Sarabjeet Singh Bedi

Implementation of hybrid image fusion technique for feature enhancement in medical diagnosis

Image fusion is used to enhance the quality of images by combining two images of same scene obtained from different techniques. In medical diagnosis by combining the images obtained by Computed Tomography (CT) scan and Magnetic Resonance Imaging (MRI) we get more information and additional data from fused image. This paper presents a hybrid technique using curvelet and wavelet transform used in medical diagnosis. In this technique the image is segmented into bands using wavelet transform, the segmented image is then fused into sub bands using curvelet transform which breaks the bands into overlapping tiles and efficiently converting the curves in images using straight lines. These tiles are integrated together using inverse wavelet transform to produce a highly informative fused image. Wavelet based fusion extracts spatial details from high resolution bands but its limitation lies in the fusion of curved shapes. Therefore for better information and higher resolution on curved shapes we are blending wavelet transform with curvelet transform as we know that curvelet transform deals effectively with curves areas, corners and profiles. These two fusion techniques are extracted and then fused implementing hybrid image fusion algorithm, findings shows that fused image has minimum errors and present better quality results. The peak signal to noise ratio value for the hybrid method was higher in comparison to that of wavelet and curvelet transform fused images. Also we get improved statistics results in terms of Entropy, Peak signal to noise ratio, correlation coefficient, mutual information and edge association. This shows that the quality of fused image was better in case of hybrid method.

An Adaptive Data Hiding Technique for Digital Image Authentication

The proposed scheme combines the advantages of cryptographic concept and imperceptibility feature of digital image watermarking in spatial domain. The watermark is first generated based on one-way hash function with the help of user key. Each bit of this new generated watermark is then embedded into respective blocks of the original image, in raster scan order. The embedding is performed by modifying the average value of pixel intensity of each block within a range specified by the contrast value for a given block. This reduces the effects of the modification as perceived by the human eye. The extraction procedure computes and compares the sum of the pixels values for the blocks of the original and watermarked image. The results demonstrates the robustness of scheme against common image processing operations like cropping, modification, low pass filter, median pass filter, scaled down and lossy JPEG compression with various quality index factor. Results also illustrate that the watermark is secure, recoverable and recognizable even after the watermarked image has been tampered, forged and modified by common image processing operations. The comparative study of proposed scheme with existing scheme has also been performed to observe the strength of the scheme.

NPT based video watermarking with non-overlapping block matching

The paper presents a naturalness preserving transform (NPT) based collusion and compression resistant watermarking technique for video. An image that is statistically similar to a video frame is chosen as the watermark and this image is embedded independently in consecutive frames of the video. To enhance the resistance to inter frame collusion based attacks, a non-overlapping block matching is used to determine the region for placing the watermark in consecutive frames. Only a trace of the watermark image is embedded which enhances the robustness of the watermark to different attacks. When a frame and the image become substantially different, another image is chosen as the watermark. The size of the watermark determines the quality of the watermarked video frames. Watermark extraction is blind and requires only the region where the watermark was originally placed. The reconstruction process is iterative and bestows immunity the watermark against noise and lossy compression. Analysis indicates that the watermark is sufficiently immune to second order inter-frame statistical attacks and is quite robust to image level compression. Experimental results confirm these theoretical findings and demonstrate the resistance of the technique to temporal frame averaging, additive noise and JPEG based compression. However, the technique is limited by the fact that the original video sequence (frames) is required for reconstruction based recovery of the watermark from the watermarked video sequence.

Robust Watermarking of Image in the Transform Domain Using Edge Detection

The human visual system exhibits reduced sensitivity to distortions in the regions of an image where the rate of change is significant. This entails that a watermark with significant value can be robust and if it resides near around edges and textured areas of an image, it would be imperceptible as well. The present work exploits this characteristic of the Human Visual system to embed a robust and imperceptible watermark in transform domain using edge detection. The embedding is done at block level in either the Discrete Hartley Transform (DHT) domain or in Discrete Cosine Transform (DCT) domain. The watermark is embedded block by block in different blocks of the image. The decision whether to embed in DHT domain or in DCT domain is based on the number of edges which exist in a given block in the image to be watermarked. Hence the threshold number of edges acts as a key in this algorithm and is used in the embedding as well in the extraction process of the watermark. The results demonstrate the robustness of scheme against common image processing operations like cropping, low pass filter, noise and lossy JPEG compression with various quality index factor. Results also illustrate that the watermark is perceptually transparent, recoverable, recognizable and robust even after the watermarked image has been passed through severe attacks.

