Rajesh Roy | ADI SHANKARA INSTITUTE OF ENGINEERING AND TECHNOLOGY (original) (raw)
Papers by Rajesh Roy
International Journal of Computer Applications, Nov 15, 2012
Retina is the portion where many important eye diseases and systemic diseases manifest. By evalua... more Retina is the portion where many important eye diseases and systemic diseases manifest. By evaluating the retinal blood vessels, doctors can diagnose the primary stages of diabetic retinopathy, age related macular degeneration, glaucoma etc which may eventually lead to blindness. The objective is to develop an algorithm that segments the retinal blood vessels in a short time and with high accuracy. But the low gray level contrast and dynamic range of the image make the blood vessel segmentation process very difficult. A new multiscale transform, Curvelet transform, is used for retinal image contrast enhancement. Since the blood vessels are distributed in various directions multistructure elements morphology is used to find the blood vessel edges. The false edges are removed by morphological reconstruction. A locally applied level dependent thresholding algorithm with connected component analysis and length filtering removes the remaining false edges after reconstruction step. The proposed algorithm, when experimentally applied on images from the DRIVE database, gave an accuracy of more than 97% in less than 15 s, thus showing its effectiveness in retinal blood vessel segmentation.
2022 International Conference on Computing, Communication, Security and Intelligent Systems (IC3SIS)
Fourier transform methods are employed heavily in digital signal processing. Discrete Fourier Tra... more Fourier transform methods are employed heavily in digital signal processing. Discrete Fourier Transform (DFT) is among the most commonly used digital signal transforms, The exponential kernel of the DFT has the properties of symmetry and periodicity. Fast Fourier Transform (FFT) methods for fast DFT computation exploit these kernel properties in different ways. In this thesis, an approach of grouping data on the basis of the corresponding phase of the exponential kernel of the DFT is exploited to introduce a new digital signal transform, named the M-dimensional Real Transform (MRT), for l-D and 2-D signals. The new transform is developed using numbertheoretic principles as regards its specific features. A few properties of the transform are explored, and an inverse transform presented. A fundamental assumption is that the size of the input signal be even. The transform computation involves only real additions. The MRT is an integer-to-integer transform. There are two kinds of redund...
Number Theory and Its Applications, 2020
This chapter presents a detailed analysis of an integer-to-integer transform that is closely rela... more This chapter presents a detailed analysis of an integer-to-integer transform that is closely related to the discrete Fourier transform, but that offers insights into signal structure that the DFT does not. The transform is analyzed for its underlying properties using concepts from number theory. Theorems are given along with proofs to help establish the salient features of the transform. Two kinds of redundancy exist in the transform. It is shown how redundancy implicit in the transform can be eliminated to obtain a simple form. Closed-form formulas for the forward and inverse transforms are presented.
Procedia Computer Science, 2015
2008 International Conference on Computing, Communication and Networking, 2008
International Conference on Communication and Electronics System Design, 2013
ABSTRACT Transforms having directional properties are important in image processing applications.... more ABSTRACT Transforms having directional properties are important in image processing applications. M-dimensional Real Transform (MRT), having frequency and phase indices, is computed using real additions only. In this paper, the directional nature of MRT is presented. Each MRT coefficient is formed from combination of image coefficients in well-defined patterns, and this resembles a spatial filtering operation. The specific filter structure depends on frequency, and location of the filter on image lattice depends on phase. Combining the patterns associated with MRT coefficients having the same frequency index, global patterns can be created over the entire image lattice. These global patterns can be used as pattern strength indicators in images containing directional patterns. A subset of global patterns of a 16x16 MRT is used to estimate the orientation field of fingerprint images. Results obtained show that MRT can be used for orientation estimation.
