Volume 2 No 1 January 2008
|
| 1. |
A Novel Approach for Segmentation of Text from Compound Images Download PDF |
|
|
Authors |
C. Nelson Kennedy Babu |
|
|
Abstract |
-In this paper, a method for the segmentation of the text regions from compound images is proposed. The Haar Discrete Wavelet Transform (DWT) is employed. The resulted detail component sub bands contain both text edges and non-text edges. The Sobel edge detector is applied on each sub image to extract the strong edges. The resultant edges are used to form an edge map using a weighted OR operator. The edge map is binarized using a threshold. A morphological dilation operation is performed on the processed edge map. The projection profiles are analyzed to localize the text regions. Finally a threshold is applied which results in the segmentation of the real text regions from the image. |
|
|
Keywords |
Text extraction, Haar DWT, Thresholding, Weighted |
|
| 2. |
Human Face Detection in Color Images using Mixed Gaussian Color Models Download PDF |
|
|
Authors |
Krishnan Nallaperumal , Ravi Subban, R.K.Selvakumar, A. Lenin Fred, C. Nelson KennadyBabu, S.S. Vinsley, C. Seldev |
|
|
Abstract |
The segmentation of the human face regions in color images is a preliminary step in many applications, such as, human motion detection, human computer interaction, face recognition, video classification. This paper proposed a skin segmentation approach and gave a comparative analysis of few mixed Gaussian color model using four color spaces. Five combinations of two color space were used in Gaussian model. This new human face detection algorithm involves two stages: applying mixed Gaussian skin color model to segment human skin regions and using template matching technique to detect human face regions in color images. RGB color space will not differentiate the human skin color and the clothes when skin color and clothe color are the same. YIQ color space produces better results than RGB. YCbCr color space produces better results than RGB, YIQ. But YUV color space produces the best results when used to segment skin regions in color images using mixed Gaussian color models. These inferences are derived from the visual effects. This algorithm is quite practical and faster in comparison to other techniques such as neural networks. |
|
|
Keywords |
Face detection, Mixed Gaussian color model, Facial Features, Eye Map and Mouth Map. |
|
| 3. |
A Simple and Fast Finger Print Feature Extraction Download PDF |
|
|
Authors |
Nallaperumal Krishnan, A. Lenin Fred, Anand Viswanathan, S. Ravi, C. Seldev Christopher, S.S. Vinsley, R.K. Selvakumar |
|
|
Abstract |
Extracting minutiae from fingerprint images is one of the most important steps in Automatic Fingerprint Identification System (AFIS). Among various types of minutiae, ridges and bifurcations are widely used. As there are chances for large number of ridges and false ridges, we consider only the bifurcations in our minutiae extraction. We proposed an efficient algorithm to extract the bifurcations by using templates for bifurcation. The proposed algorithm avoids numerous template comparisons. It also reduces the occurrence of false minutiae (bifurcations). The results achieved are compared with those obtained from some other methods. This proposed method shows some improvement in the minutiae detection process in terms of efficiency and the run time.
|
|
|
Keywords |
|
|
| 4. |
Network Anomaly Detector System for Active Networks Download PDF |
|
|
Authors |
P.Jayashree, Dr.K.S.Easwarakumar |
|
|
Abstract |
Increasing attacks necessitates the need for an efficient intrusion system for mitigating such attacks. Anomaly detection among other types of Intrusion detection(ID) plays a vital role in Intrusion detection systems(IDS). The various IDS proposed in the literature, are not complete in detecting attacks to desired probability. In this paper a complete solution to anomaly detection of intrusions in the network is drafted. A two stage detection process is assumed where the IDS performs the common pattern detection using signatures in the first stage followed by an anomaly detector in the second stage. Focus is made only on the second stage in this paper to address anomaly detection. The detection is based on network traffic analysis with less monitoring overhead and is deployed in active networks. This paper attempts to define a complete anomaly detector utilising two novel algorithms namely packet marker algorithm and mutual path algorithm to provide an efficient and reliable solution for the anomaly detection whose implementation is underway and it is expected to provide better response in terms of false positive /negative prediction and delay in prediction.
