IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Grid Fitting for Genetic Spot Array Images Containing Guide Spots
CAIP '99 Proceedings of the 8th International Conference on Computer Analysis of Images and Patterns
Digital Image Processing (3rd Edition)
Digital Image Processing (3rd Edition)
Image Analysis and Mathematical Morphology
Image Analysis and Mathematical Morphology
A Hill-Climbing Approach for Automatic Gridding of cDNA Microarray Images
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
A Deformable Grid-Matching Approach for Microarray Images
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
In this paper, a new methodological scheme for the gridding of DNA microarrays is proposed. The scheme composes of a series of processes applied sequentially. Each DNA microarray image is pre-processed to remove any noise and the center of each spot is detected using a template matching algorithm. Then, an initial gridding is automatically placed on the DNA microarray image by 'building' rectangular pyramids around the detected spots' centers. The gridlines ''move'' between the pyramids, horizontally and vertically, forming this initial grid. Furthermore, a refinement process is applied composing of a five-step approach in order to correct gridding imperfections caused by its initial placement, both in non-spot cases and in more than one spot enclosure cases. The proposed gridding scheme is applied on DNA microarray images under known transformations and on real-world DNA data. Its performance is compared against the projection pursuit method, which is often used due to its speed and simplicity, as well as against a state-of-the-art method, the Optimal Multi-level Thresholding Gridding (OMTG). According to the obtained results, the proposed gridding scheme outperforms both methods, qualitatively and quantitatively.