Fig 5 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
A Comparison of the Face Recognition Accuracy for 2D LBP, PCA, SVM and 3D LBP, PCA, SVM Face Recognition Methods.
Source publication
Face recognition has been one of the popular and important parts in Human Computer Interaction (HCI) systems that find tremendous applications, some of which are very critical like access control, surveillance, etc. There are numerous techniques available to process face images and hence, choosing an optimal algorithmic chain is not a straight forw...
Contexts in source publication
Context 1
... Fig. 3 for the overall implementation flow and Table 1 for detailed explanation. In total, we define three chains-1 (Path 2, 5). We used balanced training, i.e. the first 50% of the samples are used for training the classifier and the rest of the 50% face images were used for the testing purpose. ...
Context 2
... face recognition algorithm for both 2D and 3D face images using LBP operator and PCA algorithm with SVM as the classifier provided very good results, in terms of recognition rates. Figure 5 shows the accuracy of the developed methodology of using LBP and PCA algorithms with SVM as the classifier for 2D and 3D face images. A significant increase in accuracy is observed for the 3D face recognition system. ...
Citations
... Face recognition using an optimized algorithm chain for both 2D and 3D images gives an accuracy about 96% with SVM classifier using LBP and PCA. Further testing on 2D and 3D images using LBP and PCA with FFBPNN (Feed Forward Back Propagation Neural Network) is less effective and efficient as compared to the SVM classifier [8]. Locality Preserving Projections (LPPs) have been used for manifold systems originated from Local Binary Pattern (LBP) subjects [9]. ...
Abstract—In order to explore the accompanying examination goals for facial expression recognition, a proper combination of classification and adequate feature extraction is necessary. If inadequate features are used, even the best classifier could fail to achieve accurate recognition. In this paper, a new fusion technique for human facial expression recognition is used to accurately recognize human facial expressions. A combination of Discrete Wavelet Features (DWT), Local Binary Patterns (LBP), and Histogram of Gradients (HoG) feature extraction techniques was used to investigate six human emotions. K-Nearest Neighbors (KNN), Decision Tree (DT), Multi-Layer Perceptron (MLP), and Random Forest (RF) were chosen for classification. These algorithms were implemented and tested on the Static Facial Expression in Wild (SWEW) dataset which consists of facial expressions of high accuracy. The proposed algorithm exhibited 87% accuracy which is higher than the accuracy of the individual algorithms. Keywords-ANN; FER; DWT; LBP; HOG; K-Nearest Neighbors.
... Face recognition using an optimized algorithm chain for both 2D and 3D images gives an accuracy about 96% with SVM classifier using LBP and PCA. Further testing on 2D and 3D images using LBP and PCA with FFBPNN (Feed Forward Back Propagation Neural Network) is less effective and efficient as compared to the SVM classifier [8]. Locality Preserving Projections (LPPs) have been used for manifold systems originated from Local Binary Pattern (LBP) subjects [9]. ...
In order to explore the accompanying examination goals for facial expression recognition, a proper combination of classification and adequate feature extraction is necessary. If inadequate features are used, even the best classifier could fail to achieve accurate recognition. In this paper, a new fusion technique for human facial expression recognition is used to accurately recognize human facial expressions. A combination of Discrete Wavelet Features (DWT), Local Binary Pattern (LBP), and Histogram of Gradients (HoG) feature extraction techniques was used to investigate six human emotions. K-Nearest Neighbors (KNN), Decision Tree (DT), Multi-Layer Perceptron (MLP), and Random Forest (RF) were chosen for classification. These algorithms were implemented and tested on the Static Facial Expression in Wild (SWEW) dataset which consists of facial expressions of high accuracy. The proposed algorithm exhibited 87% accuracy which is higher than the accuracy of the individual algorithms.
... Ma et al. [25] proposed a generalized variability model that utilizes a mixture of Gaussians model (MoG), thus allowing it to approximate any arbitrary distribution. The conventional total variability model is a special case of generalized model obtained by confining the number of mixtures to one. ...
... However, DNN-HMM with proper number of hidden layers could improve the state labelling and hence obtains better speaker verification results. Figure 7 shows the overall summary of speaker recognition accuracy for the proposed MAHCC with DHMM as classifier comparing with the existing 2D LBP and PCA algorithm, 3D LBP and PCA algorithm with SVM classifiers and 3D LBP and PCA algorithm with FFBPNN as the classifiers [25]. On comparing to all the existing methods our proposed method achieves higher accuracy due to the efficient extraction of the features. ...
Speaker verification is the process used to recognize a speaker from his/her voice characteristics by extracting the features. Speaker verification with text-independent data is a process of verifying the speaker identity without limitation in the speech content. In the speaker verification process, long utterances are normally used but it contains lot of silences leading to complexity and more disruptions. So, we are performing speaker verification method based on short utterance data. The main objective of the research work is to extract, characterize, and recognize the information about speaker identity. Our proposed work contains four stages: 1) utterance partitioning, 2) feature extraction, 3) feature selection, and 4) classification. In our proposed model, an utterance partitioning approach is used to shorten the full-length speech into numerous short-length utterances before the pre-processing stage. In the feature extraction phase, noise removal is carried out with pre-emphasis filter in the pre-processing step. The Mel Advanced Hilbert-Huang Cepstral Coefficients (MAHCC) technique is used for extracting the features from the given input speech signal. Furthermore, the feature selection process is done with the help of a Crow Search Algorithm (CSA) by ranking the given feature set to obtain optimal features for classification. In the classification stage, the Deep Hidden Markov Model (DHMM) method is introduced to classify the features for speaker verification with discriminative pre-training process. Thus, the proposed approach provides an accurate classification and the implementation results show that the performance of the proposed method is better than the existing methods.
... Reflections can also prove detrimental to the system's facial recognition abilities. To improve this system, the system should be able to accurately distinguish a human face from patterns of dirt, print, or illumination that resemble a human face [28]. To accomplish this, a better method of facial recognition should be employed. ...
