Abstract (EN):
The analysis of dot blot (macroarray) images is currently based on the human identification of positive/negative dots, which is a subjective and time consuming process. This paper presents a system for the automatic analysis of dot blot images, using a pre-defined grid of markers, including a number of ON and OFF controls. The geometric deformations of the input image are corrected, and the individual markers detected, both tasks fully automatically. Based on a previous training stage, the probability for each marker to be ON is established. This information is provided together with quality parameters for training, noise and classification, allowing for a fully automatic evaluation of a dot blot image.
Language:
English
Type (Professor's evaluation):
Scientific
Contact:
caridade@isec.pt; andre.marcal@fc.up.pt; tmendo@fc.up.pt; psilva@ibmc.up.pt; Portomvm@ibmc.up.pt; FTavares@ibmc.up.pt
No. of pages:
4