2011 International Conference on Communications and Signal Processing, 2011
Page 1. 558 A New Transform for Signal Representation Utilizing neT Symmetries Rajesh Cherian Roy... more Page 1. 558 A New Transform for Signal Representation Utilizing neT Symmetries Rajesh Cherian Roy Dept. ofECE FISAT Angamaly, Kerala, India rajeshcherian@yahoo.co.in Abstract-Signal transforms are basic components of many signal processing applications. ...
International Journal of Computer Applications, 2012
Hybrid Image watermarking scheme proposed based on Discrete Cosine Transform (DCT)-Discrete Wavel... more Hybrid Image watermarking scheme proposed based on Discrete Cosine Transform (DCT)-Discrete Wavelet Transform (DWT)-Singular Value Decomposition (SVD). The cover image is reordered before DCT is applied. The DCT coefficients of the reordered image are decomposed into sub bands using DWT. The singular values of the middle sub bands are found and watermark is embedded. Simulation results shows that this method can survive attacks like rotation, cropping, JPEG compression and noising attacks and also can be used for copyright protection of multimedia objects.
International Journal of Computer Applications, 2012
In this paper, the image enhancement technique with respect to resolution and contrast has been p... more In this paper, the image enhancement technique with respect to resolution and contrast has been proposed. The proposed method is based on bi cubic interpolation, stationary wavelet transform, discrete wavelet transform and singular value decomposition. In the proposed technique stationary wavelet transform decomposes the input image into sub bands having different frequency coefficients. The high frequency coefficients have been multiplied with the orthogonal matrix (hanger and aligner) coefficients, obtained using singular value decomposition of low resolution input image. Resulting sub bands are further added with the high frequency sub bands obtained using stationary wavelet transform. Then, the low resolution input image and high frequency sub band images are interpolated using bi cubic interpolation. Inverse integer wavelet transform has been used to combine all these sub images. Image equalization is done on this image using singular value equalization. The proposed technique is tested on different satellite images. The experimental results show the proposed method gives good results over conventional methods.
International Conference on Information, Communications and Signal Processing, 2011
The Haar transform is an important signal transform that converts real input to real output, and ... more The Haar transform is an important signal transform that converts real input to real output, and it has been applied in various tasks in signal and image processing. The M-dimensional Real Transform (MRT) is a recently developed transform, and it shares the real-to-real conversion property of the Haar transform. This paper attempts to study the relationships between these two transforms.
International Journal of Computer Applications, 2012
Steganography allows us to hide a desired confidential information in a covered or host image whi... more Steganography allows us to hide a desired confidential information in a covered or host image while image encryption is decomposing the desired information to a nonreadable, non-comprehended manner. Steganography gained importance in the past few years due to the increasing need for providing secrecy in an open environment like the internet. This is made possible by hiding the very existence of the message and make communication undetectable. Steganography is the science of secret message delivery using cover media and has many technical challenges such as high hiding capacity and security. In this paper, a method is proposed to optimize these two requirements by suggesting a novel technique for hiding data in digital images. For this, an adaptive hiding capacity function along with a Kohonen neural network has been employed. This method hides secret data in Integer wavelet coefficients. The Optimal pixel adjustment (OPA) algorithm is applied after embedding the message. A new high capacity image steganographic method based on Kohonen neural network is also introduced. Kohonen network is trained according to the absolute contrast sensitivity of pixels present in cover image. On the receiving side, the original image is not needed for extracting the embedded data. It is observed that the capacity and security is increased with acceptable PSNR and hiding capacity.
2007 9th International Symposium on Signal Processing and Its Applications, 2007
M-Dimensional Real Transform (MRT) is an alternate rep-resentation of a signal which is derived f... more M-Dimensional Real Transform (MRT) is an alternate rep-resentation of a signal which is derived from the equa-tion for computation of the Discrete Fourier Transform (DFT). The raw MRT representation has redundant el-ements which makes it unsuitable for use in situations where memory ...
