Diagonal Features Research Articles

Bagging: An Ensemble Approach for Recognition of Handwritten Place Names in Gurumukhi Script

In this article, the authors present an effort to recognize handwritten Gurumukhi place names for use in postal automation. Five feature extraction techniques (zoning, horizontal peak extent, vertical peak extent, diagonal, and centroid) have been analyzed and optimized using Principal Component Analysis (PCA). Four classification methods ( k -Nearest Neighbor ( k -NN), decision tree, random forest, and Convolutional Neural Network (CNN)) have been utilized to classify the handwritten word images. To enhance the recognition results, the authors have employed Bootstrap Aggregation (Bagging) with a majority voting scheme. The authors used a public benchmark dataset of 40,000 handwritten place-name samples in the Punjabi language for their experimental work. The experiments were conducted using a 70:30 partitioning approach, where 70% of the data was utilized for training and the remaining 30% for testing. The system achieved a maximum recognition accuracy of 96.98% by utilizing a combination of zoning, vertical peak extent, and diagonal features, and a minimum Mean Squared Error (MSE) of 0.86% based on a combination of zoning and horizontal peak extent features with a majority voting scheme through ensemble (Bagging) methodology.

Critical state generators from perturbed flatbands

One-dimensional all-bands-flat lattices are networks with all bands being flat and highly degenerate. They can always be diagonalized by a finite sequence of local unitary transformations parameterized by a set of angles θi. In a previous work, we demonstrated that quasiperiodic perturbations of a specific one-dimensional all-bands-flat lattice give rise to a critical-to-insulator transition and fractality edges separating critical from localized states. In this study, we generalize these studies and results to the entire manifold of all-bands-flat models and study the effect of the quasiperiodic perturbation on the entire manifold. For weak perturbation, we derive an effective Hamiltonian and we identify the sets of manifold parameters for which the effective model maps to extended or off diagonal Harper models and hosts critical states. For all the other parameter values, the spectrum is localized. Upon increasing the perturbation strength, the extended Harper model evolves into a system with energy dependent critical-to-insulator transitions, which we dub fractality edges. Additionally, the fractality edges are perturbation-independent, i.e., remain constant as the perturbation strength varies. The case where the effective model maps onto the off diagonal Harper model features a tunable critical-to-insulator transition at a finite disorder strength.

Robust Real-Time AUV Self-Localization Based on Stereo Vision-Inertia

Autonomous underwater vehicles (AUVs) play an important role in deep-sea exploration, in which AUV self-localization is a key component. However, due to poor visibility caused by challenging marine environments, AUVs are often equipped with high-cost and heavy-weight acoustic sensors to accomplish localization tasks. We propose a robust real-time AUV self-localization method based on stereo camera and inertial sensor, which merges point and diagonal features, as well as inertial measurements to overcome the challenges of poor visibility. Our method also includes an underwater loop detection algorithm based on the combination of points and diagonal segments, which can extract effective binary descriptors in low-textured underwater scenarios. Furthermore, we develop an AUV self-localization system based on a real-time, portable, low-cost, and small volume sensor suite. Finally, we test the proposed method in a real underwater environment using our sensor suite, and the experimental results demonstrate the effectiveness of the proposed method under dramatically changing underwater scenarios.

Offline handwritten Gurumukhi word recognition using eXtreme Gradient Boosting methodology

Handwritten word recognition is undoubtedly a challenging task due to various writing styles of individuals. So, lots of efforts are put to recognize handwritten words using efficient classifiers based on extracted features that rely on the visual appearance of the handwritten text. Due to numerous real-time applications, handwritten word recognition is an important research area which is seeking a lot of attention from researchers for the last 10 years. In this article, the authors have proposed a holistic approach and eXtreme Gradient Boosting (XGBoost) technique to recognize offline handwritten Gurumukhi words. In this direction, four state-of-the-art features like zoning, diagonal, intersection & open-end points and peak extent features have been considered to extract discriminant features from the handwritten word digital images. The proposed approach is evaluated on a public benchmark dataset of Gurumukhi script that comprises 40,000 samples of handwritten words. Based on extracted features, the words are classified into one of the 100 classes based on XGBoost technique. Effectiveness of the system is assessed based on several evaluation parameters like CPU elapsed time, accuracy, precision, recall, F1-score and area under curve (AUC). XGBoost technique attained the best results of accuracy (91.66%), recall (91.66%), precision (91.39%), F1-score (91.14%) and AUC (95.66%) using zoning features based on 90% data as the training set and remaining 10% data as the testing set. The comparison of the proposed approach with the existing approaches has also been done which reveals the significance of the XGBoost technique comparatively.

