ICGST/GVIP Journal VOLUME={11}, ISSUE = {III}, June 2011
ISSN:
1687-398X
Print,
1687-3998
Online
& 1687-4005
CD-ROM
| @ARTICLE |
{P1151053407, |
| AUTHOR = |
{S.Kezia and V.Vijaya Kumar and I.Shanti Prabha}, |
| TITLE = |
{Auto Detection of Tubercle Bacilli Based on Wavelets}, |
| JOURNAL = |
{ICGST International Journal on Graphics, Vision and Image Processing, GVIP}, |
| YEAR = |
{2011}, |
| MONTH= |
{June}, |
| VOLUME = |
{11}, |
| ISSUE = |
{III}, |
| PAGES= |
{1--8} |
| ABSTRACT= |
{Tuberculosis (TB) is one of the deadliest diseases in the world. One problem in processing fluorescent Tubercle bacilli images is the presence of speckle noise which is multiplicative and is a major limitation on image quality. The effect of speckle noise can be reduced by a quality of segmentation. For this the present paper proposes a new segmentation technique, based on wavelet transforms, morphological operations and edge operators. To shade the surrounding particles and to enhance the brightness of the bacilli of the image, morphological transforms are used prior to the segmentation. This improves the quality of the proposed segmentation scheme in detecting edges of the bacilli even in the presence of speckle noise. The experimental result indicates the efficiency of the proposed method in the presence of high speckle noise}, |
| NOTE= |
{Speckle noise, image quality, edges of bacilli, edge operators}} |
(Status:
Accepted Full Paper)
| @ARTICLE |
{P1151112535, |
| AUTHOR = |
{V. R. Khapli and A. S. Bhalchandra}, |
| TITLE = |
{Spatial Domain Approach for Effective Image Retrieval using Thumbnails of Images}, |
| JOURNAL = |
{ICGST International Journal on Graphics, Vision and Image Processing, GVIP}, |
| YEAR = |
{2011}, |
| MONTH= |
{June}, |
| VOLUME = |
{11}, |
| ISSUE = |
{III}, |
| PAGES= |
{9--16} |
| ABSTRACT= |
{The paper discusses the technique for making image retrieval effective using image thumbnails. Here effective means faster and accurate. The proposed technique suggests the use of Vector quantization to extract features from image thumbnails database as well as query image thumbnail. The empirical results shows that the thumbnail size 8 is suitable for faster image retrieval without compromising accuracy, in VQ based image retrieval. It was also tested that Euclidian Distance is not always the best similarity metric for effective image retrieval. Experimentation was performed to find best similarity metric for VQ based image retrieval technique and it was found that Kolmogorov distance outperformed Euclidian Distance in terms of retrieval accuracy and retrieval time}, |
| NOTE= |
{Content based image retrieval, Codebook, Vector quantization, Similarity metrics}} |
(Status: Accepted Full Paper)
| @ARTICLE |
{P1151113541, |
| AUTHOR = |
{Ali Mohammed Sahan}, |
| TITLE = |
{Face Recognition Using Wavelet Moments and Fast Wavelet Transform}, |
| JOURNAL = |
{ICGST International Journal on Graphics, Vision and Image Processing, GVIP}, |
| YEAR = |
{2011}, |
| MONTH= |
{June}, |
| VOLUME = |
{11}, |
| ISSUE = |
{III}, |
| PAGES= |
{17--22} |
| ABSTRACT= |
{In this paper we present face recognition method using a combination of fast wavelet transform and wavelet moments. The role of fast wavelet transform is to decompose the original image into different frequency sub-bands and removes the redundancy and to preserve the original features of the face image. In order to speed up and increase the accuracy of the proposed face recognition system, we keep only the coefficients of the approximation sub-band and discard the other sub-bands coefficients to feed the next stage wavelet moments. The proposed method is tested on the ORL face database which contains large variability in facial expression, illumination and pose. The proposed method has been compared with wavelet moments and Zernike moments. The results of the experiments indicate that the proposed method is better than both Zernike moments and wavelet moments in the recognition rate and the speed of the face recognition system}, |
| NOTE= |
{Face recognition, wavelet transform, wavelet moments, Zernike moments}} |
(Status: Accepted Full Paper)
| @ARTICLE |
{P1151103474, |
| AUTHOR = |
{Vijay Kumar Kodavalla and Dr. P.G. Krishna Mohan}, |
| TITLE = |
{Qualitative Distributed Video Coding Paradigm}, |
| JOURNAL = |
{ICGST International Journal on Graphics, Vision and Image Processing, GVIP}, |
| YEAR = |
{2011}, |
| MONTH= |
{June}, |
| VOLUME = |
{11}, |
| ISSUE = |
{III}, |
| PAGES= |
{23--30} |
| ABSTRACT= |
