Biprodip Pal

Face recognition using Principle Component Analysis and Linear Discriminant Analysis

Face recognition is the process of identification of a person by their facial images. This technique makes it possible to use the facial image of a person to authenticate him into a secure system. Face is the main part of human being to be distinguished from one another. Face recognition system mainly takes an image as an input and compares this image with a number of images stored in database to identify whether the input image is in that database or not. There are many techniques used for face recognition. In this paper, we have discussed two techniques: Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). Both of these techniques are linear. PCA applies linear projection to the original image space to achieve dimensionality reduction. LDA applies linear projection from the image space to a low dimensional space by maximizing the between class scatter and minimizing the within class scatter. These methods will be discussed here based on accuracy and percentage of correct recognition.

Human face recognition using PCA based Genetic Algorithm

This paper illustrates an approach to recognize a face using Principal Components Analysis based Genetic Algorithm in the area of computer vision. Facial image analysis plays an important role for human computer interaction, although automatic face recognition is still a big challenge for many applications. The PCA is applied to extract features from images with the help of covariance analysis to generate Eigen components of the images and reduce the dimensionality. Genetic Algorithm is an optimization technique which gives the optimal solutions from the generated large search space. For our experiment we used Japanese Female Facial Expression (JAFFE) face database with an encouraging result approximately 96%.

An empirical analysis of attribute skewness over class imbalance on Probabilistic Neural Network and Naïve Bayes classifier

Many real world data are subject to skewness or imbalance. Often class distribution is imbalanced, while several attribute or feature skewness is also frequent. Skewness affects the classification of the dataset samples. While class skewness biases the classification towards majority classes, skewed features may also bias the classification as they are significant for few classes. The purpose of this paper is to find out the impact of skewed feature variation in the training dataset for the Naïve Bayesian Classifier(NBC) and Probabilistic Neural Network(PNN) while classifying imbalanced data. The experiment was carried out on six KEEL dataset which are skewed in terms of class distribution having different imbalance ratio. This work looked for skewed features in those dataset and analysed the classification performance with and without the skewed features. The result illustrates that NBC is better in the mentioned circumstance compared to PNN.

Gaussian mixture based semi supervised boosting for imbalanced data classification

Semi supervised approaches are practical in problem domain where pattern clustering is supposed to provide good classification. Gaussian Mixture Model (GMM) can approximate arbitrary probability distribution, thus is considered as a dominant tool for classification in such domains. This paper appraises the functioning for GMM as it is applied to imbalanced datasets which consists of uneven distribution of samples from all the classes. Later, an ensemble approach is presented to boost the GMMs in a semi supervised manner via Adaptive Boosting technique. Experiment on benchmark imbalanced datasets with different imbalance ratio has been carried out. Empirical result demonstrates the efficacy of the proposed Boosted GMM classifier compared to baseline approaches like K-means and GMM.

A Compare between Shor's quantum factoring algorithm and General Number Field Sieve

Factoring large integers has been one of the most difficult problems in the history of mathematics and computer science. There was no efficient solution of this problem until Shors algorithm emerged. Shors algorithm is a polynomial time factoring algorithm which works on a quantum computer. Quantum computing is a new paradigm of computing that uses quantum mechanical phenomena in solving problems. The computers we are using right now are called classical computer. The most efficient classical factoring algorithm is General Number Field Sieve (GNFS). GNFS also cannot factor integers in polynomial time. In this paper, we compared these two algorithms in factoring integer in a standalone system.

A Gaussian mixture based boosted classification scheme for imbalanced and oversampled data

Dataset with imbalanced class distribution used to abate classification performance for most of the standard classifier learning algorithms. Moreover, some application area consists of scarcity of labeled training data where clustering is most prominent way to support classification process. Gaussian Mixture Model (GMM) being able to approximate arbitrary probability distribution, is a dominant tool for classification in such cases by means of clustering. An ensemble approach is presented in this paper considering GMM as a weak learner to boost the GMMs in a semi supervised manner via Adaptive Boosting technique. This paper, firstly investigates how much K-means and GMM suffers from uneven class distribution in data. Later experiment on benchmark imbalanced datasets with different imbalance ratio and over sampled datasets using Synthetic Minority Over-sampling Technique (SMOTE) has been carried out for proposed approach. For each case cluster forest has been used as an attribute selection technique. Efficacy of the proposed Boosted GMM approach compared to standard clustering approaches like K means and GMM is exhibited from empirical analysis.

A deep domain adaption approach for object recognition using Multiple Model Consistency analysis

Domain adaption tends to transfer knowledge across domains following dissimilar distribution and where target domain has inadequate labelled samples. When knowledge is transferred from abundantly irrelevant sources negative transfer may occur resulting in poor classification of test samples. Deep learning research illustrates the semantic clustering as well as transferability of deep convolutional features for numerous tasks including domain adaption. Traditional clustering based domain adaption approaches are practical to handle negative transfer scenario. This paper presents a scheme that uses graph based consistency analysis of one supervised and another unsupervised model to effectively transfer knowledge using deep features. This approach uses local neighbourhood analysis to classify hard samples that are identified using consistency analysis of models. This method yields encouraging experimental results on benchmark domain adaption dataset compared to a single deep feature based supervised support vector machine classifier, demonstrating effective use of target domain data.

Neighbourhood consistency based deep domain adaption analysis for multi category object detection

Pattern classification in domains that follow dissimilar distribution and where target domain has insufficient labelled samples, requires transfer of knowledge across domains through a process called domain adaption. Deep learning research demonstrates the transferability of deep convolutional features that are activations of intermediate layers of convolutional neural networks for domain adaption. Traditional clustering based domain adaption approaches are practical to handle knowledge transfer scenario. This paper presents a scheme that uses local neighborhoods based consistency analysis of one supervised and another unsupervised model to effectively transfer knowledge using deep features. Contrasting conventional models this approach uses only two models to classify patterns except hard ones. Neighbourhood consistency analysis identifies the hard samples, and is classified using a third model. Experimental analysis has been carried out focusing change on category variation of different samples for train and test cases. The proposed approach yields encouraging experimental result on benchmark domain adaption dataset compared to a deep feature based single support vector machine classifier in terms of state of the art metrics demonstrating effective generalization of source domain information.

A graph rewriting approach to replace asynchronous RAMs in circuits with cycles for FPGAs

Circuit design that minimizes the number of clock cycles is easy if we use asynchronous read operations. However, most of FPGAs support synchronous read operations, but do not support asynchronous read operations. It is one of the main difficulties for users to implement parallel and hardware algorithms in FPGAs. The main contribution of this paper is to provide one of the potent approaches to resolve this problem. We assume that a circuit which includes cycles using asynchronous RAMs designed by a non-expert or quickly designed by an expert is given. Our goal is to convert this circuit with asynchronous RAMs into an equivalent synchronous ones. The resulting circuit with synchronous RAMs can be embedded into the FPGAs.