Recognition of newspaper printed in Gurumukhi script

In this work, a system for recognition of newspaper printed in Gurumukhi script is presented. Four feature extraction techniques, namely, zoning features, diagonal features, parabola curve fitting based features, and power curve fitting based features are considered for extracting the statistical properties of the characters printed in the newspaper. Different combinations of these features are also applied to improve the recognition accuracy. For recognition, four classification techniques, namely, k-NN, linear-SVM, decision tree, and random forest are used. A database for the experiments is collected from three major Gurumukhi script newspapers which are Ajit, Jagbani and Punjabi Tribune. Using 5-fold cross validation and random forest classifier, a recognition accuracy of 96.19% with a combination of zoning features, diagonal features and parabola curve fitting based features has been reported. A recognition accuracy of 95.21% with a partitioning strategy of data set (70% data as training data and remaining 30% data as testing data) has been achieved.

A Study on Recognition of Pre-segmented Handwritten Multi-lingual Characters

Wide research has been carried out for recognition of handwritten text on various languages that include Assamese, Bangla, English, Gujarati, Hindi, Marathi, Punjabi, Tamil etc. Recognition of multi-lingual text documents is still a challenge in the pattern recognition field. In this paper, a study of various features and classifiers for recognition of pre-segmented multi-lingual characters consisting of English, Hindi and Punjabi has been presented. In feature extraction phase, various techniques, namely, zoning features, diagonal features, horizontal peak extent based features and intersection and open end point based features are considered. In classification phase, three different classifiers, namely, k-NN, Linear-SVM, and MLP are attempted. Different combinations of various features and classifiers have been also performed. For script identification, we have achieved maximum accuracy of 92.89% using a combination of Linear-SVM, k-NN, and MLP classifiers, and for character recognition of English, Hindi and Punjabi, we have achieved a recognition accuracy of 92.18%, 84.67% and 86.79%, respectively.

Radial distribution of stellar motions in Gaia DR2

Abstract By taking advantage of the superb measurements of position and velocity for an unprecedented large number of stars provided in Gaia DR2, we have generated the first maps of the rotation velocity, Vrot, and vertical velocity, Vz, distributions as a function of the Galactocentric radius, Rgal, across a radial range of 5 < Rgal < 12 kpc. In the R − Vrot map, we have identified many diagonal ridge features, which are compared with the location of the spiral arms and the expected outer Lindblad resonance of the Galactic bar. We have detected also radial wave-like oscillations of the peak of the vertical velocity distribution.

Ultrafast Two-Dimensional Infrared Spectroscopy of a Quasifree Rotor: J Scrambling and Perfectly Anticorrelated Cross Peaks.

Ultrafast two-dimensional infrared (2DIR) spectra of the N_{2}O ν_{3} mode in moderately dense SF_{6} gas exhibit complex line shapes with diagonal and antidiagonal features in contrast to condensed phase vibrational 2DIR spectroscopy. Observed spectra for this quasifree rotor system are well captured by a model that includes all 36 possible rovibrational pathways and treats P (ΔJ=-1) and R (ΔJ=+1) branch resonances as distinct Kubo line shape features. Transition frequency correlation decay is due to J scrambling within one to two gas collisions at each density. Studies of supercritical solvation and relaxation at high pressure and temperature are enabled by this methodology.

