A Pin Classification Extraction Algorithm for Non-Standard Chips Based on Curve Detection

With the continuous development of the SMT (surface mounting technology), equipment circuit boards are gradually moving towards the direction of miniaturization and precision. Surface mounting technology is playing a more critical role in manufacturing. The main task of the core mounting machine is to realize the detection and identification of different chips, to ensure that the specified chips can be mounted stably with high speed and precision. With the development of patch chips, there are more detection methods for component pins. If a specific detection method is proposed for each non-standard component, the component detection will become more complicated. To solve such problems, this paper proposes an algorithm for extracting pins of non-standard chips based on curve detection, which aims to help users to teach different types of pins of non-standard chips by curve detection and use the teaching results as template matching to detect all non-standard patch chips. By mounting experiments on non-standard component,the test speed and production stability of the proposed algorithm have reached the leading level.