A Method to estimate Grape Phenolic Maturity based on Color Features

Abstract

The phenolic ripeness of the grape is one of the most important parameters to determine the optimal time for harvest. A recent line of studies proposes visual seed inspection by a trained expert to determine Phenolic Maturity. In this paper a innovative method to estimate the Grape Phenolic Maturity based in digital images is presented. Three classes of seed are de ned (immature, mature and overmature) by the expert (enologist) involved in the research. A robust method of segmentation was proposed. The classi cation of seeds according to their degree of maturity was performed by a Arti cial Neural Network. Descriptor used by the Neural Networks corresponds to a histogram of the occur- rence of colors in a color scale. The method as a whole proved to be simple and e ffective in the classi ffication of seeds. Therefore, it is possible to visualize the implementation of the method in real conditions due the high performance obtained.