Adaptive self-configuring computer vision system for quality evaluation of fresh-cut radicchio

Abstract

Abstract An innovative computer vision system (CVS) that extracts color features discriminating the quality levels occurring during fresh-cut radicchio storage in air or modified atmosphere packaging was proposed. It self-configures the parameters normally set by operators and completely automates the following steps adapting to the specific product at hand: color-chart detection, foreground extraction and color segmentation for features extraction and selection. Results proved the average value of a ⁎ over the white part and the percentage of light white with respect to the whole visible surface to be the most discriminating color features to significantly separate (P ≤ 0.05) the three desired quality levels (high, middle and poor) occurring during fresh-cut radicchio storage (whose true value was verified on the base of ammonium content and human evaluated visual quality). The proposed procedure significantly simplifies the CVS design and the optimization of its performance, limiting the subjective human intervention to the minimum. Industrial relevance The non-destructive quality control represents a valuable tool to monitor fruits and vegetables along the whole chain from production to the end-user. Increased consumers' satisfaction and reduction of waste are only two examples of benefits that can come from a frequent and consistent control of food. CVS represents the most powerful and flexible way to reach these results. The current state-of-the-art makes their design strongly related to the specific product at hand. Thresholds and features are characteristics that play a critical role in determining the final performance of the system but are generally set by designers or operators using a-priori knowledge and/or trial-and-error processes. The proposed innovative procedure allows the CVS to self-configure most of these parameters and to easily adapt to different products regardless of the number and kind of colors associated to their surface. It results of practical applications in food processing, providing a non-destructive, automatic, cheap, fast and simple technology for the quality level evaluation, whose configuration requires a reduced, less critical and less technical human intervention.