Computer Engineering and Applications ›› 2019, Vol. 55 ›› Issue (3): 167-170.DOI: 10.3778/j.issn.1002-8331.1712-0072

Previous Articles     Next Articles

Green Plants Identification Based on Structural Local Edge Pattern

SUN Mengru, WANG Yu, XING Suxia   

  1. Beijing Key Laboratory of Big Data Technology for Food Safety, School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China
  • Online:2019-02-01 Published:2019-01-24


孙梦茹,王  瑜,邢素霞   

  1. 北京工商大学 计算机与信息工程学院 食品安全大数据技术北京市重点实验室,北京 100048

Abstract: The edge detection of plant image is a critical step of plants recognition technologies based on image analysis. Edge detection can enhance important information such as edge outline, details, etc. so that the purpose for separating the target plants from the image can be achieved. Therefore, in order to separate the target plants from the background in the recognition of the green plants, the edge features of the image are extracted by using the varied local edge pattern operator. Then the local edge characteristics are described better using the structure local edge pattern operator to code the edge features. The experimental results show that the proposed edge pattern has a better recognition rate in green plant species identification.

Key words: edge detection, varied local edge pattern, structure local edge pattern, plants identification

摘要: 植物图像的边缘检测是基于图像分析植物物种识别技术的重要环节,利用边缘检测可以增强图像中的轮廓边缘、细节等信息,达到将目标植物从图像中分离出来的目的。因此,为了在绿色植物物种识别中,将图像中的目标植物与背景分离,首先利用可变局部边缘模式算子提取植物图像的边缘特征,再通过结构化局部边缘模式对边缘特征进行编码,来刻画局部边缘。实验结果表明,提出的边缘模式思想在绿色植物物种识别上能得到更高的识别率。

关键词: 边缘检测, 可变局部边缘模式, 结构化局部边缘模式, 植物识别