Performance of Color Camera Machine Vision in Automated Furniture Rough Mill Systems
暂无分享,去创建一个
The objective of this study was to evaluate the performance of color camera machine vision for lumber processing in a furniture rough mill. The study used 134 red oak boards to compare the performance of automated gang-rip-first rough mill yield based on a prototype color camera lumber inspection system developed at Virginia Tech with both estimated optimum rough mill yield and actual measured rough mill yield. Automated yield was found to be 56.3 percent compared to 69.1 percent (optimum) and 65.6 percent (observed). The relatively low yield based on the color camera lumber scanning system was due to the fact that image processing algorithms were very sensitive and tended to identify and cut out defects that were not truly present. The natural variations in the color of clear wood of red oak suggests that other sensing techniques along with color sensing will be needed to accurately characterize those lumber features that are important in furniture rough mill processing.
[1] Daniel L. Schmoldt,et al. Machine Vision Systems for Processing Hardwood Lumber and Logs , 1992 .
[2] Daniel L. Schmoldt,et al. A Multiple Sensor Machine Vision System for Automatic Hardwood Feature Detection , 1993 .
[3] R. Bruce Anderson,et al. Computerized technique for recording board defect data , 1993 .
[4] Tai-Hoon Cho,et al. A computer vision system for analyzing images of rough hardwood lumber , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.