Development of automatic counting system for urediospores of wheat stripe rust based on image processing

To realize automatic counting of urediospores of Puccinia striiformis f. sp. tritici (Pst) (causal agent of wheat stripe rust), an automatic counting system for urediospores of wheat stripe rust pathogen based on image processing was developed using MATLAB GUIDE platform in combination with Local C Compiler (LCC). The system is independent of the MATLAB environment and can be run on a computer without the MATLAB software. Using this system, automatic counting of Pst urediospores in a microscopic image can be implemented via image processing technologies including image scaling, clustering segmentation, morphological modification, watershed transformation, connected region labeling, etc. Structure design of the automatic counting system, the key algorithms used in the system and realization of the main functions of the system were described in detail. Spore counting tests were conducted using microscopic digital images of Pst urediospores and the high accuracies more than 95% were obtained. The results indicated that it is feasible to count Pst urediospores automatically using the developed system based on image processing.