Maitreyee Dutta

Hand Written Character Recognition Using Twelve Directional Feature Input and Neural Network

this paper, we have applied a new feature extraction technique to calculate only twelve directional feature inputs depending upon the gradients. Features extracted from handwritten characters are directions of pixels with respect to their neighboring pixels. These inputs are given to a back propagation neural network with one hidden layer and one output layer. An analysis has been also carried out to compare the recognition accuracy, training time and classification time of newly developed feature extraction technique with some of the existing techniques. Experimental result shows that the new approach provides better results as compared to other techniques in terms of recognition accuracy, training time and classification time. The work carried out in this paper is able to recognize all type of handwritten characters even special characters in any language.

Image Segmentation for Uneven Lighting Images using Adaptive Thresholding and Dynamic Window based on Incremental Window Growing Approach

paper proposes a novel method to address the problem of segmentation, for uneven lighting images. Though there are many segmentation methods, but most of them are based on either the fixed window method or window merging technique. Limitation of such methods is that, initial size of window is selected manually and segmentation accuracy greatly depends upon the proper choice of initial window size. In the proposed work, problem of uneven illumination condition has been addressed using dynamic window growing approach. The proposed algorithm is based on an incremental window growing approach using entropy based selection criteria. The window thus fixed by the selection criteria are considered as sub-images and each sub-images has been segmented by using minimum standard deviation difference based thresholding to improve the segmentation result. The result of the experiments show that the proposed method can deal with higher number of segmentation problem and improve the overall performance for uneven lighting image segmentation. General Terms Thresholding, window size, image binarization, entropy, standard deviation.

A review of task scheduling based on meta-heuristics approach in cloud computing

Heterogeneous distributed computing systems are the emerging for executing scientific and computationally intensive applications. Cloud computing in this context describes a paradigm to deliver the resource-like computing and storage on-demand basis using pay-per-use model. These resources are managed by data centers and dynamically provisioned to the users based on their availability, demand and quality parameters required to be satisfied. The task scheduling onto the distributed and virtual resources is a main concern which can affect the performance of the system. In the literature, a lot of work has been done by considering cost and makespan as the affecting parameters for scheduling the dependent tasks. Prior work has discussed the various challenges affecting the performance of dependent task scheduling but did not consider storage cost, failure rate-related challenges. This paper accomplishes a review of using meta-heuristics techniques for scheduling tasks in cloud computing. We presented the taxonomy and comparative review on these algorithms. Methodical analysis of task scheduling in cloud and grid computing is presented based on swarm intelligence and bio-inspired techniques. This work will enable the readers to decide suitable approach for suggesting better schemes for scheduling user’s application. Future research issues have also been suggested in this research work.

Image Edge Detection using Modified Ant Colony Optimization Algorithm based on Weighted Heuristics

Ant Colony Optimization (ACO) is nature inspired algorithm based on foraging behavior of ants. The algorithm is based on the fact how ants deposit pheromone while searching for food. ACO generates a pheromone matrix which gives the edge information present at each pixel position of image, formed by ants dispatched on image. The movement of ants depends on local variance of image’s intensity value. This paper proposes an improved method based on heuristic which assigns weight to the neighborhood. Experimental results are provided to support the superior performance of the proposed approach.

Performance evaluation of task scheduling with priority and non-priority in cloud computing

Minimizing the total allocation cost is an unavoidable issue needing to be deal with in task scheduling of cloud computing for processing all the tasks. In this paper, the comparative study has been done among the priority algorithms and secondly between the priority and non-priority task scheduling algorithms. In order to emulate the precedence relation of task, the task scheduling algorithms enumerate the priority of tasks according to the specific attributes of task, and then sort tasks by priority. The total allocation costs for each scheduling algorithm are calculated. The experimental results based on cloudsim3.0 toolkit with NetBeans IDE8.0 shows that the ABC algorithm (priority based) achieves good performance in cost parameter with the comparison of QoS driven, virtual machine tree (both are priority based) and traditional scheduling algorithms but the comparison of ABC (priority based) and PSO (non priority based) shows that the non priority algorithm gives best performance due to less waiting time to allocation task.

An Algorithm Design to Evaluate the Security Level of an Information System

Measuring the security of an Information System has become a critical issue in the era of Information Technology. As any other process, security can not be improved, if it can not be measured. The need of security metrics is important for assessing the current security status. Since all systems and organizations are different, there is no single set of metrics that is generally applicable. This paper presents an algorithm to develop the necessary security metrics for assessing the information system in a structured way and a quantitative evaluation model with qualitative decision based on Analytic Hierarchy Process (AHP) to measure the security level of the Information System. At last, a test case is given to illustrate the algorithm and effectiveness of this model.

FPGA implementation of RSA based on carry save Montgomery modular multiplication

Modular multiplication determines the efficiency of RSA cryptosystem as modular multiplication is core operation in RSA. The efficiency of modular multiplication can be improved by algorithmic improvement. The long operands in Montgomery modular multiplication can be added with carry save adders. Implementation of carry save adders on FPGAs require more area. This paper presents the implementation results of RSA on FPGAs based on carry save Montgomery.

Early-word-based montgomery modular multiplication algorithm

Modular multiplication is basic operation in public key cryptosystems like RSA. Montgomery modular multiplication being efficient is widely used. It is based on additions and shift operations. Each iteration requires a right shift, therefore in a word based architecture a complete word is not formed at end of iteration. This paper presents compute early word based scalable Montgomery architecture. It computes the most significant bit of word by applying 2 XOR operations. Also compute early scheme for common multiplicand Montgomery is proposed. Both the architectures are compared with previous architectures in literature.

Analysis of shape and orientation recognition capability of Complex Zernike Moments for signed gestures

In this paper, exact behavior of Complex Zernike Moments is analyzed. Zernike Moments contain two parameters: magnitude and orientation. In literature, mostly magnitude is considered to recognize the shape, because magnitude is orientation invariant. On the other hand, orientation of an image has its own significance in case of sign language. This work is dedicated to the study of the capability of Zernike Moments to recognize shape and orientation of Indian Sign Language gestures. Database of total 720 images of five signs (C, I, L, T, V) is used here. Test sets are designed such that they are shape specific, orientation variant and orientation invariant. Experiments are performed on these test sets for magnitude, phase and their combination. High accuracy is achieved even at lower order of Zernike Moments when both magnitude and phase are used as a feature set.

Comparative Analysis of Movement and Tracking Techniques for Indian Sign Language Recognition

Sign Language is considered as a way of communication for hearing handicapped persons. We can make the communication of deaf people easier by building a translation system of this language. To realize these systems, the identification of words and gestures in sign language is very important. Indian Sign Language (ISL) is used in major parts of India that includes gestures. Most of the gestures include movements of a part of body. Here, in this paper, the focus is to track the movement of hand, identifying its shape and direction of motion. The tracking techniques are compared on some factors and analysis is done. Preprocessing for extracting the region of interest (a hand) is done on image sequences. Tracking is done through Mean-shift and Kalman filter. The performance of the above mentioned algorithms are compared on the basis of precision, tracking time, affect of velocity change and recognition. Different shape based features are extracted based on different region based shape models. The preprocessing and feature extraction is done in MATLAB. After extracting these features are applied as input to a classifier. Classification is done in WEKA. Performance of the system is analyzed by identification of hand shape with direction.