In this paper, we propose a novel image indexing and retrieval algorithm using local tetra patterns (LTrPs) for content-based image retrieval (CBIR). The standard local binary pattern (LBP) and local ternary pattern (LTP) encode the relationship between the referenced pixel and its surrounding neighbors by computing gray-level difference. The proposed method encodes the relationship between the referenced pixel and its neighbors, based on the directions that are calculated using the first-order derivatives in vertical and horizontal directions. In addition, we propose a generic strategy to compute nth-order LTrP using (n - 1)th-order horizontal and vertical derivatives for efficient CBIR and analyze the effectiveness of our proposed algorithm by combining it with the Gabor transform. The performance of the proposed method is compared with the LBP, the local derivative patterns, and the LTP based on the results obtained using benchmark image databases viz., Corel 1000 database (DB1), Brodatz texture database (DB2), and MIT VisTex database (DB3). Performance analysis shows that the proposed method improves the retrieval result from 70.34%/44.9% to 75.9%/48.7% in terms of average precision/average recall on database DB1, and from 79.97% to 85.30% and 82.23% to 90.02% in terms of average retrieval rate on databases DB2 and DB3, respectively, as compared with the standard LBP.

Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval

Texture features for image classification and retrieval.

Medical image retrieval using deep convolutional neural network

The time of operation of overcurrent relays (OCRs) can be reduced, and at the same time, the coordination can be maintained, by selecting the optimum values of time multiplier setting (TMS) and plug setting (PS) of OCRs This paper presents hybrid genetic algorithm (GA) - nonlinear programming (NLP) approach for determination of optimum values of TMS and PS of OCRs GA has a drawback of, sometimes, converging to the values which may not be optimum, and NLP methods have a drawback of converging to local optimum values, if the initial choice is nearer to local optimum This paper proposes a hybrid method to overcome the drawback of GA and NLP method, and determine the optimum settings of OCRs The main contributions of this paper are - 1) systematic method for formulation of problem of determining optimum values of TMS and PS of OCRs in power distribution network as a constrained nonlinear optimization problem, 2) determining initial values of TMS and PS using GA technique and finding final (global optimum) values using NLP method, thus making use of the advantages of both methods (and at the same time overcoming the drawbacks of the methods)

Optimum Coordination of Directional Overcurrent Relays Using the Hybrid GA-NLP Approach

In recent years the Probabilistic Neural Network (PPN) has been used in a large number of applications due to its simplicity and efficiency. PNN assigns the test data to the class with maximum likelihood compared with other classes. Likelihood of the test data to each training data is computed in the pattern layer through a kernel density estimation using a simple Bayesian rule. The kernel is usually a standard probability distribution function such as a Gaussian function. A spread parameter is used as a global parameter which determines the width of the kernel. The Bayesian rule in the pattern layer estimates the conditional probability of each class given an input vector without considering any probable local densities or heterogeneity in the training data. In this paper, an enhanced and generalized PNN (EPNN) is presented using local decision circles (LDCs) to overcome the aforementioned shortcoming and improve its robustness to noise in the data. Local decision circles enable EPNN to incorporate local information and non-homogeneity existing in the training population. The circle has a radius which limits the contribution of the local decision. In the conventional PNN the spread parameter can be optimized for maximum classification accuracy. In the proposed EPNN two parameters, the spread parameter and the radius of local decision circles, are optimized to maximize the performance of the model. Accuracy and robustness of EPNN are compared with PNN using three different benchmark classification problems, iris data, diabetic data, and breast cancer data, and five different ratios of training data to testing data: 90:10, 80:20, 70:30, 60:40, and 50:50. EPNN provided the most accurate results consistently for all ratios. Robustness of PNN and EPNN is investigated using different values of signal to noise ratio (SNR). Accuracy of EPNN is consistently higher than accuracy of PNN at different levels of SNR and for all ratios of training data to testing data.

Enhanced probabilistic neural network with local decision circles: A robust classifier

Local maximum edge binary patterns: A new descriptor for image retrieval and object tracking

Considerations of weight factors and far-end faults in the directional overcurrent relay coordination problem formulation do not affect the optimal solution. This paper investigates this viewpoint and verifies that indeed by such an approach the optimality is not lost. But, this study reveals that in doing so, the coordination quality is sacrificed to some extent. It is also observed that if all remaining valid constraints (after relaxing few constraints based on the back-up coordination philosophy and strength of fault level generated) are considered and if the objective function is changed to running sum of all violating constraints, all valid considered constraints are satisfied. This study is done by simultaneously optimizing all settings in nonlinear environment by Sequential Quadratic Programming method using Matlab Toolbox. The results of the analysis on a sample 6-bus and IEEE 30-bus systems are presented in this paper.

A new nonlinear directional overcurrent relay coordination technique, and banes and boons of near-end faults based approach

In this paper, a new algorithm using directional local extrema patterns meant for content-based image retrieval application is proposed. The standard local binary pattern (LBP) encodes the relationship between reference pixel and its surrounding neighbors by comparing gray-level values. The proposed method differs from the existing LBP in a manner that it extracts the directional edge information based on local extrema in 0
 $$^{\circ }$$
 , 45
 $$^{\circ }$$
 , 90
 $$^{\circ }$$
 , and 135
 $$^{\circ }$$
 directions in an image. Performance is compared with LBP, block-based LBP (BLK_LBP), center-symmetric local binary pattern (CS-LBP), local edge patterns for segmentation (LEPSEG), local edge patterns for image retrieval (LEPINV), and other existing transform domain methods by conducting four experiments on benchmark databases viz. Corel (DB1) and Brodatz (DB2) databases. The results after being investigated show a significant improvement in terms of their evaluation measures as compared with other existing methods on respective databases.

/pdf/directional-local-extrema-patterns-a-new-descriptor-for-4ru4yahopn.pdf

Directional local extrema patterns: a new descriptor for content based image retrieval

In this paper, the optimal probabilistic neural network (PNN) is proposed as the core classifier to discriminate between the magnetizing inrush and the internal fault of a power transformer. The particle swarm optimization is used to obtain an optimal smoothing factor of PNN which is a crucial parameter for PNN. An algorithm has been developed around the theme of the conventional differential protection of the transformer. It makes use of the ratio of voltage-to-frequency and amplitude of differential current for the determination of operating condition of the transformer. The performance of the proposed heteroscedastic-type PNN is investigated with the conventional homoscedastic-type PNN, feedforward back propagation (FFBP) neural network, and the conventional harmonic restraint method. To evaluate the developed algorithm, relaying signals for various operating condition of the transformer, including internal and external faults, are obtained by modeling the transformer in PSCAD/EMTDC. The protection algorithm is implemented by using MATLAB.

Rudra Prakash Maheshwari

Papers

Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval

Local maximum edge binary patterns: A new descriptor for image retrieval and object tracking

A new nonlinear directional overcurrent relay coordination technique, and banes and boons of near-end faults based approach

Directional local extrema patterns: a new descriptor for content based image retrieval

Power Transformer Differential Protection Based On Optimal Probabilistic Neural Network