![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextgreen.png)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextred.png)
![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextgreen.png)
![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltext_open_medium.gif)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextred.png)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltext_restricted_medium.gif)
An Image Enhancement System for Feature Recognition in Electron Magnetic Resonance Tomograms
Subscribe/Renew Journal
An image enhancement system is developed for better recognition of features of interest in electron magnetic resonance (EMR) tomograms. The system integrates background subtraction with adaptive optimal template filtering for better performance. The non zero background, caused by the accumulation of imaging agent, is initially removed by background subtraction using bilinear as well as cubic interpolation techniques. Subsequently, a local contrast around each pixel is computed using an optimal template. The size and shape of the optimal template is determined by the statistical properties around the pixel of interest. The application system is developed in C language, and its performance is evaluated using murine EMR images, acquired from a continuous wave EMR scanner. Both signal to noise ratio (SNR) and the edge preserving characteristics are used as test parameters for the evaluation of the system. The results show reliable mapping of the distribution of imaging agents in various organs and tumors of a mouse. In comparison to simple adaptive filtering techniques such as the linear least square error (LLSE) and the minimum mean square error (MMSE) methods, the system presented in this paper shows better image enhancement and greater edge preserving capability.
Keywords
Electron Magnetic Resonance Images, Adaptive Filters, Background Subtraction, Optimal Template, Signal to Noise Ratio, Feature Detection.
User
Subscription
Login to verify subscription
Font Size
Information
![](https://i-scholar.in/public/site/images/abstractview.png)
Abstract Views: 184
![](https://i-scholar.in/public/site/images/pdfview.png)
PDF Views: 3