Beyond superficial emotion recognition: Modality-adaptive emotion recognition system
3
Citation
52
Reference
10
Related Paper
Citation Trend
Keywords:
Modality (human–computer interaction)
Feature (linguistics)
This paper presents a novel scheme for feature extraction for face recognition by fusing local and global discriminant features. The facial changes due to variations of pose, illumination, expression, etc. are often appeared only some regions of the whole face image. Therefore, global features extracted from the whole image fail to cope with these variations. To address these problems, face images are divided into a number of non-overlapping sub-images and then G-2DFLD method is applied to each of these sub-images as well as to the whole image to extract local and global discriminant features, respectively. The G-2DFLD method is found to be superior to other appearance-based methods for feature extraction. All these extracted local and global discriminant features are then fused to get a large feature vector. Its dimensionality is then reduced by the PCA technique to decrease overall complexity of the system. A multi-class SVM is used as a classifier for recognition based on these reduced features. The proposed method was evaluated on two popular face recognition databases, the AT&T (formerly ORL) and the UMIST face databases. The experimental results show that the new method outperforms the global features extracted by the PCA, 2DPCA, PCA+FLD, 2DFLD and G-2DFLD methods in terms of face recognition.
Feature (linguistics)
Cite
Citations (9)
Some of the best current face recognition approaches use feature extraction techniques based on either Principle Component Analysis (PCA), Local Binary Patterns (LBP), Autoencoder (non-linear PCA), etc. While each of these feature techniques works fairly well, we propose to combine multiple feature extractors with deep learning in a system so that the overall face recognition accuracy can be improved. The output from multiple feature extractions is classified using a deep learning approach. Deep learning algorithms possess high capability to learn more complex functions in order to handle difficult computer vison tasks. Our proposed method integrates the output of three different feature extractors, specifically PCA, LBP+PCA, and dimensionality reduction of LBP features using a Neural Network (NN). The features from the above three techniques are concatenated to form a joint feature vector. This feature vector is fed into a deep Sacked Sparse Autoencoder (SSA) as a classifier to generate the recognition results. Our proposed approach is evaluated by ORL and AR face databases. The experimental results indicate that our system outperforms existing ones based on individual feature techniques as well as reported systems employing multiple feature types.
Autoencoder
Feature vector
Local Binary Patterns
Feature (linguistics)
Feature Learning
Cite
Citations (3)
Feature extraction, discriminant analysis, and classification rules are three crucial issues for face recognition. We present hybrid approaches to handle three issues together. For feature extraction, we apply the multiresolution wavelet transform to extract the waveletface. We also perform the linear discriminant analysis on waveletfaces to reinforce discriminant power. During classification, the nearest feature plane (NFP) and nearest feature space (NFS) classifiers are explored for robust decisions in presence of wide facial variations. Their relationships to conventional nearest neighbor and nearest feature line classifiers are demonstrated. In the experiments, the discriminant waveletface incorporated with the NFS classifier achieves the best face recognition performance.
Feature vector
Feature (linguistics)
Cite
Citations (460)
This paper presents a new method for Synthetic Aperture Radar(SAR) images feature extraction and target recognition using independent component analysis and support vector machine. Low-frequency sub-band image is obtained by wavelet decomposition of a SAR image. Independent Component Analysis(ICA) is used for extracting feature vectors from the low-frequency sub-band image as the feature of the target. Support Vector Machine(SVM) is used to perform target recognition. The method is used for recognizing three-class targets in MSTAR database and the recognition rate arrives at 96.92%. Experimental result shows that the method is an effective method for SAR images feature extraction and target recognition.
Automatic Target Recognition
Feature (linguistics)
Feature vector
Cite
Citations (6)
Face recognition has been extensively studied by many scholars in the recent decades. Local binary pattern (LBP) is one of the most popular local descriptors and has been widely applied to face recognition. Wavelet transform is also more and more active in the field of pattern recognition. In this paper, a novel feature extraction method is proposed to overcome illumination influence. First, a given face image is processed by the LBP operator, and an LBP image is obtained. Second, wavelet transform is used to extract discriminant feature from the LBP image. The experiment results on LFW, Extended YaleB and CMU-PIE face databases show that the proposed method outperforms several popular face recognition methods, and the preprocessing step plays an important role to extract effective features for classification.