Offline Handwritten Numeral Recognition using Combination of Different Feature Extraction Techniques

A handwritten numeral recognition system using a combination of different feature extraction techniques has been presented in this paper. Initially, we have prepared a skeleton of the numeral, so that meaningful feature information about the numeral can be extracted. For feature extraction, a combination of four types of features, namely, centroid features, diagonal features, zoning features, and peak extent based features has been used. SVM classifier has been considered for classification purpose. For experimental results, 6000 samples of isolated handwritten numerals have been considered. The proposed system achieves maximum recognition accuracy of 96.3% using five-fold cross validation technique.

Robust Visual Tracking Based on Convolutional Features with Illumination and Occlusion Handing

Visual tracking is an important area in computer vision. How to deal with illumination and occlusion problems is a challenging issue. This paper presents a novel and efficient tracking algorithm to handle such problems. On one hand, a target’s initial appearance always has clear contour, which is light-invariant and robust to illumination change. On the other hand, features play an important role in tracking, among which convolutional features have shown favorable performance. Therefore, we adopt convolved contour features to represent the target appearance. Generally speaking, first-order derivative edge gradient operators are efficient in detecting contours by convolving them with images. Especially, the Prewitt operator is more sensitive to horizontal and vertical edges, while the Sobel operator is more sensitive to diagonal edges. Inherently, Prewitt and Sobel are complementary with each other. Technically speaking, this paper designs two groups of Prewitt and Sobel edge detectors to extract a set of complete convolutional features, which include horizontal, vertical and diagonal edges features. In the first frame, contour features are extracted from the target to construct the initial appearance model. After the analysis of experimental image with these contour features, it can be found that the bright parts often provide more useful information to describe target characteristics. Therefore, we propose a method to compare the similarity between candidate sample and our trained model only using bright pixels, which makes our tracker able to deal with partial occlusion problem. After getting the new target, in order to adapt appearance change, we propose a corresponding online strategy to incrementally update our model. Experiments show that convolutional features extracted by well-integrated Prewitt and Sobel edge detectors can be efficient enough to learn robust appearance model. Numerous experimental results on nine challenging sequences show that our proposed approach is very effective and robust in comparison with the state-of-the-art trackers.

Automatic video superimposed text detection based on Nonsubsampled Contourlet Transform

Compared with other video semantic clues, such as gestures, motions etc., video text generally provides highly useful and fairly precise semantic information, the analysis of which can to a great extent facilitate video and scene understanding. It can be observed that the video texts show stronger edges. The Nonsubsampled Contourlet Transform (NSCT) is a fully shift-invariant, multi-scale, and multi-direction expansion, which can preserve the edge/silhouette of the text characters well. Therefore, in this paper, a new approach has been proposed to detect video text based on NSCT. First of all, the 8 directional coefficients of NSCT are combined to build the directional edge map (DEM), which can keep the horizontal, vertical and diagonal edge features and suppress other directional edge features. Then various directional pixels of DEM are integrated into a whole binary image (BE). Based on the BE, text frame classification is carried out to determine whether the video frames contain the text lines. Finally, text detection based on the BE is performed on consecutive frames to discriminate the video text from non-text regions. Experimental evaluations based on our collected TV videos data set demonstrate that our method significantly outperforms the other 3 video text detection algorithms in both detection speed and accuracy, especially when there are challenges such as video text with various sizes, languages, colors, fonts, short or long text lines.

Measurement of Ultrafast Excitonic Dynamics of Few-Layer MoS2 Using State-Selective Coherent Multidimensional Spectroscopy.

We report the first coherent multidimensional spectroscopy study of a MoS2 film. A four-layer sample of MoS2 was synthesized on a silica substrate by a simplified sulfidation reaction and characterized by absorption and Raman spectroscopy, atomic force microscopy, and transmission electron microscopy. State-selective coherent multidimensional spectroscopy (CMDS) on the as-prepared MoS2 film resolved the dynamics of a series of diagonal and cross-peak features involving the spin-orbit split A and B excitonic states and continuum states. The spectra are characterized by striped features that are similar to those observed in CMDS studies of quantum wells where the continuum states contribute strongly to the initial excitation of both the diagonal and cross-peak features, while the A and B excitonic states contributed strongly to the final output signal. The strong contribution from the continuum states to the initial excitation shows that the continuum states are coupled to the A and B excitonic states and that fast intraband relaxation is occurring on a sub-70 fs time scale. A comparison of the CMDS excitation signal and the absorption spectrum shows that the relative importance of the continuum states is determined primarily by their absorption strength. Diagonal and cross-peak features decay with a 680 fs time constant characteristic of exciton recombination and/or trapping. The short time dynamics are complicated by coherent and partially coherent pathways that become important when the excitation pulses are temporally overlapped. In this region, the coherent dynamics create diagonal features involving both the excitonic states and continuum states, while the partially coherent pathways contribute to cross-peak features.

