Abstract
In this paper, a new image enhancement approach is proposed, which has the ability to improve the gridding results in DNA microarray analysis. The proposed approach is implemented as a conditional sub-block bi-histogram equalization (CSBE). This is accomplished by first, decomposing an input image into a number of m x n sub-blocks. Second, the threshold of each sub-block is determined independently. Third, the sub-block is divided into two sub-images based on the threshold. Fourth, only pixels having value greater than the threshold are histogram equalized, and the two sub-images are then recombined. The proposed method is tested on various DNA microarray images, giving excellent results, compared to existing methods.
| Original language | English |
|---|---|
| Title of host publication | IEEE International Conference on Video and Signal Based Surveillance, 2006: AVSS 2006 |
| Publisher | IEEE |
| Number of pages | 1 |
| ISBN (Print) | 0769526888 |
| Publication status | Published - 2006 |
| Event | IEEE International Conference on Video and Signal Based Surveillance - Duration: 1 Jan 2006 → … |
Conference
| Conference | IEEE International Conference on Video and Signal Based Surveillance |
|---|---|
| Period | 1/01/06 → … |
Keywords
- DNA microarrays
- gridding
- histogram equalization
- image processing