Face recognition using direct, weighted linear discriminant analysis and modular subspaces

Face recognition using direct, weighted linear discriminant analysis and modular subspaces

Linear Discriminant Analysis (LDA) is a popular statistical method for both feature extraction and dimensionality reduction in face recognition. The major drawback of LDA is the so-called small sample size (3S) problem. This problem always occurs when the total number of training samples is smaller than the dimension of feature space. Under this situation, the within-class scatter matrix Sw becomes singular and LDA approach cannot be implemented directly. To overcome the 3S problem, this paper proposes a novel wavelet-face based subspace LDA algorithm. Wavelet-face feature extraction and dimensionality reduction are based on two-level D4-filter wavelet transform and discarding the null space of total class scatter matrix St. It is shown that our obtained projection matrix satisfies the uncorrelated constraint conditions. Hence in the sense of statistical uncorrelation, this projection matrix is optimal. The proposed method for face recognition has been evaluated with two public available databases, namely ORL and FERET databases. Comparing with existing LDA-based methods to solve the 3S problem, our method gives the best performance.

Academic Information System (Sistem Informasi Akademik aka SIAKAD) Online of Universitas Prima Indonesia (UNPRI) is one of the applications used to facilitate the administration process of lectures which includes the filling process of study plan cards (Kartu Rencana Studi aka KRS), study result cards (Kartu Hasil Studi aka KHS), class schedules, submission of research titles, seminars, and other processes. SIAKAD UNPRI can be accessed by students, lecturers, and academics where every user has a password that has been encrypted to maintain the security of information from people who are not responsible, password security using the encryption method needs to be changed regularly, but there are still many students, lecturers and academic community who are reluctant to change passwords. To improve the security verification stage for SIAKAD users, we propose a face recognition feature approach. Face recognition is a feature that allows the identification of someone from a digital image or video. The way the facial recognition method works is by comparing face data from the camera or images with images that were previously stored in a database. In this study, the Kohonen SOM method is proposed for face identification based on the feature extraction approach of discrete cosine transform (DCT), linear discriminant analysis (LDA) and principal component analysis (PCA) to improve the security of UNPRI SIAKAD users. The analytical framework is done by requiring students to do face taking, where each student will save 5 (five) faces extracted with facial features using the DCT, LDA and PCA model approach, feature extraction results are used as input to the Kohonen SOM network for training and testing facial recognition, then analysis of the effect of DCT, LDA and PCA feature extraction on the Kohonen network on facial recognition accuracy.

Uncorrelated trace ratio linear discriminant analysis for undersampled problems

Regularized discriminant analysis for the small sample size problem in face recognition

This is the author’s version of a work that was submitted/accepted for pub-lication in the following source:

Face recognition in artificial intelligence is a frequent problem. This application was extensively used in our daily life. Several smartphones were opening phones with facial identification to safeguard private details and used on Facebook to identify instantly when users of Facebook appear in pictures. Several approaches for face recognition have already been suggested until now, but it remains very difficult in real-world situations. A primary technique to differentiate people depends on various conditions, for example, partial facial occlusion, illumination, and posture variety. This paper aims at designing a face recognition approach utilizing machine learning algorithm and principal component analysis (PCA). It is experimented using linear discriminant analysis, multilayer perceptron, Naive Bayes, and support vector machine. Moreover, it has achieved recognition accuracy of 97% & 100% by using PCA and linear discriminant analysis.

Sequence describes the primary structure of a protein, which contains important structural, characteristic, and genetic information and thereby motivates many sequence-based computational approaches to infer protein function. Among them, feature-base approaches attract increased attention because they make prediction from a set of transformed and more biologically meaningful sequence features. However, original features extracted from sequence are usually of high dimensionality and often compromised by irrelevant patterns, therefore dimension reduction is necessary prior to classification for efficient and effective protein function prediction. A protein usually performs several different functions within an organism, which makes protein function prediction a multi-label classification problem. In machine learning, multi-label classification deals with problems where each object may belong to more than one class. As a well-known feature reduction method, linear discriminant analysis (LDA) has been successfully applied in many practical applications. It, however, by nature is designed for single-label classification, in which each object can belong to exactly one class. Because directly applying LDA in multi-label classification causes ambiguity when computing scatters matrices, we apply a new Multi-label Linear Discriminant Analysis (MLDA) approach to address this problem and meanwhile preserve powerful classification capability inherited from classical LDA. We further extend MLDA by l1-normalization to overcome the problem of over-counting data points with multiple labels. In addition, we incorporate biological network data using Laplacian embedding into our method, and assess the reliability of predicted putative functions. Extensive empirical evaluations demonstrate promising results of our methods.

