Potato Worm Eye Detection Based on Morphology and Wavelet Transform

Detection of potato with worm eye is difficult in the process of damage identification and is perishable in storage and product processing, thus leading to a serious problem of food safety and economic issue. In view of the complexity of bruise detection for potatoes, a non-destructive detection algorithm has been proposed based on imaging technique in this study. The morphology is utilized to get the target sub-image that include the particles. The segmentation method combining the wavelet transform based segmentation and edge detection threshold is employed to segment visible detect components. Experimental results show that the proposed algorithm in PSNR and FC has relatively improved accuracy, the maximum reach about 61.32% and 94.46%. In addition, the relative accuracy of factor Q has an extreme improvement. This image processing is an effective potential method.