Multidimensional coherent spectroscopy of a semiconductor microcavity

Rephasing and non-rephasing two-dimensional coherent spectra map the anti-crossing associated with normal-mode splitting in a semiconductor microcavity. For a 12-meV detuning range near zero detuning, it is observed that there are two diagonal features related to the intra-action of exciton-polariton branches and two off-diagonal features related to coherent interaction between the polaritons. At negative detuning, the lineshape properties of the diagonal intra-action features are distinguishable and can be associated with cavity-like and exciton-like modes. A biexcitonic companion feature is observed, shifted from the exciton feature by the biexciton binding energy. Closer to zero detuning, all features are enhanced and the diagonal intra-action features become nearly equal in amplitude and linewidth. At positive detuning the exciton- and cavity-like characteristics return to the diagonal intra-action features. Off-diagonal interaction features exhibit asymmetry in their amplitudes throughout the detuning range. The amplitudes are strongly modulated (and invert) at small positive detuning, as the lower polariton branch crosses the bound biexciton energy determined from negative detuning spectra.

Dual Tree Complex Wavelet Transform for Image Security using Arnold Method

The increasing globalization led to the transmission of vast amount of digital documents like texts, images, videos or audios over the internet from one point to another. However, some of these documents might be highly confidential and its transmission over the internet must be protected from unauthorized access. In this paper, we have proposed a novel hybrid Arnold transform scheme based on dual tree complex wavelet transform with block shuffling internally as well as externally. In this scheme, we have provided double layer of security by utilizing the multi-resolution property of wavelet using Arnold transform andblock shuffling.In contrast to the discrete wavelet transform (DWT), the design of Dual Tree Complex Wavelet Transform poses good directional properties for diagonal features and is rugged to shift Invariance. Our scheme provides high security as even after the extraction of first layer, without knowing the extraction algorithm, original image cannot be recovered in its entirety. The proposed scheme is tested on various test images and the obtained results show the effectiveness of the proposed scheme.

A Novel Hierarchical Technique for Offline Handwritten Gurmukhi Character Recognition

The increasing need of a handwritten character recognition system in the Indian offices such as banks, post offices and so forth, has made it an imperative field of research. In present paper, Authors have presented a novel hierarchical technique for isolated offline handwritten Gurmukhi character recognition. A robust feature set of 105 feature elements is proposed under this work for recognition of offline handwritten Gurmukhi characters using four types of topological features, namely, horizontally peak extent features, vertically peak extent features, diagonal features, and centroid features. For classification Support Vector Machines (SVMs) classifier has been used in this work. SVMs classifier has been considered with four different kernels, namely, linear kernel, polynomial kernel, RBF kernel and sigmoid kernel. For training and testing of a classifier, we have used 3,500 samples of isolated offline handwritten Gurmukhi characters written by one hundred different writers. Maximum recognition accuracy of 91.80 % have been achieved with proposed technique, while using PCA feature set and SVM with a linear kernel classifier.

Control vectors for splines

Traditionally, modelling using spline curves and surfaces is facilitated by control points. We propose to enhance the modelling process by the use of control vectors. This improves upon existing spline representations by providing such facilities as modelling with local (semi-sharp) creases, vanishing and diagonal features, and hierarchical editing. While our prime interest is in surfaces, most of the ideas are more simply described in the curve context. We demonstrate the advantages provided by control vectors on several curve and surface examples and explore avenues for future research on control vectors in the contexts of geometric modelling and finite element analysis based on splines, and B-splines and subdivision in particular.

