Efficientnet-Lite and Hybrid CNN-KNN Implementation for Facial Expression Recognition on Raspberry Pi

Wahab, Mohd Nadhir Ab; Nazir, Amril; Ren, Anthony Tan Zhen; Noor, Mohd Halim Mohd; Akbar, M.S.; Mohamed, Ahmad Sufril Azlan

doi:10.1109/access.2021.3113337

Cited by 61 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 4 shows the comparison of existing FER models and proposed fused deep learning method. Our proposed fused deep learning method achieved maximum accuracy of 85.96% which is 12.45% higher than CNN‐KNN, 73 12.5% higher than the ensemble of 8 CNN, 74 16.24% higher than CNN with VGG, 74 20.89% higher than human accuracy 75 and 32.87% higher than HoG + SVM 76 …”

Section: Performance Analysismentioning

confidence: 89%

Fused deep learning based Facial Expression Recognition of students in online learning mode

Sumalakshmi

Vasuki²

2022

Concurrency and Computation

View full text Add to dashboard Cite

In this research work, Facial Expression Recognition (FER) is used in the analysis of facial expressions during the online learning sessions in the prevailing pandemic situation. An integrated geometric and appearance feature extraction is presented for the FER of the students participating in the online classes. The integrated features provided a low-dimensional significant feature area for better facial data representation. Feasible Weighted Squirrel Search Optimization (FW-SSO) algorithm is applied for selecting the optimal features due to its efficient exploration of the search space and enhancement of the dynamic search. The output of the FW-SSO algorithm is used for tuning the autoencoder. Autoencoder is used for combining the G&A features, for feature optimization process. Classification is done by using Long Short-Term Memory (LSTM) network with Attention Mechanism (ALSTM), as it is highly efficient in capturing the long-term dependency of the facial landmarks in the image/video sequences.The proposed fused deep learning method focuses on the fusion of the G&A features for high discrimination. Experimental analysis using FER-2013 and LIRIS datasets demonstrated that the proposed method achieved maximum accuracy of 85.96% than the existing architectures and maximum accuracy of 88.24% than the VGGNet-CNN architecture.

show abstract

Section: Performance Analysismentioning

confidence: 89%

Fused deep learning based Facial Expression Recognition of students in online learning mode

Sumalakshmi

Vasuki²

2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…The core idea of the K-nearest-neighbor (KNN) algorithm [34][35][36][37][38][39][40][41] is to search the top K feature points with the highest similarity in another feature space as candidate features. After adaptive histogram equalization, the details of the dark part of the original image become clearer and the candidate points with a higher Harris response value change during feature point detection, so high-quality matching point pairs in other areas of the same image can be obtained.…”

Section: Knn Matching Algorithm To Eliminate Mismatchingmentioning

confidence: 99%

Section: Knn Matching Algorithm To Eliminate Mismatchingmentioning

confidence: 99%

Fast Target Recognition Based on Improved ORB Feature

et al. 2022

View full text Add to dashboard Cite

A novel fast target recognition algorithm is proposed under the dynamic scene moving target recognition. Aiming at the poor matching effect of the traditional Oriented Fast and Rotated Brief (ORB) algorithm on underexposed or overexposed images caused by illumination, the idea of combining adaptive histogram equalization with the ORB algorithm is proposed to get better feature point quality and matching efficiency. First, the template image and each frame of the video stream are processed by grayscale. Second, the template image and the image to be input in the video stream are processed by adaptive histogram equalization. Third, the feature point descriptors of the ORB feature are quantized by the Hamming distance. Finally, the K-nearest-neighbor (KNN) matching algorithm is used to match and screen feature points. According to the matching good feature point logarithm, a reasonable threshold is established and the target is classified. The comparison and verification are carried out by experiments. Experimental results show that the algorithm not only maintains the superiority of ORB itself but also significantly improves the performance of ORB under the conditions of underexposure or overexposure. The matching effect of the image is robust to illumination, and the target to be detected can be accurately identified in real time. The target can be accurately classified in the small sample scene, which can meet the actual production requirements.

show abstract

“…They educated our version on the FER-2013 dataset after which as compared its overall performance to that of different architectures educated in the equal dataset. Their version cangenerate an accuracy of 76% [4].The raspberry pi module is so precise that it can be used in applications that require the analysis of minute details. Research by a team of researchers from the University of Chile is proof of the above statement.…”

Section: Literature Surveymentioning

confidence: 99%

Internet-based cattle health monitoring system using raspberry Pi

Kumar¹,

Vardhan²,

Swetha

et al. 2022

ijhs

View full text Add to dashboard Cite

Cattle farming is one of the major branches of agriculture. People who grew and monitor cattle often don’t have just a few of them. Instead, they have many numbers of cows, horses, oxen, etc. When the number of cattle increases, it becomes tougher for the one who maintains the cattle to check up on their health individually. To resolve this issue, this study aims the development of an IoT system that is capable of monitoring the temperature and heartbeat rate of the sensor periodically. This is achieved using sensors like temperature sensors, heartbeat rate sensors, etc. It also uses software like ThingSpeak, Rasbian OS, etc. The temperature of the cattle is measured with a temperature sensor and transmitted to the raspberry pi. The heart rate sensor also sends data about the cattle's heartbeat rate to the pi. The GPS sends the cattle's latitude and longitude to the module. The information is then sent to the ThingSpeak software. The data collected by the sensors is displayed by ThingSpeak software. The data includes the temperature of the cow, the heartbeat rate of the cattle, and the latitude and longitude details of the cow.

show abstract

Efficientnet-Lite and Hybrid CNN-KNN Implementation for Facial Expression Recognition on Raspberry Pi

Cited by 61 publications

References 19 publications

Fused deep learning based Facial Expression Recognition of students in online learning mode

Fused deep learning based Facial Expression Recognition of students in online learning mode

Fast Target Recognition Based on Improved ORB Feature

Internet-based cattle health monitoring system using raspberry Pi

Contact Info

Product

Resources

About