Digital Image Processing

K. Karthika ¹, C. Akila ¹, V. Kavitha ²

Affiliations
1 Anna University of Technology, Tirunelveli, IN
2 Department of CSE, Anna University, Tirunelveli, IN

Abstract

Image restoration is the process of recovering high quality original image from the degraded version of the image. The noises in the digital images are introduced during their acquisition and transmission. The objective of this paper is to denoise the color images which are affected by the Gaussian and Impulse noise. In this paper, the fuzzy peer cluster concept is used. A fuzzy peer cluster will be defined as a group of pixels which are similar to the processing pixel. The fuzzy peer cluster for each image pixel will be determined and the Fuzzy rule is used to detect the impulse noise in each image pixel. Impulse noise in the image pixel is removed by using the Swapping Bilateral Filter. Gaussian noise in the pixel is detected by means of the suggested median value. Gaussian noise in the image is reduced by using the same Swapping Bilateral Filter.

Keywords

Fuzzy Technique, Image Noise, Image Restoration, Suggested Median, Swapping Bilateral Filter.

Full Text

     

S. Karpagalakshmi ¹, C. Akila ¹, V. Kavitha ¹

Affiliations
1 Department of CSE, Anna University of Technology, Tirunelveli, IN

Abstract

This Paper presents an appealing loom to Non Local Means (NLM) image denoising algorithm that uses Principal Component Analysis (PCA) for dimensionality reduction. This Principal Component Analysis is applied individually for the three bands namely red, green, blue of the color images crooked with a frequently occurring noise model namely the Gaussian noise. As a result of PCA, obtain the Eigen value measures on the observed data and then develop a small number of artificial data set (principal components) using Parallel Analysis that will account for most of the variance in the observed data set. The principal components can then be used as predictor or criterion variables in subsequent analysis. Consequently measure the neighborhood similarity weight for the subspace using the normalization technique. The ensuing algorithm is referred to as the Principal Neighborhood Dictionary (PND) Nonlocal Means. The performance and the computational time of the proposed method is improved by the retrieval of the significant principal components from the projected subspace for each bands and increase of subspace window size respectively. The accuracy of the proposed PND method is compared with the other state of art methods and the superior performance of the proposed image denoising method is stated in terms of the increased Peak Signal to Noise Ratio (PSNR).

Keywords

Nonlocal Means (NLM), Parallel Analysis, Principal Component Analysis, Principal Neighborhood Dictionary.

Full Text

     

R. Paul Jeba Kumar ¹, C. Akila ², R. Mercy ², M. Deepa Lakshmi ³

Affiliations
1 Anna University, Tirunelveli, IN
2 Department in CSE, Anna University, Tirunelveli, IN
3 PSNCET, Tirunelveli, IN

Abstract

This paper describes effective texture characterization techniques using wavelet packet decompositions. The proposed work presents a statistical view of the image classification problem by combining the tasks, namely feature extraction (FE) and similarity measurement (SM), into a joint modeling and classification scheme. The proposed method uses the wavelet packet energy as a feature for texture classification for a compact feature representation and better classification accuracy. It shows that incorporating the sub band grouping and selection method and Fuzzy C Means algorithm improves the feature selection and classification accuracy. Experimental results on a database of texture images indicate that the new method significantly improves Classification rates compared with traditional approaches, while it retains comparable levels of computational complexity.

Keywords

Mutual Information, SGS, DWPT, FCM.

Full Text