Discriminative Learning and Recognition of Image Set Classes Using Canonical Correlations

Dimensionality reduction of image features using the canonical contextual correlation projection

Canonical correlation analysis using within-class coupling

Steady State Visual Evoked Potential (SSVEP) has been commonly adopted in Brain Computer Interface (BCI) applications. For wearable BCI applications, several aspects of SSVEP-based BCI systems, such as speed, subject variability, and accurate target detection, are under ongoing research investigations. Up to date, Canonical Correlation Analysis (CCA) has been considered the state-of-the-art feature extraction method for SSVEP-based BCI systems. Nevertheless, although CCA outperforms traditional SSVEP detection methods, such as Power Spectral Density Analysis (PSDA), achieving high accuracies when detecting target frequencies is still a challenging task due to user variation and physiological changes in the human body. In this paper, we investigate an SSVEP-based BCI application using wireless EEG recording and an Android tablet-based user interface. We propose a fusion of CCA and PSDA solutions at the score level by dividing their score space into multiple partitions, and extract and combine their complementary discriminative information to minimize the detection error in a linear fashion. We investigated transforming the fusion score space to lower dimensions with the purpose of alleviating redundancy. As such, we employed Principal Component Analysis (PCA), and Linear Discriminant Analysis (LDA). Our experimental results demonstrated that our proposed score fusion method is effective in reducing the effect of noise and non-stationary elements in EEG dynamics. Average detection accuracies improved from 63% for CCA to 72% for fusion+PCA and further improved to 98% for fusion+LDA.

The canonical correlation analysis (CCA) aims at measuring linear relationships between two sets of variables (views) that can be used for feature extraction in classification problems with multiview data. However, the correlated features extracted by the CCA may not be class discriminative, since CCA does not utilize the class labels in its traditional formulation. Although there is a method called discriminative CCA (DCCA) that aims to increase the discriminative ability of CCA inspired from the linear discriminant analysis (LDA), it has been shown that the extracted features with this method are identical to those by the LDA with respect to an orthogonal transformation. Therefore, DCCA is simply equivalent to applying single-view (regular) LDA to each one of the views separately. Besides, DCCA and the other similar DCCA approaches have generalization problems due to the sample covariance matrices used in their computation, which are sensitive to outliers and noisy samples. In this paper, we propose a method, called discriminative alternating regression (D-AR), to explore correlated and also discriminative features. D-AR utilizes two (alternating) multilayer perceptrons, each with a linear hidden layer, learning to predict both the class labels and the outputs of each other. We show that the features found by D-AR on training sets significantly accomplish higher classification accuracies on test sets of facial expression recognition, object recognition, and image retrieval experimental data sets.

Video event carries very rich and complex semantics, and video event analysis is intrinsically multi-view learning problem. In this paper, by revealing the relationship between canonical correlation analysis (CCA) and linear discriminant analysis (LDA), we propose a new convenient multi-view learning architecture, i.e., multi-view discriminative fusion on CCA (MvDF-CCA). Instead of pair-wise relation consideration among different views, MvDF-CCA separately aligns each view space to the target one comprised by labeled indicators, which is easy expanding to additional view data. MvDF-CCA leverages the discriminative ability in LDA and the strengths in CCA, and maps all view spaces to the same target labeled space, which can be concurrent execution on large scale video categorization. Competitive results are reported on the well-known UCF101 and Columbia Consumer Video (CCV) benchmarks.

An automated wood recognition system is designed to classify tropical wood species. The wood features are extracted based on two feature extractors: Basic Grey Level Aura Matrix (BGLAM) technique and statistical properties of pores distribution (SPPD) technique. Due to the nonlinearity of the tropical wood species separation boundaries, a pre classification stage is proposed which consists of Kmeans clustering and kernel discriminant analysis (KDA). Finally, Linear Discriminant Analysis (LDA) classifier and K-Nearest Neighbour (KNN) are implemented for comparison purposes. The study involves comparison of the system with and without pre classification using KNN classifier and LDA classifier. The results show that the inclusion of the pre classification stage has improved the accuracy of both the LDA and KNN classifiers by more than 12%.

