Emotion recognition using support vector machine and one-dimensional convolutional neural network

Sujanaa, J.; Palanivel, S.; Balasubramanian, M.

doi:10.1007/s11042-021-11041-5

Cited by 11 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of population 10 and a maximum number of iterations of 25 were considered for the experiment for the implemented V‐FER model. The proposed D‐TSA algorithm was evaluated with other algorithms like “particle swarm optimization (PSO), 37 gray wolf optimization (GWO), 38 whale optimization algorithm (WOA), 39 TSA, 36 and machine learning algorithms like neural network (NN), 40 deep belief network (DBN), 41 SVM, 42 K‐nearest neighbor (KNN), 43 RNN 44 …”

Section: Resultsmentioning

confidence: 99%

“…The number of population 10 and a maximum number of iterations of 25 were considered for the experiment for the implemented V-FER model. The proposed D-TSA algorithm was evaluated with other algorithms like "particle swarm optimization (PSO), 37 gray wolf optimization (GWO), 38 whale optimization algorithm (WOA), 39 TSA, 36 and machine learning algorithms like neural network (NN), 40 deep belief network (DBN), 41 SVM, 42 K-nearest neighbor (KNN), 43 RNN. 44 " In expert systems and statistics, the learning percentage is an optimizing constraint in a meta-heuristic algorithm that regulates the step size at every iteration while moving around a minimum of a loss function.…”

Section: Experimental Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic FERNet: Deep learning with optimal feature selection for face expression recognition in video

Jagadeesh

Baranidharan

2022

Concurrency and Computation

View full text Add to dashboard Cite

This work concentrates on the recognition of facial emotion from video sequences with deep learning. Once the input video is converted into frames, the face detection is performed on each frame using the viola-jones face detection algorithm.Then, the feature extraction is performed by three well-performing feature extraction techniques like modified local directional pattern, spatio-temporal features, and scale-invariant feature transforms. The extracted features from all the frames of the video are concatenated. To reduce the feature-length for decreasing the training complexity, and enhance the recognition performance, the optimal feature selection is accomplished with the distance-based tunicate swarm algorithm. These selected features are processed to an innovative deep learning model termed a heuristically modified recurrent neural network. The same D-TSA improves the performance of RNN by optimally tuning its hidden neurons. Experimental results on a widely used benchmark dataset and manually collected dataset show that the classification performance is improved using spatio-temporal features, SIFT, M-LDP, and optimal feature selection, and thus, the proposed model with HM-RNN outperforms the other existing models. K E Y W O R D Sdistance-based tunicate swarm algorithm, face expression recognition in the video, heuristically modified recurrent neural network, Viola-Jones face detection algorithm INTRODUCTIONEmotions in human beings are understood by their facial expressions that are analyzed to identify the nature of that individual and their intentions. 1Hence, understanding these facial expressions is a persistent issue in the area of human-computer interaction (HCI). 2 Thus, these facial analyzes are broadly researched based on computer vision, in which certain applications like facial expression recognition and face recognition seek more attention in the improvement of network architectures. 3 Face expression recognition provides automated analysis in the practical applications for recognizing the facial expressions in videos, which influences the interaction interface between the human robots, which is the study of making communications among the humans and robots. Recently, the facial recognition approaches analyze the video frames using six basic expressions and also evaluated the neutral expression in the frames. 4 Similarly, face recognition methods are considered to be a significant biometric technique in many fields for providing authentication. 5 These methods use dynamic features like variations in facial texture and facial landmarks that provide eminent information for showing the emotional status. Thus, extracting the dynamic information from the whole video sequence is essential for recognizing the facial expression. These facial expression analysis systems are employed for categorizing the image or video sequence among the six basic expressions into single basic emotion. 6

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

Dynamic FERNet: Deep learning with optimal feature selection for face expression recognition in video

