Automated prediction of sensory scores for color and appearance in canned black beans (Phaseolus vulgaris L.) using machine vision

Abstract

Evaluation of canning quality of beans is commonly carried out by simple visual inspection that is time-consuming, resource intensive, and biased by the experience of the panelist. Moreover, there is not a standard scale to rate visual quality traits of canned beans. In this research, a machine vision system was implemented and tested for automatic inspection of color (COL) and appearance (APP) in canned black beans. Various color and textural image features (average, standard deviation, contrast, correlation, energy, and homogeneity from red, green, blue, lightness, red/green, yellow/blue, hue, saturation and value color scales) were extracted from beans and brine images, and evaluated to predict the quality rates for COL and APP of a group of bean panelists using multivariate statistics. Sixty-nine commercial canned black bean samples from different brands and markets were used for analysis. In spite of the “fair” agreement among the sensory panelists for COL and APP, as determined by multi-rater Kappa analysis, machine vision data based on partial least squares regression model showed high predictive performance for both COL and APP with correlation coefficients of 0.937 and 0.871, and standard errors of 0.26 and 0.38, respectively. When a classification was performed based on both COL and APP traits, a support vector machine model was able to sort the samples into two sensory quality categories of “acceptable” and “unacceptable” with an accuracy of 89.7%. Using simple color and texture image data, a machine vision system showed potential for the automatic evaluation of canned black beans by COL and/or appearance as a professional visual inspection.