Hotelling’s Canonical Correlation Analysis (CCA) works with two sets of related variables, also called views, and its goal is to find their linear projections with maximal mutual correlation. CCA is most suitable for unsupervised feature extraction when given two views but it has been also long known that in supervised learning when there is only a single view of data given, the supervision signal (class-labels) can be given to CCA as the second view and CCA simply reduces to Fisher’s Linear Discriminant Analysis (LDA). However, it is unclear how to use this equivalence for extracting features from multiview data in semisupervised setting (i.e. what modification to the CCA mechanism could incorporate the class-labels along with the two views of the data when labels of some samples are unknown). In this paper, a CCA-based method supplemented by the essence of LDA is proposed for semi-supervised feature extraction from multiview data.KeywordsSemisupervised LearningFeature ExtractionMultiview LearningLDACCA

Chapter 11 - Canonical analysis

Since standard canonical correlation analysis (CCA) works with vectorized representations of data, an limitation is that it may suffer small sample size problems. Moreover, two-dimensional CCA (2D-CCA) extracts unsupervised features and thus ignores the useful prior class information. This makes the extracted features by 2D-CCA hard to discriminate the data from different classes. To solve this issue, we simultaneously take the prior class information of intra-view and inter-view samples into account and propose a new 2D-CCA method referred to as supervised two-dimensional CCA (S2CCA), which can be used for multi-view feature extraction and classification. The method we propose is available to face recognition. To verify the effectiveness of the proposed method, we perform a number of experiments on the AR, AT&T, and CMU PIE face databases. The results show that the proposed method has better recognition accuracy than other existing multi-view feature extraction methods.

We propose a new approach to building appearance models of 3D objects which is based on Canonical Correlation Analysis (CCA). In appearance based modeling, instead of building an explicit object model (e.g., 3D geometrical object model), a low dimensional object representation is obtained from a set of images. In standard appearance models typically Principal Component Analysis (PCA) is used for feature extraction. In our experiments we compare the performance of standard appearance models based on PCA and models based on CCA for 3D pose estimation. Results indicate that, while getting by with a smaller number linear features, CCA-based models perform consistently better.

A computer vision system for automatic recognition and classification of five varieties of plant leaves under controlled laboratory imaging conditions, comprising: 1–Cydonia oblonga (quince), 2–Eucalyptus camaldulensis dehn (river red gum), 3–Malus pumila (apple), 4–Pistacia atlantica (mt. Atlas mastic tree) and 5–Prunus armeniaca (apricot), is proposed. 516 tree leaves images were taken and 285 features computed from each object including shape features, color features, texture features based on the gray level co-occurrence matrix, texture descriptors based on histogram and moment invariants. Seven discriminant features were selected and input for classification purposes using three classifiers: hybrid artificial neural network–ant bee colony (ANN–ABC), hybrid artificial neural network–biogeography based optimization (ANN–BBO) and Fisher linear discriminant analysis (LDA). Mean correct classification rates (CCR), resulted in 94.04%, 89.23%, and 93.99%, for hybrid ANN–ABC; hybrid ANN–BBO; and LDA classifiers, respectively. Best classifier mean area under curve (AUC), mean sensitivity, and mean specificity, were computed for the five tree varieties under study, resulting in: 1–Cydonia oblonga (quince) 0.991 (ANN–ABC), 95.89% (ANN–ABC), 95.91% (ANN–ABC); 2–Eucalyptus camaldulensis dehn (river red gum) 1.00 (LDA), 100% (LDA), 100% (LDA); 3–Malus pumila (apple) 0.996 (LDA), 96.63% (LDA), 94.99% (LDA); 4–Pistacia atlantica (mt. Atlas mastic tree) 0.979 (LDA), 91.71% (LDA), 82.57% (LDA); and 5–Prunus armeniaca (apricot) 0.994 (LDA), 88.67% (LDA), 94.65% (LDA), respectively.

