Accuracy of spot detection and classification plays a critical role in the analysis of ELISPOT data. Differences in staining intensities of spots and their morphological variations make it difficult developing a reliable software application. An image recognition method allowing the automatic detection and classification of round objects (spots) on ELISPOT images independently of the registration conditions was developed. The emphasis is done on objects of elliptical shape, which is typical for a wide range of spots. It can be analyzed by both monochrome and a dual-color version of our software. The method of subdivision of objects into groups is also described which is based on color attributes of spots.
Keywords: Dual-color ELISPOT; ELISPOT; Image analysis; Mathematical algorithm; Spot detection; Spot recognition.