De-blurring Cardiac SPECT Images by Maximum Likelihood Approach
Journal Title: Bonfring International Journal of Advances in Image Processing - Year 2015, Vol 5, Issue 1
Abstract
This paper presents a blind de-convolution algorithm for enhancing cardiac SPECT images by reducing the blur present in the image. The method is based on maximum likelihood estimate and in particular, the processing is done in a suitable color space. An iterative algorithm, without any prior information, is used to estimate the original image and the point spread function. Blur metric and peak signal to noise ratio are considered for performance evaluation of the algorithm. The effect of number of iterations on the quality of de-blurred image is also studied. Real medical images are used for appraising the algorithm
Authors and Affiliations
Neethu Sasi, Jayasree V. K.
Keywords
Related Articles
- EP ID EP116572
- DOI 10.9756/BIJAIP.10372
- Views 135
- Downloads 0
Image Fusion Algorithms for Medical Images-A Comparison
This paper presents a comparative study of medical image fusion algorithms along with its performance analysis. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images are used to fuse which form a contempor...
De-blurring Cardiac SPECT Images by Maximum Likelihood Approach
This paper presents a blind de-convolution algorithm for enhancing cardiac SPECT images by reducing the blur present in the image. The method is based on maximum likelihood estimate and in particular, the processin...
A Survey of MRI Segmentation Techniques for Brain Tumor Studies
Brain tumor is one of the advancing brain illness among the existing population. The causes of the condition being non-deterministic, it is found that the survival rates of people suffering from brain tumor is very less....
Altered Fingerprint Matching Using Ridge Texture and Frequency in the Unaltered Region
Fingerprint alteration is the process of changing the regularly spaced ridge structure by mechanical or chemical means to hide the identity from Automated Fingerprint Identification System. This paper presents a method f...
Mammogram Image Segmentation by Watershed Algorithm and Classification through k-NN Classifier
This paper presents a novel approach to detect the tumors in the mammogram images based on watershed algorithm. To increase the performance of the classifier, watershed algorithm combined with K-NN classifier is implemen...