Vision sensing system for early detection of Pebrine spore in silk moth

An important aspect of silkworm seed production is to ensure Pebrine disease free eggs. For that reason, the egg-laying moths are cut and their tissues are examined under microscope for presence of Pebrine spores in those tissues. If the tissues are found free of infection, then only the corresponding eggs are distributed amongst the villagers pursuing sericulture. Currently the entire process is manual, time and labor intensive. Many a time human error also creeps in leading to outbreak of Pebrine disease. This paper proposes automation of the Pebrine spore detection process by capturing photomicrographic images and classifying Pebrine spores using digital image processing technique thereby improving productivity and accuracy of this process. Captured RGB image has been enhanced by image enhancement process to get better processing result in further steps. Local threshold based segmentation technique has been applied to segment the foreground objects. The segmented foreground objects have been labeled individually by a stack-based connected-component labeling technique. Then advanced binary morphological technique based feature detection procedures have been performed to remove the unwanted noise and non-Pebrine objects and to extract various feature parameters of filtered Pebrine objects. Initially, more than 200 images have been analyzed using developed solution & the results have been validated with the human experts. Laboratory experiments found the accuracy of detection in the tune of 75%.