International Journal of Computer Applications, 2012
Super resolution is the process of reconstructing high resolution(HR) image from multiple low res... more Super resolution is the process of reconstructing high resolution(HR) image from multiple low resolution(LR) images of a scene. LR images are at a specific pixel shift from each other. High Resolution(HR) grids are formed from these LR images using Stationary Wavelet Transform (SWT) by image registration. Interpolation of the missing pixel in the HR grid is done using Curvelet Transform(CT). Experimental results show that our method has got high PSNR compared to Curvelet Transform based super resolution. Also, it is verified that there is no need of filter to avoid interpolation errors
International Journal of Computer Applications, 2012
This paper presents an invisible robust blind digital watermarking algorithm using adaptive and d... more This paper presents an invisible robust blind digital watermarking algorithm using adaptive and distributed quantization in contourlet domain for colour images. In the proposed watermarking scheme, the blue plane of the colour image is decomposed into series of multiscale, local and directional sub images using contourlet transform. The low frequency component of the transform is divided into non overlapping blocks, into which Arnold scrambled binary watermark is embedded, with help of adaptive quantization step value of each block. A blind detection algorithm is employed for the watermark recovery process, which does not require the original image. Experimental results show that the proposed algorithm is highly resistant to attacks such as JPEG compression, noising, cropping etc. The proposed method is compared with an odd-even quantization based technique and the results prove that the adaptive quantization based technique gives better robustness, under similar conditions.
The International Congress for …, 2007
A New Image Compression and Decompression technique based on 8x8 MRT MS Anish Kumar, Rajesh Cheri... more A New Image Compression and Decompression technique based on 8x8 MRT MS Anish Kumar, Rajesh Cherian Roy, R. Gopikakumari Division of Electronics Engg, School of Engineering, Cochin University of Science and Technology, Kochi-22, Kerala, India [ ...
AEU - International Journal of Electronics and Communications, 2008
The demand for high-speed transmission of best quality images over the internet has led to a stro... more The demand for high-speed transmission of best quality images over the internet has led to a strong need for the development of better algorithm for coding images. The transform coders are highly popular in encoding images. M-dimensional real transform (MRT) gives ...
International Journal of Computer Applications, Nov 15, 2012
Retina is the portion where many important eye diseases and systemic diseases manifest. By evalua... more Retina is the portion where many important eye diseases and systemic diseases manifest. By evaluating the retinal blood vessels, doctors can diagnose the primary stages of diabetic retinopathy, age related macular degeneration, glaucoma etc which may eventually lead to blindness. The objective is to develop an algorithm that segments the retinal blood vessels in a short time and with high accuracy. But the low gray level contrast and dynamic range of the image make the blood vessel segmentation process very difficult. A new multiscale transform, Curvelet transform, is used for retinal image contrast enhancement. Since the blood vessels are distributed in various directions multistructure elements morphology is used to find the blood vessel edges. The false edges are removed by morphological reconstruction. A locally applied level dependent thresholding algorithm with connected component analysis and length filtering removes the remaining false edges after reconstruction step. The proposed algorithm, when experimentally applied on images from the DRIVE database, gave an accuracy of more than 97% in less than 15 s, thus showing its effectiveness in retinal blood vessel segmentation.
2022 International Conference on Computing, Communication, Security and Intelligent Systems (IC3SIS)
Fourier transform methods are employed heavily in digital signal processing. Discrete Fourier Tra... more Fourier transform methods are employed heavily in digital signal processing. Discrete Fourier Transform (DFT) is among the most commonly used digital signal transforms, The exponential kernel of the DFT has the properties of symmetry and periodicity. Fast Fourier Transform (FFT) methods for fast DFT computation exploit these kernel properties in different ways. In this thesis, an approach of grouping data on the basis of the corresponding phase of the exponential kernel of the DFT is exploited to introduce a new digital signal transform, named the M-dimensional Real Transform (MRT), for l-D and 2-D signals. The new transform is developed using numbertheoretic principles as regards its specific features. A few properties of the transform are explored, and an inverse transform presented. A fundamental assumption is that the size of the input signal be even. The transform computation involves only real additions. The MRT is an integer-to-integer transform. There are two kinds of redund...