A new perspective on the solution of uncertainty quantification and reliability analysis of large-scale problems

This work revisits the computational performance of non-intrusive Monte Carlo versus intrusive Galerkin methods of large-scale stochastic systems in the framework of high performance computing environments. The purpose of this work is to perform an assessment of the range of the relative superiority of these approaches with regard to a variety of stochastic parameters. In both approaches, the solution of the resulting algebraic equations is performed with a combination of primal and dual domain decomposition methods implementing specifically tailored preconditioners. The solution of repeated simulations of the Monte Carlo method is accelerated with an A-orthogonalization procedure aiming at reducing the iterations of subsequent simulations, while the solution of the augmented equations of the stochastic Galerkin method is enhanced with preconditioners which combine the block diagonal features of the resulting matrices as well as the sparsity pattern of the off block-diagonal terms. Numerical results are presented, demonstrating the efficiency of the proposed implementations on a large-scale 3D problem with different stochastic characteristics and useful conclusions are derived regarding the ranges of stochastic parameters in which non-intrusive solvers have a superior performance compared to intrusive ones and vice versa.

Recognition of Handwritten Numerals of Manipuri Script

this paper a support vector machine based handwritten numerals recognition system of Manipuri Script (Meetei Mayek) is investigated. We have used various feature extraction technique such as background directional distribution (BDD), zone based diagonal, projection histograms and Histogram Oriented Gradient features. In Background Directional Distribution (BDD) features background distribution of neighboring background pixels to foreground pixels in 8-different directions is considered forming a total of 128 features. For the computation of diagonal features, the whole image is divided into 64 zones of equal dimension each of size 4×4 pixels then features are extracted from the pixels of each zone by moving along the diagonal, thus consisting of 64 features in total. Projection Histograms count the number of foreground pixels in different directions such as vertical, horizontal, horizontal, left diagonal and right diagonal creating a total of 190 features. The HOG based feature is computed over the validation data set, was achieved by means of 9 rectangular cells and 9 bin histogram per cell Different combinations of these features are used for forming various feature vectors. These feature vectors are classified by using SVM classifier as 5-fold cross validation with RBF (radial basis function) kernel. Experimental results show that the proposed system performs well with the combined features and is robust to the writing variations that exist between persons and for a single person at different instances, thus being promising for user independent recognition of Meetei Mayek numeral.

MDP Feature Extraction Technique for Offline Handwritten Gurmukhi Character Recognition

Character recognition is intricate work because of the various writing styles of different individuals. Most of the published work on handwritten character recognition problems deals with statistical features, and a few works deal with structural features, in general, and Gurmukhi script, in particular. In the present work, we propose a methodology for offline handwritten Gurmukhi character recognition by using a modified division points (MDP) feature extraction technique. We also compare this technique with other recently used feature extraction techniques, namely zoning features, diagonal features, directional features, intersection and open end points features, and transition features. To select a representative set of features is the most significant task for a character recognition system. After feature extraction, the classification stage makes use of the features extracted in the previous stage to recognize the character. In this work, we used linear-support vector machines (linear-SVM), k-nearest neighbor (k-NN), and multilayer perceptron (MLP) classifiers for recognition. For experimental analysis, we used 10,500 samples of the isolated, offline, handwritten, basic 35 akhars of Gurmukhi script. The proposed system achieved a maximum recognition accuracy of 84.57%, 85.85% and 89.20% with linear-SVM, MLP and k-NN classifiers, respectively, with a five-fold cross validation technique.

Action recognition from a different view

In this paper, we propose a novel approach to recognise human activities from a different view. Although appearance-based recognition methods have been shown to be unsuitable for action recognition for varying views, there must be some regularity among the same action sequences of different views. Self-similarity matrices appear to be relative stable across views. However, the ability to effectively realise this stability is a problem. In this paper, we extract the shape-flow descriptor as the low-level feature and then choose the same number of key frames from the action sequences. Self-similarity matrices are obtained by computing the similarity between any pair of the key frames. The diagonal features of the similarity matrices are extracted as the highlevel feature representation of the action sequence and Support Vector Machines (SVM) is employed for classification. We test our approach on the IXMAS multi-view data set. The proposed approach is simple but effective when compared with other algorithms.