Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
IRIS Feature Extraction and Classification using FPGA
Babasaheb G. Patil,Nikhil Niwas Mane,Shaila Subbaraman
International Journal of Electrical and Computer Engineering , 2012, DOI: 10.11591/ijece.v2i2.158
Abstract: This paper proposes a new architecture for VLSI implementation of singular value decomposition for IRIS feature extraction and determining simple hamming distance for pattern classification. Using dedicated personal computers for such applications is economically not justified. The main aim of this work is to provide flexible and reprogrammable hardware solution based on field programmable gate array (FPGA) for feature extraction and classification. Keywords: Singular value decomposition, FPGA, Jacobi transformation, finite state machine.
Soft Computing Based Texture Classification with MATLAB Tool
Pankaj H. Chandankhede
International Journal of Soft Computing & Engineering , 2012,
Abstract: This paper deals with Implementation of my previous work [1]. Here MATLAB simulation software is use as a platform tool for designing the concept of Texture Classification using Soft Computing Tool as a function of MATLAB. This paper classifies Textures on the basis of two novel approaches of artificial neural network & adaptive neuro-fuzzy inference system. This paper proves that neuro-fuzzy model performed better than the neural network in classification of texture image of three different types.
Implementation of Cryptographic Algorithm on FPGA  [PDF]
Prof. S. Venkateswarlu,Deepa G.M,G. Sriteja?
International Journal of Computer Science and Mobile Computing , 2013,
Abstract: Advanced Encryption Standard (AES), a Federal Information Processing Standard (FIPS), is anapproved cryptographic algorithm that is used to protect electronic data. The AES can be programmed insoftware or built with hardware. The paper presents a hardware implementation of the AES algorithm onFPGA. The algorithm was implemented in FPGA using Spartan 3E starter kit and Xilinx ISE developmentsuite. The purpose of this attempt was to test the correctness of the implemented algorithm and to gainexperience in optimization of algorithm structure for the embedded implementation in the target application.
An Optimal Implementation on FPGA of a Hopfield Neural Network  [PDF]
W. Mansour,R. Ayoubi,H. Ziade,R. Velazco,W. EL Falou
Advances in Artificial Neural Systems , 2011, DOI: 10.1155/2011/189368
Abstract: The associative Hopfield memory is a form of recurrent Artificial Neural Network (ANN) that can be used in applications such as pattern recognition, noise removal, information retrieval, and combinatorial optimization problems. This paper presents the implementation of the Hopfield Neural Network (HNN) parallel architecture on a SRAM-based FPGA. The main advantage of the proposed implementation is its high performance and cost effectiveness: it requires multiplications and additions, whereas most others require multiplications and additions. 1. Introduction Artificial Neural Networks (ANN’s) have become a subject of very dynamic and extensive research [1–4]. One important factor is the progress in VLSI technology, which makes easier the implementation and testing of ANNs in ways not available in the past. Indeed, the improvement of VLSI technology makes feasible the implementation of massively parallel systems with thousands of processors. Another important factor is the resurging of ANNs as a powerful paradigm for complex classification and pattern recognition applications. There are many publications in the literature concerning the implementation of Hopfield Neural Network (HNN) in FPGAs (Field Programmable Gates Arrays). In [2] an implementation of HNN on Xilinx VirtexE is used for block truncation coding for image/video compression. Reference [4] describes an implementation of HNN on FPGA (Virtex-4LX160) for the identification of symmetrically structured DNA motifs in Alpha Data, which has better performance than the same algorithms implemented in C++ on a IBM X260 Server. In another work [1] is studied the implementation of an associative memory neural network (AMNN) using reconfigurable hardware devices such as FPGA and its applications in image pattern recognition systems. In reference [5], the authors use a modified rule training (simultaneous perturbation learning rule) for HNN and showe its implementation in an FPGA. The basic associative memory paradigm can be defined as the storage of a set of patterns in such a way that if a new pattern is presented, the response is a pattern among the stored patterns which closely resembles . This implies that it is possible to recall the complete pattern even if only part of it is available. This powerful concept can be utilized in many applications such as pattern recognition, image reconstruction from a partial image, noise removal, and information retrieval. The Hopfield Neural Network, a very interesting model of ANNs which was discovered by Hopfield in the 80’s [6], can be used as an associative
Texture Classification Based on Texton Features  [cached]
U Ravi Babu,V Vijay Kumar,B Sujatha
International Journal of Image, Graphics and Signal Processing , 2012,
Abstract: Texture Analysis plays an important role in the interpretation, understanding and recognition of terrain, biomedical or microscopic images. To achieve high accuracy in classification the present paper proposes a new method on textons. Each texture analysis method depends upon how the selected texture features characterizes image. Whenever a new texture feature is derived it is tested whether it precisely classifies the textures. Here not only the texture features are important but also the way in which they are applied is also important and significant for a crucial, precise and accurate texture classification and analysis. The present paper proposes a new method on textons, for an efficient rotationally invariant texture classification. The proposed Texton Features (TF) evaluates the relationship between the values of neighboring pixels. The proposed classification algorithm evaluates the histogram based techniques on TF for a precise classification. The experimental results on various stone textures indicate the efficacy of the proposed method when compared to other methods.
