Haricot bean (Phaseolus vulgaris L.) is the most widely produced and consumed legume in the world and occupies an important place in human nutrition in many regions of Africa by improving the nutritional status of many low income populations. It is well known that a significant problem with haricot bean is that it does not soften easily and remains hard even after two or more hours of cooking in boiling water. Prolonged storage, especially under high temperature (≥ 25°C) and high relative humidity (≥ 65%), conditions that predominate in tropical regions promotes this phenomenon called hard-to-cook. This hardness of beans and the concomitant need for long boiling times leads to reduced palatability and protein digestibility, waste of time and energy. Several methods have been proposed to study the hard-to-cook of bean but they are laborious, time consuming and invasive since they destroy the analyzed sample. The main objective of this work was to study hard-to-cook bean non invasively by images processing. A computer vision systems (CVS) consisting of a standard lighted box, a camera for images acquisition and images processing software was developed. Red bean images analysis based on RGB and luminance histograms determination, histogram features definition and determination was achieved. Histograms showed a left shift in variation in color of the bean during storage, proving that red bean browned during storage. Four histogram features were defined and calculated on each histogram, that is, the maximum grey level value GLVmax, the minimum grey level value GLVmin, the most representative grey level value MRGLV and the relative amount of pixels corresponding to this value Pmax. Six histograms features which varied significantly (P < 0.05) with the storage conditions, highly correlated positively (0.97 < r < 0.99) to water capacity absorption (WCA) of bean, a classical attribute of the hard-to-cook, while four histogram features which varied significantly (P < 0.05) with the storage conditions, highly correlated negatively (-0.99 < r < -0.9). The results obtained confirm that beans undergo color changes during storage, which is related to the hard-to-cook phenomenon. It demonstrates the ability of color histogram-based images processing of beans to assess this phenomenon in terms of color images attributes.
Key words: Images processing, color histogram, haricot beans, hard-to-cook.
Copyright © 2019 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0