Improved PCA + LDA Applies to Gastric Cancer Image Classification Process

One-dimensional vs. two-dimensional based features: Plant identification approach

The concentrations and spreading of eight synthetic and two natural progestins (PGs) were investigated in surface waters from ten sites at the Douro River Estuary. Samples were filtrated and subjected to solid-phase extraction (SPE) to isolate and concentrate the target PGs. The extracts were cleaned by silica cartridges and analyzed by LC-MS/MS. The finding of biologically relevant amounts of gonanes (22.3 ± 2.7 ng/L), progesterone derivatives (12.2 ± 0.5 ng/L), drospirenone (4.1 ± 0.8 ng/L), and natural PGs (9.4 ± 0.9 ng/L) support the possibility of these compounds acting as endocrine disruptors. Despite the absence of significant differences amongst sampling sites and seasons, the principal component analysis (PCA) and the linear discriminant analysis (LDA) approaches reveal that spring and summer have different patterns of PG distribution compared to autumn and winter. The assessment of risk coefficients (RQs) and the potential concentrations of synthetic progestins in fish blood sustains that all tested compounds pose a significant risk to local biota (RQs > 1). Additionally, three progestins-norethindrone, norethindrone acetate, and medroxyprogesterone acetate-should reach human-equivalent therapeutic levels in fish plasma. Overall, the current data show PGs' presence and potential impacts in one of the most important estuaries of the Iberian Peninsula.

Recently, virtual reality (VR) has received significant attention among researchers to accomplish realistic interaction between humans and computers. Among the different application areas of VR, multimedia human computer interaction requires accurately collect and identify the motions of human body in real time. For enabling highly realistic and efficient communication among humans and computers, design of human motion recognition system becomes necessary to determine diverse complex and distinct human actions. Therefore, this study designs a new optimal bidirectional long short term memory (BiLSTM) with fully convolution network (FCN), called OBiLSTM-FCN model for human motion recognition in VR environment. The proposed OBiLSTM-FCN model comprises different processes namely feature extraction, classification, and hyperparameter optimization. Primarily, kernel based linear discriminant analysis (LDA) approach is employed as a feature extraction technique. In addition, the BiLSTM-FCN technique is applied as a recognition model to determine human motions. Finally, the Adam optimizer is applied to optimally tune the hyperparameters involved in the BiLSTM-FCN model. The performance validation of the OBiLSTM-FCN model take place and the resultant values portrayed the improved performance over the other compared methods.KeywordsVirtual realityDeep learningHuman motion recognitionHyperparameter tuningAdam optimizer

This paper proposes a view-invariant gait recognition algorithm, which builds a unique view invariant model taking advantage of the dimensionality reduction provided by the Direct Linear Discriminant Analysis (DLDA). Proposed scheme is able to reduce the under-sampling problem (USP) that appears usually when the number of training samples is much smaller than the dimension of the feature space. Proposed approach uses the Gait Energy Images (GEIs) and DLDA to create a view invariant model that is able to determine with high accuracy the identity of the person under analysis independently of incoming angles. Evaluation results show that the proposed scheme provides a recognition performance quite independent of the view angles and higher accuracy compared with other previously proposed gait recognition methods, in terms of computational complexity and recognition accuracy.

Linear discriminant analysis (LDA) is a popular feature extraction technique in statistical pattern recognition. However, it often suffers from the small sample size problem when dealing with the high dimensional image data. Moreover, while LDA is guaranteed to find the best directions when each class has a Gaussian density with a common covariance matrix, it can fail if the class densities are more general. In this paper, a new feature extraction method, nonparametric maximum margin criterion (NMMC), is proposed. NMMC finds the important discriminant directions without assuming the class densities belong to any particular parametric family, and it does not depend on the nonsingularity of the within-class scatter matrix. Our experimental results on the ATT and FERET face databases demonstrate that NMMC outperforms the existing variant LDA methods and the other state-of-art face recognition approaches.

The fast development of modern technologies has led to the frequent usage of face detection and recognition approaches in various fields due to their user-friendly nature. Generally, face recognition approaches identify individuals by their facial features. Recently, numerous face recognition methods were designed by leveraging the significance of deep learning approaches. These approaches are divided into numerous tasks, and implementing these tasks is time consuming as they require real-time images for processing. However, facial features vary across time because of ageing, haircuts, etc. Furthermore, images with poor resolution may also influence the recognition ability of the framework. Therefore, an advanced face recognition framework is designed in this work. The key intent of this designed model is to tackle the obstacles of the classical models and detect individuals in diverse environmental circumstances with better accuracy. Here, the relevant images are collected from a standard data source, and the quality of the image is enhanced using a Retinex-based image enhancement technique. Next, the Generative Adversarial Network (GAN) is employed to synthesize real images that mitigate the effects of pose discrepancies and occlusion, providing clearer features for recognition. Next, synthesized images are fed to Residual network 50 (ResNet50) for face recognition. Finally, the precise face segmentation is done with the support of Gather-Excite Networks of ResUNet (GEN-ResUNet). This integrated approach enhances the accuracy of face recognition, especially in challenging environments with lighting variations and occlusions. The effectiveness of the model is proven by conducting extensive experimentation.