Sachin D. Ruikar

Wavelet Based Image Denoising Technique

This paper proposes different approaches of wavelet based image denoising methods. The search for efficient image denoising methods is still a valid challenge at the crossing of functional analysis and statistics. In spite of the sophistication of the recently proposed methods, most algorithms have not yet attained a desirable level of applicability. Wavelet algorithms are useful tool for signal processing such as image compression and denoising. Multi wavelets can be considered as an extension of scalar wavelets. The main aim is to modify the wavelet coefficients in the new basis, the noise can be removed from the data. In this paper, we extend the existing technique and providing a comprehensive evaluation of the proposed method. Results based on different noise, such as Gaussian, Poissons, Salt and Pepper, and Speckle performed in this paper. A signal to noise ratio as a measure of the quality of denoising was preferred.

Image denoising using wavelet transform

An image is often corrupted by noise in its acquisition and transmission. Removing noise from the original image is still a challenging problem for researchers. In this work new approach of threshold function developed for image denoising algorithms. It uses wavelet transform in connection with threshold functions for removing noise. Universal, Visu Shrink, Sure Shrink and Bayes Shrink, normal shrink are compared with our threshold function, it improves the SNR efficiently.

Selection of wavelet for satellite image compression using picture quality measures

Satellite Images are major resource for various earth scientists, geologist and metrologies for better perceptive of earths environment and conditions. The increasing availability of satellite images has raised the need for compression of satellite image without significant loss of perceptual image. The Discrete Wavelet Transform (DWT) offer the optimal results for image compression. The purpose of this paper is to selection of wavelet by comparing various wavelet functions like Haar, Daubechies, Symlets, Coiflets, Biorthogonal, Reverse-Biorthogonal and Discrete Meyer wavelet for satellite image compression. The fine pick of wavelet function aids in improving the quality of image. The compressed image performance is analyzed by using picture quality measures. The picture quality measures assist in selection of most optimized wavelet function. This paper will put forward a decent orientation for the application designers and scientists to opt for the worthy wavelet function for their purpose.

Image demosaicking by nonlocal adaptive thresholding

Single sensor digital color cameras capture only one of the three primary colors at each pixel and full color image is formed by interpolating all other missing color samples at each pixel. This process is color demosaicking. Most demosaicking algorithms assume the existence of high local spectral redundancy in estimating the missing color samples. However, for images with sharp color transitions and high color saturation, such an assumption may be invalid and visually unpleasant demosaicking errors will occur. In this paper the image non-local redundancy is used to improve the local color reproduction result. For that First, multiple local directional estimates of a missing color sample are computed and fused according to local gradients. Then nonlocal pixels similar to the estimated pixel are searched to enhance the local estimate. For that an adaptive thresholding method rather than the commonly used nonlocal means filtering is implemented to improve the local estimate. Results demonstrate that the local directional interpolation and nonlocal adaptive thresholding (LDI-NAT) method outperforms than other CDM methods in reconstructing the edges and reducing color interpolation artifacts, leading to higher visual quality of reproduced color images.

Text detection and recognition in natural scene images

Text detection in natural scenes is an important but challenging problem because of variations in the text fonts, size, line orientation, complex background in image and non-uniform illuminations. To overcome these problems, effective features for text image recognition are used.In this paper, a text region detector is designed by using a widely used feature descriptor, histogram of oriented gradients (HOG). Local binarization is applied to segment connected components. For text extraction, parameters like normalized height width ratio and compactness are taken into account to filter out text and non-text components. Text recognition is implemented using zone centroid and image centroid based distance metric feature extraction system.

Super-resolution of face image extracted from a video sequence

This paper describes a technique to obtain a high resolution image from a given video sequence. The images obtained from inexpensive cameras are generally of low-quality and low-resolution and feeding those images to facial analysis systems generate undesirable outputs. The approach is to implement learning-based super-resolution algorithm on the low-resolution images to obtain high-resolution output. All the images extracted from the video are not useable in super-resolution algorithm. Therefore face quality assessment using facial feature extraction is utilized to discard the unwanted face images. Based on the quality score, it summarizes the input video sequence into a single best quality frontal face image. The employed super-resolution algorithm is applied on the best image resulting in an improved and enhanced high-quality, high-resolution image.

Image quality improvement in computed tomography using anisotropic diffusion

This paper presents the effect of noise reduction filter on computed tomography (CT) images. In CT examinations, a high radiation dose results in high-quality images, but unfortunately, as the radiation increases, the associated risk of cancer also increases. Especially in paediatric applications it is essential to maintain low radiation dose. Anisotropic diffusion is Selective and nonlinear filtering technique which filters an image within the object boundaries & not across the edge orientation. This technique is used to improve an image quality and allow the use of a low-dose CT protocol.

Image Denoising using Neighbors Variation with Wavelet

The image gets corrupted by Additive White Gaussian Noise during the process of acquisition, transmission, storage and retrieval. Denoising refers to suppressing the noise while retaining the edges and other important detailed structures as much as possible. This paper presents a general structure of the recovery of images using a combination of variation methods and wavelet analysis. The variation formulation of the problem allows us to build the properties of the recovered signal directly into the analytical machinery. The efficient wavelet representation allows us to capture and preserve sharp features in the signal while it evolves in accordance with the variation laws. We propose the three different variation model for removing noise as Horizontal, vertical and Cluster. Horizontal and Vertical variation model obtained the threshold at each decomposed level of Wavelet. Cluster variation model moving mask in different wavelet sub band. This proposed scheme has better PSNR as compared to other existing technique. General Terms Image Processing