Automatic detection of molecular markers in digital images

Labeled molecular markers are an important tool in molecular biology. This work presents a method for the automatic identification of molecular markers in dot blot images. The method detects the location of markers in the image and their size. An experiment was made with 6 test images, which were used to produce an additional set of 222 images with various rotation, translation, contrast and noise levels. Over 7500 markers were identified automatically and compared with reference values obtained manually. The RMS error for the marker positioning in the original test images were between 1.1 and 3.8 pixels, which is about 1/10 of the typical radius (26 pixels). The method proposed was found to be almost insensitive to grid rotation and translation, and reasonably robust to image contrast changes and presence of noise.