The size measurement and defect detection of chip pins are of great significance in intelligent manufacturing activities. In order to achieve high-quality and high-precision detection of chip pin width, spacing and length, and pin defects, the author uses the HALCON vision software platform and adopts shape matching Perform detection experiments with one-dimensional measurement algorithms. First, the upper computer controls the camera to collect pictures, and uses the shape-based template matching method combined with the pyramid search algorithm to match and locate the chip. Secondly, the chip pin area is obtained by applying affine transformation. Finally, the extracted pin area is used The one-dimensional measurement algorithm realizes the size measurement and defect detection of the chip. The experimental results show that the detection time of a single image is 56ms, the measurement error is ±0.01mm, and the defect detection accuracy rate is 100%. Therefore, using machine vision online detection can not only ensure the accuracy of measurement, but also ensure the accuracy, and the requirements of high precision and real-time in the detection industry have been fully met.