Volume 1 No.1 January 2007
|
| 1. |
Information Extraction from Biomedical Literature using Text Mining Framework Download PDF |
|
|
Authors |
K. Latha, S. Kalimuthu and Dr. R. Rajaram |
|
|
Abstract |
Biomedical publications are unstructured in nature, making it difficult to utilize data mining or knowledge discovery techniques to retrieve needed documents. In this paper we propose a Text Mining Framework to extract the Biomedical documents from the Biomedical Literature. Our Framework is divided into three distinct stages such as text gathering, text preprocessing and data analysis. The goal of this paper is to use optimized methods to the three stages and to display results. We have used java as front end and oracle as back end for implementing the framework. |
|
|
Keywords |
Biomedical literature, Data mining, Framework, Text mining. |
|
| 2. |
Design of Novel Photonic Antenna for Optical Wireless Communication by Analyzing Non Linear Filtering Effects using Advanced Optical Signal Processing Method Download PDF |
|
|
Authors |
L.R.D. Suresh and Dr. S. Sundaravadivelu |
|
|
Abstract |
Many structures for photonic antenna were suggested after analyzing its ability and suitability to optical wireless communication using classical transmission line analogy. But we are using novel idea that is analyzing the non linear filtering effects of triangular grating structure with metal strips (non linear structure) and then designing the photonic antenna. We are using recent advanced optical signal processing technique namely the Beam Propagation Method for our analysis and design. The results show that the radiation efficiency and spectral width are very much improved by this structure and it is suitable for long distance optical wireless communication. |
|
|
Keywords |
Beam Propagation Method, nonlinear filtering, photonic antenna, optical wireless communication. |
|
| 3. |
Performance Analysis of Vector Quantizer using Modified Generalized Lloyd Algorithm Download PDF |
|
|
Authors |
Mrs. V.S. Jayanthi, K. Swapnil Marothi, T.M. Ishaq Mohammed Abbas and Dr. A. Shanmugam |
|
|
Abstract |
In this paper, we propose a new Vector Quantization method that generates codebook using Generalized Lloyd Algorithm. Our algorithm known as MGLA is derived from Generalized Lloyd Algorithm to overcome empty cell problem. Further, Huffman coding of the indices generated by the encoder is used. Our experiments on several training and test images demonstrate that the proposed scheme can produce the reconstructed images of good quality in terms of Peak Signal to Noise Ratio. A gain of 2dB to 15.9dB in the PSNR has been obtained through MGLA in our tests, by using a few additional iteration steps. |
|
|
Keywords |
Empty cell problem, Generalized Lloyd Algorithm, Huffman coding, Peak Signal to Noise Ratio, Vector Quantization. |
|
| 4. |
Performance Analysis of Biorthogonal Wavelet Filters for Lossy Fingerprint Image Compression Download PDF |
|
|
Authors |
S.S. Gornale, R.R. Manza, Vikas Humbe and K.V. Kale |
|
|
Abstract |
The increasing amount of fingerprints collected by law enforcement agencies has created an enormous problem in storage and transmission [1]. To reduce the increasing demand of storage space and transmission time, Compression techniques are the need of the day. There are many image compression techniques available at present. Wavelet coding is one of the effective techniques for compression and de-noising of image [2] [3]. In wavelet based image coding, a variety of orthogonal and biorthogonal filters have been developed by researchers for signal analysis and compression. The selection of wavelet filters plays a crucial part in achieving an effective coding performance, because there is no filter that performs the best for all images [4]. The Current Compression system uses the biorthogonal wavelet filters instead of orthogonal. Because Orthogonal filters have a nice property of energy preservation where as biorthogonal filters lack of it. Daubechies, Symlet and Coiflet filters having special property of more energy conservation, more vanishing moments , regularity and asymmetry than other biorthogonal filters [5]-[7]. In this paper we have analyze the best biorthogonal wavelet filter out of Daubechies, Symlet and Coiflet for lossy fingerprint image compression. For this, we have applied Daubechies, Symlet and Coiflet Wavelet Transforms (WT) through different orders at 1 to 5 decomposition levels on the fingerprint images. Our results show that the Coiflet4 (4th order) wavelet filter is more suitable for lossy fingerprint image compression and gives a better compression at 5th level. |
