Identification of Volcano Hotspots by using Resilient Back Propagation (RBP) Algorithm Via Satellite Images
Data Hiding in Encrypted Compressed Videos for Privacy Information Protection
Improved Video Watermarking using Discrete Cosine Transform
Contrast Enhancement based Brain Tumour MRI Image Segmentation and Detection with Low Power Consumption
Denoising of Images by Wavelets and Contourlets using Bi-Shrink Filter
The work presented in this paper addresses the increasing demand of visual signal delivery to terminals with arbitrary resolutions, without heavy computational burden to the receiving end. In this paper, the principle of Seam Carving is incorporated into a wavelet codec (i.e., SPIHT). For each input image, block-based seam energy map is generated in the pixel domain and the curvelet transform is performed for the retargeted image. Different from the conventional wavelet-based coding schemes, curvelet coefficients here are grouped and encoded according to the resultant seam energy map. The bit stream is then transmitted in energy in descending order. At the decoder side, the end user has the ultimate choice for the spatial scalability without the need to examine the visual content; and an image with arbitrary aspect ratio can be reconstructed. The simulation result proved that the proposal technique give better results compared to wavelet based image compression.
The main objective of binary image enhancement is to process a binary image so that result is more suitable for specific application. While processing images, noise corrupts due to sensing of images sensed by malfunctioning cameras, image storage in faulty memory locations and image transmission via noisy channels. Binary images are useful for some applications as they need less memory for storage, less bandwidth for transmission and less computational time for processing. Hence it is necessary to suppress noise in noisy images to extract the necessary details. This paper proposes binary image enhancement technique using a parameterized adaptive iterative model in spatial domain. The type of noise considered is salt and pepper noise. Performance of the proposed method can be measured via subjective results like input-output images and objective like peak signal to noise ratio.
An adaptive visible/invisible watermarking scheme is done to prevent the privacy and preserving copyright protection of digital data using Hadamard transform based on the scaling factor of the image. The value of scaling factor depends on the control parameter. The scaling factor is calculated to embed the watermark. Depending upon the control parameter, the visible and invisible watermarking is determined. The proposed Hadamard Transform Domain Method is more robust again image/signal processing attacks. Furthermore, it also shows that the proposed method confirm the efficiency through various performance analysis and experimental results.
Medical image watermarking has become an important research area in the field of data security and confidentiality as patient's medical records are linked to open environment for further diagnosis and long term storage. Confidentiality of patient's data can be achieved by hiding Electronic Patient's Record (EPR) data in corresponding medical images, thus saving storage space and bandwidth requirement at the time of transmission. However, medical images require extreme care when embedding additional data within them because the additional information must not affect the image quality and readability. This paper makes a review of twenty five different watermarking algorithms for medical images in terms of patient information hiding scheme as well as to protect medical images from any unauthorized access. The objective of this paper is to conduct a research on medical image applications and advantages and also, discuss the performance analysis of described medical image watermarking methods in terms of PSNR (Peak Signal to Noise Ratio) and MSE (Mean Square Error).
Recently, there has been many researches on the fundus image for the detection of abnormality. Diabetic Retinopathy (DR) is the damage of retina caused by complication of diabetes, which results in complete vision loss. Macula is responsible for the pinpoint vision. Diabetic Macular Edema (DME) is the major problem for the diabetic patients. Several techniques have been reported about an automated solution for the diabetic macular edema detection. This paper outlines the various methods for the detection of macular edema. The normal retinal images are trained with different classifiers for the classification of abnormality. Our survey describes the different classifiers and algorithms to identify the normal and abnormal cases from the fundus images. It motivates further for future development.