โ Scribed by Tae-Hyeon Kim; Tai-Hoon Cho; Young Shik Moon; Sung Han Park
No coin nor oath required. For personal study only.
In this paper, efficient techniques for solder joint inspection have been described. Using three layers of ring-shaped LEDs with different illumination angles, three frames of images are sequentially obtained. From these images the regions of interest (soldered regions) are segmented, and their characteristic features including the average gray level and the percentage of highlights-referred to as 2D features -are extracted. Based on the backpropagation algorithm of neural networks, each solder joint is classified into one of the pre-defined types. If the output value is not in the confidence interval, the distribution of tilt angles -referred to as 3D features -is calculated, and the solder joint is classified based on the Bayes classifier. The second classifier requires more computation while providing more information and better performance. The choice of a combination of neural network and Bayes classifier is based on the performance evaluation of various classifiers. The proposed inspection system has been implemented and tested with various types of solder joints in SMDs. The experimental results have verified the validity of this scheme in terms of speed and recognition rate.
๐ SIMILAR VOLUMES
An underwater robotic system for visual inspection of reactor vessel internals has been developed. The Korea Electric Power Robot for Visual Test (KeproVt) consists of an underwater robot, a vision processor based measuring unit, a master control station and a servo control station. The vision proce
This paper presents a Machine Vision System developed for on-line visual pulp inspection under the critical lighting requirements of the UNE-ISO 5350-2 standard. These requirements typically result in a very low dynamic range in the electronic images due to the following: high-speed displacement of