Number Theory and Its Applications, 2020
This chapter presents a detailed analysis of an integer-to-integer transform that is closely rela... more This chapter presents a detailed analysis of an integer-to-integer transform that is closely related to the discrete Fourier transform, but that offers insights into signal structure that the DFT does not. The transform is analyzed for its underlying properties using concepts from number theory. Theorems are given along with proofs to help establish the salient features of the transform. Two kinds of redundancy exist in the transform. It is shown how redundancy implicit in the transform can be eliminated to obtain a simple form. Closed-form formulas for the forward and inverse transforms are presented.
Procedia Computer Science, 2015
2008 International Conference on Computing, Communication and Networking, 2008
International Conference on Communication and Electronics System Design, 2013
ABSTRACT Transforms having directional properties are important in image processing applications.... more ABSTRACT Transforms having directional properties are important in image processing applications. M-dimensional Real Transform (MRT), having frequency and phase indices, is computed using real additions only. In this paper, the directional nature of MRT is presented. Each MRT coefficient is formed from combination of image coefficients in well-defined patterns, and this resembles a spatial filtering operation. The specific filter structure depends on frequency, and location of the filter on image lattice depends on phase. Combining the patterns associated with MRT coefficients having the same frequency index, global patterns can be created over the entire image lattice. These global patterns can be used as pattern strength indicators in images containing directional patterns. A subset of global patterns of a 16x16 MRT is used to estimate the orientation field of fingerprint images. Results obtained show that MRT can be used for orientation estimation.
2011 International Conference on Communications and Signal Processing, 2011
Page 1. 558 A New Transform for Signal Representation Utilizing neT Symmetries Rajesh Cherian Roy... more Page 1. 558 A New Transform for Signal Representation Utilizing neT Symmetries Rajesh Cherian Roy Dept. ofECE FISAT Angamaly, Kerala, India rajeshcherian@yahoo.co.in Abstract-Signal transforms are basic components of many signal processing applications. ...
International Journal of Computer Applications, 2012
Hybrid Image watermarking scheme proposed based on Discrete Cosine Transform (DCT)-Discrete Wavel... more Hybrid Image watermarking scheme proposed based on Discrete Cosine Transform (DCT)-Discrete Wavelet Transform (DWT)-Singular Value Decomposition (SVD). The cover image is reordered before DCT is applied. The DCT coefficients of the reordered image are decomposed into sub bands using DWT. The singular values of the middle sub bands are found and watermark is embedded. Simulation results shows that this method can survive attacks like rotation, cropping, JPEG compression and noising attacks and also can be used for copyright protection of multimedia objects.
International Journal of Computer Applications, 2012
In this paper, the image enhancement technique with respect to resolution and contrast has been p... more In this paper, the image enhancement technique with respect to resolution and contrast has been proposed. The proposed method is based on bi cubic interpolation, stationary wavelet transform, discrete wavelet transform and singular value decomposition. In the proposed technique stationary wavelet transform decomposes the input image into sub bands having different frequency coefficients. The high frequency coefficients have been multiplied with the orthogonal matrix (hanger and aligner) coefficients, obtained using singular value decomposition of low resolution input image. Resulting sub bands are further added with the high frequency sub bands obtained using stationary wavelet transform. Then, the low resolution input image and high frequency sub band images are interpolated using bi cubic interpolation. Inverse integer wavelet transform has been used to combine all these sub images. Image equalization is done on this image using singular value equalization. The proposed technique is tested on different satellite images. The experimental results show the proposed method gives good results over conventional methods.
