摘要: 将多传感器技术用于电子宠物“智能狗”的视觉系统,提出一种集娱乐与安全功能于一体的架构体系,阐述该系统的工作流程,介绍基于一阶差分链码图像的表示方法和句法模式识别理论,给出一种新的头部形状检测方法,仿真实验结果表明,该系统能够获得较好的性能,且具有一定市场应用价值。
关键词:
模式识别,
链码,
多传感器,
多目标识别
Abstract: The multi-sensor technique is applied into the vision system of electronic pet called electronic dog, and a system architecture is proposed, which integrates the recreation and the security capabilities. The flowchart of the system is explained. The method based on first-order difference chain code image and structural pattern recognition theory are introduced. A novel head shape detection method is given. Simulation experimental results show this system gets better performance and has the value of market application.
Key words:
pattern recognition,
chain code,
multi-sensor,
multi-target recognition
中图分类号:
王 慧;介龙梅. 基于多传感器/目标识别的电子宠物视觉系统[J]. 计算机工程, 2009, 35(11): 178-180.
WANG Hui; JIE Long-mei. Electronic Pet Vision System Based on Multi-sensor and Multi-target Recognition[J]. Computer Engineering, 2009, 35(11): 178-180.