|
|
|
Keywords |
Active network, Anomaly detection, Intrusion detection , Network traffic |
|
| 5. |
Automatic Curvilinear Structure detection from Satellite Images using Multiresolution GMM Download PDF |
|
|
Authors |
Mirnalinee Dhinesh, Sukhendu Das, Koshy Varghese |
|
|
Abstract |
This paper presents a multi-resolution based framework for detecting curvilinear structures from satellite images. Curvilinear structure detection finds its application in remote-sensed images for the extraction of networks such as roads, rivers, and highways. In the proposed methodology, curvilinear segments from the satellite images are extracted using multi-resolution GMM approach. The extracted curvilinear segments can be used for the detection and recognition of roads in the satellite images. Results show the validity of the approach.
|
|
|
Keywords |
|
|
| 6. |
A Method for Filtering the Blocking Artifacts in Block Coded JPEG Images Download PDF |
|
|
Authors |
Nallaperumal Krishnan, Jennifer J. Ranjani, Dr. M. Suganthi, G. S. R. Emil Selvan |
|
|
Abstract |
The popular international standard for compression, the Joint Photographers Expert Group (JPEG) can lead to noticeable discontinuities along the boundaries called the ‘blocking artifacts’. When the image is JPEG compressed the high frequency details of the coded image are mainly contaminated by quantization noise. The effect of quantization noise in the image can be approximated to that of Gaussian noise. The filter proposed in this paper preserve the details whereas the artifacts are smoothened. |
|
|
Keywords |
Blocking artifact, JPEG, Post processing, Image Enhancement. |
|
| 7. |
Combined Statistical and Structural Approach for Unsupervised Texture Classification Download PDF |
|
|
Authors |
C.Umarani, L.Ganesan, S. Radhakrishnan |
|
|
Abstract |
A combined statistical and structural approach have been used in this paper for texture representation. A set of Texture Primitives have been suggested. These primitives are basically tested for the presence of texture by conducting a suitable statistical test called Nair’s test. The set of universal primitives are labeled as local descriptor and the frequency of occurrences of these primitives is used as the global descriptor, namely Texture Primitive Spectrum for a given texture image. Since the occurrence of primitives and their placement rules uniquely define a texture image, the primitive spectrum is also unique, for a texture image. These spectrums are shown to be effectively used for un supervised texture classification for Brodatz and Vistex data bases of texture images. An average correct classification of 96% has been obtained. |
|
|
Keywords |
Texture- Primitives – Universal set of Primitives – global descriptor - Texture Primitive Spectrum – Un supervised texture classification. |
|
| 8. |
A Fractional Derivative Approach for Robust Segmentation of Blood Vessels in Digital Fundus Retinal Images Download PDF |
|
|
Authors |
G.VijayaSaradhi, S.Balasubramanian, V.Chandrasekaran |
|
|
Abstract |
Segmentation of Blood vessels is of key importance in the diagnosis of retinal images and early detection of diabetic retinopathy. In this paper, we propose a novel approach for segmentation of blood vessels in digital fundus retinal images using a fractional derivative-based edge operator. We have tested our algorithm on the standard DRIVE database. The results show significant improvement in terms of accuracy in segmentation and robustness to noise.