International Conference on Information, Communications and Signal Processing, 2011
The Haar transform is an important signal transform that converts real input to real output, and ... more The Haar transform is an important signal transform that converts real input to real output, and it has been applied in various tasks in signal and image processing. The M-dimensional Real Transform (MRT) is a recently developed transform, and it shares the real-to-real conversion property of the Haar transform. This paper attempts to study the relationships between these two transforms.
International Journal of Computer Applications, 2012
Steganography allows us to hide a desired confidential information in a covered or host image whi... more Steganography allows us to hide a desired confidential information in a covered or host image while image encryption is decomposing the desired information to a nonreadable, non-comprehended manner. Steganography gained importance in the past few years due to the increasing need for providing secrecy in an open environment like the internet. This is made possible by hiding the very existence of the message and make communication undetectable. Steganography is the science of secret message delivery using cover media and has many technical challenges such as high hiding capacity and security. In this paper, a method is proposed to optimize these two requirements by suggesting a novel technique for hiding data in digital images. For this, an adaptive hiding capacity function along with a Kohonen neural network has been employed. This method hides secret data in Integer wavelet coefficients. The Optimal pixel adjustment (OPA) algorithm is applied after embedding the message. A new high capacity image steganographic method based on Kohonen neural network is also introduced. Kohonen network is trained according to the absolute contrast sensitivity of pixels present in cover image. On the receiving side, the original image is not needed for extracting the embedded data. It is observed that the capacity and security is increased with acceptable PSNR and hiding capacity.
2007 9th International Symposium on Signal Processing and Its Applications, 2007
M-Dimensional Real Transform (MRT) is an alternate rep-resentation of a signal which is derived f... more M-Dimensional Real Transform (MRT) is an alternate rep-resentation of a signal which is derived from the equa-tion for computation of the Discrete Fourier Transform (DFT). The raw MRT representation has redundant el-ements which makes it unsuitable for use in situations where memory ...
International Journal of Computer Applications, 2012
Super resolution is the process of reconstructing high resolution(HR) image from multiple low res... more Super resolution is the process of reconstructing high resolution(HR) image from multiple low resolution(LR) images of a scene. LR images are at a specific pixel shift from each other. High Resolution(HR) grids are formed from these LR images using Stationary Wavelet Transform (SWT) by image registration. Interpolation of the missing pixel in the HR grid is done using Curvelet Transform(CT). Experimental results show that our method has got high PSNR compared to Curvelet Transform based super resolution. Also, it is verified that there is no need of filter to avoid interpolation errors
International Journal of Computer Applications, 2012
This paper presents an invisible robust blind digital watermarking algorithm using adaptive and d... more This paper presents an invisible robust blind digital watermarking algorithm using adaptive and distributed quantization in contourlet domain for colour images. In the proposed watermarking scheme, the blue plane of the colour image is decomposed into series of multiscale, local and directional sub images using contourlet transform. The low frequency component of the transform is divided into non overlapping blocks, into which Arnold scrambled binary watermark is embedded, with help of adaptive quantization step value of each block. A blind detection algorithm is employed for the watermark recovery process, which does not require the original image. Experimental results show that the proposed algorithm is highly resistant to attacks such as JPEG compression, noising, cropping etc. The proposed method is compared with an odd-even quantization based technique and the results prove that the adaptive quantization based technique gives better robustness, under similar conditions.
The International Congress for …, 2007
A New Image Compression and Decompression technique based on 8x8 MRT MS Anish Kumar, Rajesh Cheri... more A New Image Compression and Decompression technique based on 8x8 MRT MS Anish Kumar, Rajesh Cherian Roy, R. Gopikakumari Division of Electronics Engg, School of Engineering, Cochin University of Science and Technology, Kochi-22, Kerala, India [ ...
AEU - International Journal of Electronics and Communications, 2008
The demand for high-speed transmission of best quality images over the internet has led to a stro... more The demand for high-speed transmission of best quality images over the internet has led to a strong need for the development of better algorithm for coding images. The transform coders are highly popular in encoding images. M-dimensional real transform (MRT) gives ...