Fuzzy fusion of image analysis attributes for quality assessment

摘要

Quality grading is done by the consumer in a fuzzy way according to his senses. Visual appearance is the main source of information and can be broken down by image analysis to attributes like size, colour, shape and abnormalities. Starting with such basic quality attributes, at the example of tomatoes a reasoning is proposed, mapping various fuzzy consumer aspects to overall quality classes. The objective is to achieve an automatic rating of fruit quality. Such a mapping of fuzzy attributes to an overall visual quality can easily be rearranged and optimised according to varying consumers expectations.