摘要
基于DSP的柑橘形状分级技术,分别对该系统的硬件和软件部分进行介绍。硬件部分采用高性能的DSP芯片作为图像处理的核心部分,为形状检测的实时性提供了保证;软件部分介绍柑橘识别算法的基本原理,将Zernike矩作为特征参数并利用k均值聚类法进行识别,实验表明:对于正常果型、轻度果型的检测准确率很高,能满足实际检测的要求。
Orange Grading Technoly Based on DSP, including its hardware part and software part was introduced. The hardware part equipped with the high performance DSP acts as the core component of the image processing,that provides a guarantee of the realtime of the shape detection.The software part introduces the basic principle of the orange recognition arithmetic,and differentiates by Zernike moments and k-meansalgorithm.The experiments show it can meet the practical detection requirements that the high detectin accuracy of the normal fruit shape and the low-grade fruit shape.
出处
《微计算机信息》
2011年第2期128-129,71,共3页
Control & Automation
基金
基金申请人:朱莉
项目名称:基于DSP的柑橘形状分级技术
基金颁发部门:衢州科技局立项资助项目(2009Z22)