|
|
Keywords |
Decomposition, Fingerprint Image Compression, Wavelet Compression, Wavelet Filter. |
|
| 5. |
Real-Time Pipelined Rank Filter Download PDF |
|
|
Authors |
Dragana Prokin and Milan Prokin |
|
|
Abstract |
The major difference between hardware realizations of state-of-the-art algorithms and real-time pipelined rank filtering algorithm is that it reduces the complexity of specialized processing hardware, due to identical pipelined stages. The latency of pipelined rank filter is equal to the number of bits in input data sample. The pipelined rank filter produces one output rank sample each clock cycle, providing real-time nonlinear filtering of images and video. |
|
|
Keywords |
Pipelined, rank, median, filter. |
|
| 6. |
Micro Machined Non-Linear Wavelength Filters for Image Acquisition Download PDF |
|
|
Authors |
S. Perumal Sankar and Dr. S. Sundaravadivelu |
|
|
Abstract |
A key metric for digital imaging systems is the rate at which image information is delivered to the target. Typically, the rate of data delivery is given by the product of pixel modulation, multiplied by number of pixels, multiplied by the number of gray-scale bits. Obviously, the method achieving gray-scale is more important. By capitalizing on high-speed analog nature of GLV device, it is possible to deliver many millions of gray-scale pixels per second. Using a GLV device, it is quiet possible to project an image with 1080 x 1980 pixel resolution at a rate of 60 frames per second. The goal is to produce natural colors with high resolution by using non-linear filter characteristics of grating microstructure called grating light valve. The wavelength selective surface operation of this filter depends on a periodic array of elements and the grating depth of GLV. The depth of the grating element is in the order of one fourth of the electrical wavelength, and the array period is typically several wavelengths for efficient operation. |
|
|
Keywords |
Non-linear filter, MOEMS, GLV. |
|
| 7. |
Skin Detection in Luminance Images using Threshold Technique Download PDF |
|
|
Authors |
A. Hani. K. Almohair, Abd Rahman Ramli, Elsadig A.M. and B. Shaiful J. Hashim |
|
|
Abstract |
With the development of the chromatic skin color detection models, the threshold value is a useful and forceful element to discriminate between the skin and non-skin pixels. This paper reports an experimental investigation, which aims at using different threshold values to classify the human skin. The chromatic skin color model was used to model skin color in the r-g chromaticity space. This model based on testing database containing many of human images. It has been found that the threshold value is an important tool for increasing the human skin regions detected in color images containing luminance. |
|
|
Keywords |
Skin chrominance models, Pixels classification, Skin detection. |
|
| 8. |
Fixed pattern noise correction and implementation for infrared focal plane array based staring system using scene statistics Download PDF |
|
|
Authors |
Ajay Kumar, S. Sarkar and R.P. Agarwal |
|
|
Abstract |
The spatial and temporal non-uniformities in infrared focal plane array (IRFPA), which is called as fixed pattern noise (FPN), results in a slowly varying pattern on the thermal image thereby, degrading the resolving capabilities of thermal imaging system considerably. In this paper a scene based fixed pattern noise correction method using the scene statistical parameter is presented. The proposed method corrects both the additive and multiplicative types of fixed patter noise thus eliminating the need of halting the operation of thermal camera for calibration. FPGA based approach is presented for implementing the proposed algorithms. Comparison of the proposed method with Scribner algorithm and Harris constant statistics methods show it to be the most superior of the three. |
|
|
Keywords |
FPGA, fixed pattern noise, Infrared focal plane array, Thermal imaging. |
