International Journal of Image, Graphics and Signal Processing (IJIGSP)

IJIGSP Vol. 4, No. 3, Apr. 2012

Cover page and Table of Contents: PDF (size: 144KB)

Table Of Contents

REGULAR PAPERS

A Research on Visual Analysis of Badminton for Skill Learning

By Tatsunori Hashimoto Masashi Toda

DOI: https://doi.org/10.5815/ijigsp.2012.03.01, Pub. Date: 8 Apr. 2012

A lot of researches that detect the difference of the proficiency are reported for the dynamic scene of sports. Athlete population increases in late years. However, coach same as before population. In this research, it aimed at the helpful information in the beginner’s skill improvement by using the dynamic scene to play badminton for the clearing shot and aimed to acquire it. We compare standard deviation and average time from Ragging-back of stroke in beginner group and expert group to shot. It pretends and it compares it the detection of tracks of the joint part of the racket head to the shot from the Lagging-back beginning. Beginner and expert’s difference and common features are clarified by comparing images of the shot in the there is a shuttle state and the state of pretense. As a result, the feature and the beginner who drew yen while swinging to expert’s tracks got the feature such as gradual seen from the lowest part of tracks to the shot compared with the expert. Moreover, it has been understood that there is a difference between the beginner group and the expert group also at the time that hangs the shot and stability of the shot.

[...] Read more.
A Novel Algorithm for Minutiae Matching

By Om Preeti Chaurasia Saumya Ranjan Giri Anchal Garg

DOI: https://doi.org/10.5815/ijigsp.2012.03.02, Pub. Date: 8 Apr. 2012

This paper presents a simple and novel algorithm for minutiae matching in fingerprint images. After correct detection of all minutiae in two fingerprint images, the algorithm iteratively processes each minutiae point from two images and tries to find out the number of common points on the basis of structural similarity among them. We try to find all matching pairs of minutiae between two fingerprint images with reference to a pair of chosen reference point. Once all the common minutiae points identified, the matching score can be calculated using various existing formulas.

[...] Read more.
Noisy Image Decomposition Based On Texture Detecting Function

By Ruihua Liu Ruizhi Jia Liyun Su

DOI: https://doi.org/10.5815/ijigsp.2012.03.03, Pub. Date: 8 Apr. 2012

At present, most of image decomposition models only apply to some ideal images, such as, noise-free, without blurring and super resolution images, and so on. In this paper, they propose a novel decomposition model based on dual method and texture detecting function for noisy image. Firstly, they prove the existence of minimal solutions of the noisy decomposition model functional. Secondly, they write down an alterative implementation algorithm. Finally, they give some numerical experiments, which show that their model can effectively work for Gaussian noisy image decomposition.

[...] Read more.
General Research on Automatic Image Shrinking in the Wireless Capsule Endoscopy

By Igor Zhukov Fedorov Evgeny Mikhaylov Dmitry Ivanova Ekaterina Kukushkin Alexander Starikovski Andrey Tolstaya Anastasia

DOI: https://doi.org/10.5815/ijigsp.2012.03.04, Pub. Date: 8 Apr. 2012

In this paper we propose a method of image shrinking without loss of the quality with regard to a modern field in medical research - wireless capsule endoscopy. 
The wireless capsule is a small devise with a size of 1,5x2 cm. That means that the memory chip on which the results of the examination of the gastrointestinal tract are stored should also be tiny. The scope of the device imposes strict restrictions on the shrinking scheme that should be taken into consideration.
This article gives a brief overview of existing data shrinking methods and their application possibilities, namely triplets coding of binary combinations, conversion combination MTF (move-to-front) and Rice coding. Taking into consideration the specificity of application the more promising is the third way of image shifting without loss. This method is based on modified shrinking algorithms mentioned above.
According to the carried out experiments the overall scheme of the device was developed. This scheme implements the most efficient method of coding.
The described algorithm allows image shrinking on 20%. That means that endoscopic capsule may work significantly longer.

[...] Read more.
Sine Cosine Taylor Like Technique for Connected Component Detector by ICNN Simulation

By S.Senthilkumar Abd Rahni Mt Piah

DOI: https://doi.org/10.5815/ijigsp.2012.03.05, Pub. Date: 8 Apr. 2012

Sine cosine Taylor like technique is employed to carry out connected component detector (CCD) simulation under improved cellular neural network (ICNN) architecture to yield better accuracy for hand written character and image recognition system. The principal simulation results reveal that this technique performs well in comparison with other techniques.

[...] Read more.
EEG based Autism Diagnosis Using Regularized Fisher Linear Discriminant Analysis

By Mahmoud I. Kamel Mohammed J. Alhaddad Hussein M. Malibary Khalid Thabit Foud Dahlwi Ebtehal A. Alsaggaf Anas A. Hadi

DOI: https://doi.org/10.5815/ijigsp.2012.03.06, Pub. Date: 8 Apr. 2012

Diagnosis of autism is one of the difficult problems facing researchers. To reveal the discriminative pattern between autistic and normal children via electroencephalogram (EEG) analysis is a big challenge. The feature extraction is averaged Fast Fourier Transform (FFT) with the Regulated Fisher Linear Discriminant (RFLD) classifier. 
Gaussinaty condition for the optimality of Regulated Fisher Linear Discriminant (RFLD) has been achieved by a well-conditioned appropriate preprocessing of the data, as well as optimal shrinkage technique for the Lambda parameter. Winsorised Filtered Data gave the best result.

[...] Read more.
Edge Detection System using Pulse Mode Neural Network for Image Enhancement

By S.Jagadeesh Babu P.Karunakaran S.Venkatraman Hameem Shanavas .I T.Kapilachander

DOI: https://doi.org/10.5815/ijigsp.2012.03.07, Pub. Date: 8 Apr. 2012

Edge detection of an image reduces significantly the amount of data and filters out information that may be regarded as less irrelevant. Edge detection is efficient in medical imaging. Pulse mode neural networks are becoming an attractive solution for function approximation based on frequency modulation. Early pulse mode implementation suffers from some network constraints due to weight range limitations. To provide the best edge detection, the basic algorithm is modified to have pulse mode operations for effective hardware implementation. In this project a new pulse mode network architecture using floating point operations is used in the activation function. By using floating point number system for synapse weight value representation, any function can be approximated by the network. The proposed pulse mode MNN is used to detect the edges in images forming a heterogeneous data base. It shows good learning capability. In addition, four edge detection techniques have been compared. The coding is written in verilog and the final result have been simulated using Xilinx ISE simulator.

[...] Read more.
Luminance-based Embedding Approach for Color Image Watermarking

By Jamal Ali Hussein

DOI: https://doi.org/10.5815/ijigsp.2012.03.08, Pub. Date: 8 Apr. 2012

In this paper a new non-blind luminance-based color image watermarking technique is proposed. The original 512×512 color host image is divided into 8×8 blocks, and each block is converted to YCbCr color space. A 32×32 monochrome image is used as a watermark and embedded in the selected blocks of the original image. The selected blocks must have log-average luminance that is closer to the log-average luminance of the image. DCT transform is applied to the Y component of each selected block. Each four values of the watermark image are embedded into each selected block of the host image. The watermark values are embedded in the first four AC coefficients leaving the DC value unchanged. The watermark is extracted from the watermarked image using the same selected blocks and DCT coefficients that have been used in the embedding process. This approach is tested against variety of attacks and filters: such as, highpass, lowpass, Gaussian, median, salt and peppers, and JPEG compression. The proposed approach shows a great ability to preserve the watermark against these attacks.

[...] Read more.