A Design of Secure Watermarking Scheme for Images in Spatial Domain

Digital watermarking (DWM) technology has been proposed for the implementation of digital right management (DRM) system that can be used for establishing ownership right, ensuring authorized access and content authentication. The goal of this paper is to protect copyrights and content authentication of digital still images with the consideration of high level of robustness against changes made to invisible watermark contents in context to spatial domain. The proposed scheme combines the advantages of cryptographic concept and imperceptibility feature of digital image watermarking. The watermark is first generated based on hash function with the use of user key. Each bit of this new generated watermark is then encoded into respective blocks of 4times4 pixels of the original image, in raster scan order. The encoding is performed by modifying the average value of pixel intensity of each block with in a range specified by the contrast value for a given block. This reduces the effects of the modification as perceived by the human eyes. The experimental results show the robustness of scheme against common image processing operations. The results also demonstrate the location of modification as corresponding error in the extracted watermark

Video Watermarking Scheme based on IDR frames using MPEG-2 Structure

A robust, imperceptible and blind video watermarking scheme based on MPEG-2 is presented. The proposed algorithm using the DC coefficients from 8 × 8 block of discrete coefficient transform generated by picking candidate IDR frames based on column transposition method in order to embed the scrambled binary watermark. The watermark can only be extracted by using the secret keys, enhances the security of watermark. The robustness is evaluated by testing against spatial synchronisation attacks, temporal synchronisation attacks and re-encoding attacks by evaluating two parameters as normalised correlation and bit error rate in order to find the degree of similarity and degree of dissimilarity respectively between the original and extracted watermark. The superiority of the proposed algorithm is that the excellent robustness achieved against temporal synchronisation attacks and compression attack by comparing it with previous work and also good perceptibility obtained without changing the motion vectors during the DPCM process of MPEG-2 encoding scheme.

Hybrid image fusion of multimodality medical images for clinical diagnosis

In this paper, hybrid image fusion technique is implemented to improve the image content by fusing images taken from imaging tools. The computed tomography and magnetic resonance imaging are fused using dual tree complex wavelet transforms and curvelet transform. The obtained images are further fused using proposed hybrid technique. MATLAB R2013a coding is used for the fusion of image fusion transforms. Two set of images (brain and abdomen) are used to compare and evaluate the performance of the fusion algorithms. The fused images were evaluated using performance assessment criterias i.e. entropy, root mean square error, correlation coefficient, peak signal to noise ratio, mutual information and edge association. Result shows that the fused image using hybrid transform contains more useful information and relevant details for disease diagnosis. Performance evaluation criterias gives higher weightage to hybrid image fusion followed by curvelet and dual tree complex wavelet transforms.

Robust Video Watermarking Scheme Based on Intra-coding Process in MPEG-2 Style

The proposed scheme implemented a semi blind digital watermarking method for video exploiting MPEG-2 standard. The watermark is inserted into selected high frequency coefficients of plain types of discrete cosine transform blocks instead of edge and texture blocks during intra coding process. The selection is essential because the error in such type of blocks is less sensitive to human eyes as compared to other categories of blocks. Therefore, the perceptibility of watermarked video does not degraded sharply. Visual quality is also maintained as motion vectors used for generating the motion compensated images are untouched during the entire watermarking process. Experimental results revealed that the scheme is not only robust to re-compression attack, spatial synchronization attacks like cropping, rotation but also strong to temporal synchronization attacks like frame inserting, deleting, swapping and averaging. The superiority of the anticipated method is obtaining the best sturdiness results contrast to the recently delivered schemes.