Image processing to identify damage to soybean seeds

ABSTRACT: In Brazil and worldwide, commercialization of soybeans is great importance to the economy, making their quality considered. The presence damaged soybean seeds decreases added value product. Businesses need fast effective techniques maintain quality. present research aimed identify, through image processing, damage caused seeds, namely greenish wrinkled due variations humidity temperature, where it was possible identify from images. Results obtained for indicated that red color scale most suitable selection its more significant variation compared other scales. For separation can be stated find a parameter with 74.3% accuracy in removing medium high degrees wrinkle damage.