Computer Vision System Applied to Classification of "Manila" Mangoes During Ripening Process
Derechos de accesoopenAccess
MetadataShow full item record
AuthorVelez-Rivera, Nayeli; Blasco, José; Chanona-Perez, Jorge; Calderon-Dominguez, Georgina; de Jesus Perea-Flores, Maria; Arzate-Vazquez, Israel; Cubero, Sergio; Farrera-Rebollo, Reynold
Cita bibliográficaVelez-Rivera, Nayeli, Blasco, J., Chanona-Perez, J., Calderon-Dominguez, Georgina, de Jesus Perea-Flores, M., Arzate-Vazquez, Israel, Cubero, Sergio, Farrera-Rebollo, Reynold (2014). Computer Vision System Applied to Classification of "Manila" Mangoes During Ripening Process. Food and Bioprocess Technology, 7(4), 1183-1194.
Mango is an important crop that is marketed on a large scale around the world. The degree of ripeness of mangoes is an important quality attribute that has traditionally been evaluated manually through their physicochemical properties and color parameters, but recent non-destructive technologies such as computer vision systems (CVS) are emerging to replace these destructive, slow, and costly methods by others that are faster and more reliable. In the present work, physicochemical properties and color parameters obtained using a CVS at laboratory level were linked to establish the ripening stages of mango cv. "Manila." Classification process involving multivariate analysis was applied with the aim of using only color parameters to estimate levels of ripeness. A set of 117 mangoes was used to estimate the ripening index (RPI) from the physicochemical properties, and another set of 39 mangoes was used to validate the classification process in mangoes harvest in a different season. The RPI was useful for establishing three phases of maturation, namely: pre-climacteric, climacteric, and senescence. These showed correspondences with the color changes evaluated in two color spaces (CIELAB and HSB). Principal component analysis was efficient in selecting the most significant variables and separating the mangoes into the three ripening stages. Multivariate discriminant analysis made it possible to obtain classification rates of 90 % by using only a*, b*, H and S color coordinates, the CIELAB system being, in general, more efficient at classification than HSB. The results obtained showed that CVS developed for the study can be used as a useful non-invasive, efficient method for the evaluation of the ripeness of mangoes.