An Empty Bottle Intelligent Inspector Based on Support Vector Machines and Fuzzy Theory

This text studies empty bottle intelligent inspector based machine vision instead of manual inspection. The system structure is illustrated in detail in this paper. The text also presents the method to extract features from images. After extracting feature, the fuzzy support vector machines are used as classifier. A genetic algorithm based on optimization algorithm is simultaneously proposed to confirm the parameters of the fuzzy support vector machines, ensuring that the fuzzy SVMs have good classification ability. The experiments demonstrate that using this method to inspect empty bottles, the accuracy rate may reach above 96%.