Subjective measurement of cosmetic defects using a Computational Intelligence approach

This paper presents a Computational Intelligence scheme to deal with subjective human inspection tasks in the industry that are subjective measurements. The scheme is used to solve two cosmetic subjective measurements tasks, classification of cosmetic defects and detection of non-uniform color regions in a translucent film. The first problem is solved with two approaches supervised and unsupervised Artificial Neural Networks. Both techniques yield the same performance, 92.35% of correct classification. Considering that a human inspector has a performance between 85% and 90%, the performance achieved is acceptable. The second problem is faced with a hybrid system based on fuzzy clustering and a Self-Organizing Map. The hybrid approach involves management of uncertainty through fuzzy theory and unsupervised training supported by the SOM. The proposed system is able to find non-uniform color regions with better resolution than a human inspector. The system also showed to be more sensitive than a simple fuzzy clustering approach.