|
|
|
Keywords |
Biomedical image processing, blood vessel segmentation, diabetic retinopathy, fractional derivative |
|
| 9. |
Bi-Level 3D-Image Reconstruction from Two Orthogonal Projections with Periodicity and Sub Image Constraints Download PDF |
|
|
Authors |
V. Masilamani, Kamala Krithivasan |
|
|
Abstract |
As the Computed Tomography (CT) requires nor-mally hundreds of projections to reconstruct the image, patients are exposed to more X-ray energy, which may cause side effects such as cancer. Even when the variability of the particles in the object is very less, the Computed Tomography requires many projections for good quality reconstruction. Discrete Tomography makes use of less variability of the particles in an object to obtain good quality reconstruction. Though the reconstructed image and the original image have same projections, in general, they need not be the same. In addition to projections, if a priori information about the image is known, it is possible to obtain good quality reconstructed image. Here we give an efficient polynomial time algorithm to reconstruct a bi-level 3D-(1,1,1)-periodic image from its projection images along x and y directions , and a known sub image of the unknown image by reducing our reconstruction problem to integral max flow problem. |
|
|
Keywords |
Discrete Tomography, Image Reconstruction, Pro-jection, Computed Tomography, Integral Max Flow Problem. |
|
| 10. |
Hansa Filter: A Fuzzy Adaptive Nonlinear Gaussian Filter Download PDF |
|
|
Authors |
Krishnan Nallaperumal,.Selvakumar R.K., Arumugaperumal S., Annam.S and Vishwanath N |
|
|
Abstract |
Over the years a variety of methods have been introduced to remove Gaussian noise from digital images, such as Gaussian filtering, anisotropic filtering, and Total Variation minimization. However, many of these algorithms remove the fine details and structure of the image in addition to the noise because of assumptions made about the frequency content of the image. The Non-Local Fuzzy Adaptive Nonlinear Gaussian algorithm used in Hansa Filter does not make these assumptions, but instead assumes that the image contains an extensive amount of redundancy. These redundancies can then be exploited to remove the noise in the image. This Hansa Filter will implement the Non- Local Fuzzy Adaptive Nonlinear Gaussian algorithm and compare it to other denoising methods using a better metric Fidelity Measure for Noise Restoration – FMNR which measure the quality of noise restoration algorithm better than MSE measurement.
|
|
|
Keywords |
|
|
| 11. |
Adaptive Single Pixel Based Lossless Intra Coding For Download PDF |
|
|
Authors |
R.K. Selvakumar, Member IEEE, Krishnan Nallaperumal, Senior Member, IEEE |
|
|
Abstract |
-A new adaptive single pixel based lossless intra coding technique
employs pixel based DPCM(Differential Pulse Code Modulation) is presented
as an enhancement of H.264/MPEG-4 AVC(Advanced Video Coding)
standard. The current video standard H.264/AVC follows a block coding
style, which uses a number of prediction modes to leverage the compression
ratio. In this paper, we have addressed techniques to trace a significant pixel
in the source block adaptively based on perceptual considerations, applied
pixel wise DPCM for spatial prediction and entropy coded But, the block
style of H.264/AVC is not troubled for the transform encoding and decoding
process. From the experiments, it follows that the new adaptive single pixel
based lossless intra coding technique offers a better image quality and good
compression ratio as compared with the methods available in the current
standard. For image of any size, the current standard H.264 /AVC Intra
coding of 4x4 block prediction, one column pixel of the source block predicts
the entire row samples of the prediction block. If the visual significance of
source block in the macro block is considered for spatial prediction it offers
better results. In this paper, we highlight the exclusion of excess image data
present in both Luma and chromo components of a video frame based on a
single pixel.
|
|
|
Keywords |
|
|
| 12. |
Down Sampling To Improve I-Frame Of Video Download PDF |
|
|
Authors |
R.K.Selvakumar, Nallaperumal Krishnan, S.Shunmugam, K.Arulmozhi |
|
|
Abstract |
In this paper, the I-Frame of video/digital image is
down sampled by leaving alternate pixels in chessboard fashion and
the same procedure is repeated to reduce the image to one-fourth of
its original size. Then DCT transformation, JPEG quantization,
Huffman coding are applied sequentially to the resultant image. The
resultant bit stream is stored /transmitted. On the other side,
decoding of Huffman code, dequantization, inverse DCT are applied
and the resultant image is up sampled twice to get the full resolution
and in each stage bilinear interpolation technique is used to fill the
intermediate pixels. The restored image has good visual quality and
reasonable PSNR.
|
|
|
Keywords |
|
