World Congress of Computers in Agriculture and Natural Resources, Proceedings of the 2002 Conference · 2013 · 13 citations · 1 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionAutomated SortingColor AnalysisFruit QualityFruit SortingImage ClassificationPattern RecognitionAutomatic ClassificationColor ClassificationColor SaturationFruit ClassificationFruit Quality AttributesRgb Color SpaceVisual InspectionVisual Sorting
A common problem in fruit production systems is sorting and classification. A usualprocedure to carry out this task is based on human visual inspection consideringgeneral fruit attributes like color and size. Color contains important information aboutfruit status and in some cases it is decisive for fruit quality differentiation. Anadequate color classification can improve system accuracy and productivity.Large-scale utilization of automatic classification system for this purpose demands arobust color classification even under different color saturation, variations ofenvironment lighting and light reflections. This paper provides an investigation on theapplicability of color classification using an artificial neural network in the fruit-sortingdomain. Using the well-known network generalization property we investigate theapplicability of this approach to the segmentation of colored images represented bythe RGB color system. Jointly with color analysis, we also use some shape analysisto generate a robust and real time system that was tested for orange classificationaccording to a Brazilian standard and which was able to provide fruit classificationunder less restricted visual conditions.
1