evaluation with our new dataset using OpenCV to collect gait information in an actual laboratory environment. The results of the experiment show that the proposed method and its application in a real environment are feasible to enhance laboratory safety monitoring.

show abstract

Dynamic Facial Expression Recognition based on Two-Stream-CNN with LBP-TOP

Cited by 24 publications

References 26 publications

EmotionNet Nano: An Efficient Deep Convolutional Neural Network Design for Real-Time Facial Expression Recognition

EmotionNet Nano: An Efficient Deep Convolutional Neural Network Design for Real-Time Facial Expression Recognition

Feature Reuse Residual Networks for Insect Pest Recognition

Using CNN's Gait Recognition to Strengthen Laboratory Safety Supervision

Contact Info

Product

Resources

About