Local Binary Patterns
Feature (linguistics)
Cite
Citations (6)
NMF and FLD based feature extraction with application to Synthetic Aperture Radar target recognition
Feature extraction is a very important step in Synthetic Aperture Radar automatic target recognition (SAR ATR). In this paper, a feature extraction procedure based on the nonnegative matrix factorization (NMF) and Fisher linear discriminant (FLD) analysis is proposed for target recognition in SAR images. Firstly, segmented SAR images are processed by the NMF algorithm, which can extract nonnegative features that contain the local spatial structure information of targets. Then the FLD method is applied to the extracted features, thus the discriminability of the features can be enhanced. Both the spatial locality and separability between classes are enforced by this two-phase feature extracting procedure. Finally, the obtained features are used for automatic target recognition. Compared to several other methods, experimental results show the effectiveness of the proposed method for target feature extraction and recognition in SAR images.
Non-negative Matrix Factorization
Automatic Target Recognition
Feature (linguistics)
Cite
Citations (8)
Performance of hyperspectral image classification depends on feature extraction. Compared with conventional hand-crafted feature extraction, deep learning can learn feature with more discriminative information. In this paper, a two-channel deep convolutional neural network (Two-CNN) is proposed to learn jointly spectral-spatial feature from hyperspectral image. The proposed model is composed of two channels of CNN, each of which learns feature from spectral domain and spatial domain respectively. The learned spectral feature and spatial feature are then concatenated and fed to fully connected layer to extract joint spectral-spatial feature for classification. When number of training samples is limited, we propose to train the deep model using transfer learning to improve the performance. Low-layer and mid-layer features of the deep model are learned and transferred from other scenes, only top-layer feature is learned using the limited training samples of the current scene. Experiment results on real data demonstrate the effectiveness of the proposed method.
Discriminative model
Feature (linguistics)
Feature Learning
Cite
Citations (125)
Handwritten character recognition of Devanagari script is an area of research in the field of pattern recognition. Feature extraction is crucially significant step in recognition system. In handwritten optical character recognition, the size of feature vectors is very high. By reducing image size, the dimension of feature vectors can be reduced but this also reduces the pixel information. This paper focus on the improvement in performance of recognition system using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). In proposed system, first raw features are extracted using three different feature extraction methods: chain coding, edge detection using gradient features and direction feature techniques, which are reduced by LDA and characters are classified using SVM classifier.
Devanagari
Feature (linguistics)
Feature vector
Cite
Citations (8)
Feature extraction builds up the basis of pattern classification and recognition. The infrared image information of the target mainly concentrates on the low frequency part after being transformed by wavelet. In this paper, we propose a new kind of moment algorithm to obtain some real translation, rotation and scaling invariant features of the infrared target, and we also use neural network to classify targets. The simulation result shows that the applied method can recognize the target classification efficiently and reliably.
Feature (linguistics)
Cite
Citations (1)
The statistical Haralick features from the texture description methods GLCM, GLDM, SRDM, NGLCOM, NGLDM and Run-length features from the texture description method GLRLM are widely used to extract features in mammogram images for analysis and classification of abnormality. In this paper a novel feature extraction method based on spectral shape is proposed for classification of abnormality in mammogram image. The spectral shape features are extracted from the mammogram images and analyzed for classification performance. The classification performance of this method is compared with the Haralick features and the run-length features. A typical mammogram image processing system generally consists of mammogram image acquisition, pre-processing, segmentation, feature extraction, feature selection and classification. These processes are executed and the features analyzed. The performance of the proposed spectral shape feature is examined.
Feature (linguistics)
Cite
Citations (5)