Jagadeesh

Baranidharan

2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Sujanaa and Palanivel [29] used datasets comprising of mouth images in the form of video frames to categorize emotions into happy, normal, and surprise. Histogram Oriented Gradient (HOG) and LBP were used to extract features, while the SVM and one-dimensional neural network were trained to detect these emotions, and accuracy of 97.44 and 98.51% were achieved, respectively.…”

Section: Review Of Related Literaturementioning

confidence: 99%

Perspective on Dark-Skinned Emotion Recognition Using Deep-Learned and Handcrafted Feature Techniques

Irhebhude¹,

Kolawole²,

Amos³

2023

Emotion Recognition - Recent Advances, New Perspectives and Applications

View full text Add to dashboard Cite

Image recognition has been widely used in various fields of applications such as human—computer interaction, where it can enhance fluency, accuracy, and naturalness in interaction. The need to automate the decision on human expression is high. This paper presents a technique for emotion recognition and classification based on a combination of deep-learned and handcrafted features. Residual Network (ResNet) and Rotation Invariant Local Binary Pattern (RILBP) features were combined and used as features for classification. The aim is to classify, identify, and make judgment on facial images from dark-skinned facial images. Facial Expression Recognition 2013 (FER2013) and self-captured dark-skinned datasets were used for the experiment and validated. The result showed 93.4% accuracy on FER dataset and 95.5% on self-captured dataset, which proved the efficiency of the proposed model.

show abstract

“…Thus, the technique performed worse than the original HOG paradigm but proved that pedestrian detection with HOG-based multi-convolutional features could obtain a high detection accuracy and stabilized network performance. Then Sujanaa et al [ 16 ] proposed to eliminate pedestrian detection and classification issues by introducing the combined pyramid histogram of oriented gradient (PHOG) and CNN algorithm for real-time object tracking. They used the PHOG descriptor to create pyramid histograms over the entire image and attach them into a single vector, whereas the CNN is used as the classifier for the PHOG features extracted from the window’s raw image data.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Detection Quality Rate with a Combined HOG and CNN for Real-Time Multiple Object Tracking across Non-Overlapping Multiple Cameras

Kalake

Dong

Wan

et al. 2022

Sensors

View full text Add to dashboard Cite

Multi-object tracking in video surveillance is subjected to illumination variation, blurring, motion, and similarity variations during the identification process in real-world practice. The previously proposed applications have difficulties in learning the appearances and differentiating the objects from sundry detections. They mostly rely heavily on local features and tend to lose vital global structured features such as contour features. This contributes to their inability to accurately detect, classify or distinguish the fooling images. In this paper, we propose a paradigm aimed at eliminating these tracking difficulties by enhancing the detection quality rate through the combination of a convolutional neural network (CNN) and a histogram of oriented gradient (HOG) descriptor. We trained the algorithm with an input of 120 × 32 images size and cleaned and converted them into binary for reducing the numbers of false positives. In testing, we eliminated the background on frames size and applied morphological operations and Laplacian of Gaussian model (LOG) mixture after blobs. The images further underwent feature extraction and computation with the HOG descriptor to simplify the structural information of the objects in the captured video images. We stored the appearance features in an array and passed them into the network (CNN) for further processing. We have applied and evaluated our algorithm for real-time multiple object tracking on various city streets using EPFL multi-camera pedestrian datasets. The experimental results illustrate that our proposed technique improves the detection rate and data associations. Our algorithm outperformed the online state-of-the-art approach by recording the highest in precisions and specificity rates.

show abstract

Emotion recognition using support vector machine and one-dimensional convolutional neural network

Cited by 11 publications

References 33 publications

Dynamic FERNet: Deep learning with optimal feature selection for face expression recognition in video

Dynamic FERNet: Deep learning with optimal feature selection for face expression recognition in video

Perspective on Dark-Skinned Emotion Recognition Using Deep-Learned and Handcrafted Feature Techniques

Enhancing Detection Quality Rate with a Combined HOG and CNN for Real-Time Multiple Object Tracking across Non-Overlapping Multiple Cameras

Contact Info

Product

Resources

About