Study on the Classification of Spot Target and Extended Target

摘要：

In the field of machine vision, lots of calculations of target data sampled and recorded by a detector are needed to obtain the information of a target. These calculations can waste lots of time and require more complex hardware. And for different targets, a lot of time and money could be saved when a suitable algorithm is applied to implement distinct work. In this paper, to carry out the classification of targets of detectors and select the right algorithm of target detection and recognition, the rule of minimum image size of an extended target is presented. In this rule, clear definitions of a spot target and an extended target are given. Through theoretical analysis, computer simulation and experiments, the results show that this rule of minimum image dimension of an extended target is correct and feasible. The results also show that one target is called an extended target when its dimension is bigger than 5×5 and it is called spot target if is not.

关键词： Machine vision detection recognition spot target extended target rule of minimum image size of extended target

作者: Cheng-liang Ge Zhi-wei Huang

作者单位: Institute of Applied Electronics, CAEP P.O. Box 919-1012,Sichuan Mianyang 621900, China

会议类型: 国际会议

会议名称: 2010 International Conference on Image Analysis and Signal Processing(2010 图像分析与信号处理国际会议 IASP 10)

会议地点: 厦门

会议语种:英文

页码: 373-378

在线出版日期: 2010-04-12（万方平台首次上网日期，不代表论文的发表时间）