{In the present state-of-art, video compression is always referred to one of the popular hybrid transform and predictive coding standards such as H.26x, MPEG2, MPEG4, VC-1 and DivX so on. These standards work very well for applications such as broadcast and video-on-demand etc. However there are other class of emerging applications such as wireless video surveillance, wireless video sensor networks, disposable cameras for some medical applications etc. For these said emerging applications, state-of-the-art predictive video coding standards are not suitable. A new video compression paradigm known as Distributed Video Coding (DVC) is a solution for many of these emerging applications. This paper outlines emerging applications which necessitated DVC, implementation results and its maturity levels}, |
| NOTE= |
{Group of Pictures (GOP), Group of Sources (GOS), Discrete Cosine Transform (DCT), Low Density Parity Check Accumulator (LDPCA) and Distributed Video Coding (DVC)}} |
(Status: Accepted Full Paper)
| @ARTICLE |
{P1151123630, |
| AUTHOR = |
{Mansi Subhedar andGajanan Birajdar}, |
| TITLE = |
{Block Level Entropy Thresholding Technique for High Volume Image Adaptive Data Hiding}, |
| JOURNAL = |
{ICGST International Journal on Graphics, Vision and Image Processing, GVIP}, |
| YEAR = |
{2011}, |
| MONTH= |
{June}, |
| VOLUME = |
{11}, |
| ISSUE = |
{III}, |
| PAGES= |
{31--38} |
| ABSTRACT= |
{Digital image steganography is the art of hiding data in other digital images in such a way that it is imperceptible to human observer. Significant aspects of steganographic system are the stego image quality and capacity of data hiding. In the proposed algorithm, high volume data hiding is achieved by taking the JPEG (Joint Photographic Experts Groups) image into account. Two different approaches are used in this paper. In the first approach, after dividing cover image into 8X8 non overlapping blocks, DCT (Discrete Cosine Transform) is computed and based on Entropy Threshold (ET) scheme, these blocks are selected for information embedding decision. Second approach performs same processing steps by dividing the cover image into 16X16 non overlapping blocks. After data embedding, the quality of stego image is analysed using various metrics like PSNR (Peak Signal to Noise Ratio), RMSE (Root Mean Square Error), SNR (Signal to Noise Ratio) and MSSIM (Mean Structural Similarity Index) for both the approaches. It is evident from the simulation results that stego object with minimum distortion can be obtained while maintaining the high capacity of data embedding using the second approach as compared to first one}, |
| NOTE= |
{ Steganography, JPEG, Data hiding, Entropy thresholding, DCT, MSSIM}} |
(Status: Accepted Full Paper)
| @ARTICLE |
{P1151024109, |
| AUTHOR = |
{Yamuna Govindarajan and Sivakumar Dakshinamurthi}, |
| TITLE = |
{Attack Analysis of Robust Watermarking Technique for Patent Infringement}, |
| JOURNAL = |
{ICGST International Journal on Graphics, Vision and Image Processing, GVIP}, |
| YEAR = |
{2011}, |
| MONTH= |
{June}, |
| VOLUME = |
{11}, |
| ISSUE = |
{III}, |
| PAGES= |
{39--45} |
| ABSTRACT= |
{The process of updating, duplicating and distributing the digital maps turn out to be greatly simpler in the form of digital data. Illegal replication and sharing or forgery of the maps is too trouble-free simultaneously. A digital watermarking method has been proposed in this paper, which is used for Patent Infringement. To record the information of a protected primary image and the related watermarks, new Shuffling Technique, Composition & Decomposition, and Encryption & Decryption have been utilized by this method. The processing of watermark could be supported by the quadtree and supplementary protection to information is given by Rijndael. For Patent Protection, we have proposed a new architecture. For promising digital rights management application, the proposed new architecture embraces guarantee for a healthier negotiation between quality and security. Moreover that, from the audition results, we show that the proposed watermarking scheme can robustly recover decipherable watermarks from variety of assail host images}, |
| NOTE= |
{ Digital watermarking, Patent protection, Shuffling, Quadtree, Rijndael, Robustness}} |
(Status: Accepted Full Paper)
| @ARTICLE |
{P1151120613, |
| AUTHOR = |
{M.Narayana and Sanddep.V.M and Subhash Kulkarni }, |
| TITLE = |
{Skeletal Distance Mapped Functional Features for Improved CBIR}, |
| JOURNAL = |
{ICGST International Journal on Graphics, Vision and Image Processing, GVIP}, |
| YEAR = |
{2011}, |
| MONTH= |
{June}, |
| VOLUME = |
{11}, |
| ISSUE = |
{III}, |
| PAGES= |
{47--56} |
| ABSTRACT= |
{We propose a simple, fast, robust and efficient technique to extract the shape signatures for the standard MPEG-7 and Large Binary Databases for binary object shape mining. The Improved Content Based Image Retrieval system uses five shape features- two features have derived from combination of skeleton, region, and boundary information and the other three have been derived from distance mapped functional(level contours). All these shape features exhibit invariance to rotation and scaling}, |
| NOTE= |
{CBIR; Distance Metric; Shape Retrieval; Precision; Recall}} |
(Status: Accepted Full Paper)
|