Gem-Pro is a new tool for gene mining and functional profiling of bacteria. It initially identifies homologous genes using BLAST and then applies three filtering steps to select orthologous gene pairs. The first one uses BLAST score values to identify trivial paralogs. The second filter uses the shared identity percentages of found trivial paralogs as internal witnesses of non-orthology to set orthology cutoff values. The third filtering step uses conditional probabilities of orthology and non-orthology to define new cutoffs and generate supportive information of orthology assignations. Additionally, a subsidiary tool, called q-GeM, was also developed to mine traits of interest using logistic regression (LR) or linear discriminant analysis (LDA) classifiers. q-GeM is more efficient in the use of computing resources than Gem-Pro but needs an initial classified set of homologous genes in order to train LR and LDA classifiers. Hence, q-GeM could be used to analyze new set of strains with available genome sequences, without the need to rerun a complete Gem-Pro analysis. Finally, Gem-Pro and q-GeM perform a synteny analysis to evaluate the integrity and genomic arrangement of specific pathways of interest to infer their presence. The tools were applied to more than 2 million homologous pairs encoded by Bacillus strains generating statistical supported predictions of trait contents. The different patterns of encoded traits of interest were successfully used to perform a descriptive bacterial profiling.

Canonical correlation analysis (CCA) has recently attracted great attention and many experimental results have illustrated its effectiveness. In this paper, we study the relationship between CCA classifier and minimum squared error (MSE) classifier. It helps us look into the nature of CCA classifier. In traditional CCA method, the class-membership matrix is deliberately coded in full rank. Under this case, we will prove CCA is equivalent to MSE classifier. It is also shown that even the class-membership matrix is centered and thus not in full rank, CCA is equivalent to Fisher linear discriminant analysis (FDA). Some experiments are presented to verify the results.

Facial Expression recognition has become vital considering its numerous applications including Human Computer Interaction, security, medical field etc. In order to effectively implement these applications, the proposed method aims to increase the overall accuracy and robustness of the recognition system. Fusion of two feature extraction methods, namely Gabor and Local Directional Pattern (LDP) that are complementary in nature is carried out. Gabor Features focuses on the structural details whereas LDP targets the textural and subtler details in a robust manner. Fusion is carried out using Canonical Correlation Analysis (CCA) based fusion, as it effectively utilizes the correlation between the two features for fusion. For the efficient training of the classifiers, optimal feature vector is obtained by projecting the original feature vector on Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) subspace. To prove the robustness of the proposed method, it is tested on benchmark datasets under ideal as well as different conditions such as noisy environment, low resolution, small sample space, different facial components etc. The method has shown better performance than the state of the art methods.

A feature extraction method for Facial Expression Recognition Systems is proposed based on CCA using FMEDA and DPA. For proper classification of expression it has been trained with Recurrent neural network. The Cohn Kanade Extensive, ORL and Yale databases are used in this paper. The images have been preprocessed using image normalization and then contrast limited adaptive histogram equalization to remove the illumination variance and noises. After down-sampling, the dimensions with factor data is provided to Canonical Correlation Analysis that finds the linear combinations among two sets of variables for determining correlation with each other. DPA and FMEDA have been used to extract features from specially low frequency coefficients of the image as some of the low frequency coefficients have more discrimination power compared to others and by extracting those features a higher true recognition rate can be achieved. The results provided in this paper show the advantage of this method compared to other methods like Principal Component Analysis and Linear Discriminant Analysis which uses between and within class scatter matrices and try to maximize the discrimination in transformed domain. This method searches for best discrimination features in transformed domain. Dimensionally reduced data is provided to recurrent neural network for training purpose. Meanwhile, the proposed method is more robust and effective compared to other methods in this field.