Application of some valid methods in logs counting system based on digital image processing

Automatic counting system of logs was desirable since manual operating was tedious, time-consuming and with a great potential of inaccuracies. Images of the logs were produced with CCD cameras. Because the difficulties might arise due to various reasons such as the contrast quality, touching and overlapping logs, the most pivotal step was the segmentation of the object. Distance transform was adopted so that the logs´ binary transform image was changed to one rank grey image, and the conglutinate logs in the picture could be divided by erosion arithmetic. The erosion times were two-part of maximum numerical value for distance transform. The logs were counted by scanning the core points. Through the application of these techniques described in this paper, the accurate counting method of approximate circle images such as logs was realized.