Texture Classification based on Gabor Wavelet  [PDF]
Amandeep Kaur,Savita Gupta
International Journal of Research In Computer Science , 2012,
Abstract: This paper presents the comparison of Texture classification algorithms based on Gabor Wavelets. The focus of this paper is on feature extraction scheme for texture classification. The texture feature for an image can be classified using texture descriptors. In this paper we have used Homogeneous texture descriptor that uses Gabor Wavelets concept. For texture classification, we have used online texture database that is Brodatz’s database and three advanced well known classifiers: Support Vector Machine, K-nearest neighbor method and decision tree induction method. The results shows that classification using Support vector machines gives better results as compare to the other classifiers. It can accurately discriminate between a testing image data and training data.
Texture Classification of Brain  [PDF]
Nikita Dubey
International Journal of Computer Technology and Electronics Engineering , 2011,
Abstract: In this paper, a new cluster-based approach is proposed for extracting features from the coefficients of a two-dimensional discrete wavelet transform. The wavelet coefficients from the matrix of each frequency channel are segregated into non-overlapping clusters in an unsupervised mode using a set of application-specific representative images. In practical situations, this set of representative images can be the same as the ones kept aside for training a classifier. The proposed method divides the matrices of computed wavelet coefficients into disjoint clusters that are centered around the position of dominant coefficients. The features that can distinguish images of one class from those of other classes are obtained by computing energies of the clusters. The feature vectors so obtained are then presented as input patterns to an image classifier, such as a neural network. Experimental results based on the applications for texture classification and wood surface defect detection have shown that the proposed cluster-based wavelet feature extraction method is able to effectively extract important intrinsic information content from the test images, and increase the overall classification accuracy as compared with conventional feature extraction methods Medical image is completely incomprehensible to untrained eye. Since Normal Human eye has limitation to discriminate the gray scale images. It has only discriminate pixel intensities up to 15-30 gray levels. This restricts qualitative analysis of medical images. Hence we concentrate more on quantitative analysis that reveals more information from image. The presented contribution aimed at developing an automated imaging system which can efficiently classifies the normal tissues in medical images obtained from Computed Tomography (CT) scans. This paper presents texture feature based approach for Computerized Tomography (CT) scan images. A novel method of texture feature extraction based on Ridgelet transform has been reported in this paper. The approach consists of two steps: extraction of most discriminative texture features of regions of interest (ROI) and creation of classifier that automatically identifies the various tissues. The proposed algorithm validate against data obtained from different patients.
Object classification methods for application in FPGA based vehicle video detector
Wies?aw PAMU?A
Transport Problems : an International Scientific Journal , 2009,
Abstract: The paper presents a discussion of properties of object classification methods utilized in processing video streams from a camera. Methods based on feature extraction, model fitting and invariant determination are evaluated. Petri nets are used for modelling the processing flow. Data objects and transitions are defined which are suitable for efficient implementation in FPGA circuits. Processing characteristics and problems of the implementations are shown. An invariant based method is assessed as most suitable for application in a vehicle video detector.
Golomb Coding Implementation in FPGA
G. H. H’ng,M. F. M. Salleh,Z. A. Halim
Elektrika : Journal of Electrical Engineering , 2008,
Abstract: Golomb coding for data compression is a well known technique due to its lower complexity. Thus, it has become one of the favourite choices for lossless data compression technique in many applications especially in mobile multimedia communication. In this paper, the development of Golomb Coding compression and decompression algorithms in the Field Programmable Gate Array (FPGA) is presented. The coding scheme development in FPGA utilises the Verilog HDL. In order to prove its validity, the developed algorithm is simulated using the ALTERA Quartus II software.
FPGA Implementation of MPLS
Mirza Raheber Raza,,Praveen Kumar Y G,,Dr. M. Z. Kurian,,Dr. K. V. Narayanswamy
International Journal of Innovative Technology and Exploring Engineering , 2013,
Abstract: This paper presents a hardware architecture of Multi-Protocol Label Switching (MPLS). MPLS is a protocol used primarily to prioritize internet traffic and improve bandwidth utilization. MPLS solutions are meant to be used with Layer 2 or Layer 3 protocols. This paper presents hardware architecture to implement MPLS on FPGA.
Page 1 /100
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.