Introduction
Thailand is one of the most important mango (Mangifera indica L.) producers and exporters in Southeast Asia. Current fruit sorting techniques in Thailand are done by hand, which is tedious and inaccurate. Therefore, there is a need to improve the efficiency and accuracy of fruit quality assessment which can meet the demands of high-value markets. Low-cost and non-destructive sensing technologies capable of sorting fruits according to their properties have a potential to fulfill the need. Computer vision system (CVS) and image processing have been applied increasingly for sorting applications in recent years. Computer vision is a technology which produces precise and meaningful descriptions of physical objects from images (BALLARD AND BROWN, 1982). Image processing is a non-destructive method which processes signals of an image and the output can be either an image or, a set of characteristics or parameters of interest related to the image. Color of mango fruits is a decisive factor for consumers’ acceptance. External defects such as anthracnose, bruises and latex stains often go undetected in hand sorting due to their delayed development until several days after initiation. Advanced methods to precisely determine these quality parameters would be useful in assuring nutritional and economic value of fruits. Studies on the application of image processing for quality inspection of Thai mangos will make a significant contribution to the implementation of new sorting technologies. This will allow fruit producing and packaging companies to increase the value of their products, enabling them to offer to their customers a “premium class”.