基于可变局部边缘模式的绿色植物物种识别

PDF下载HTML

Title:

Identification of green plant species based on varied local edge patterns

作者:

陈肖蒙, 王瑜, 肖洪兵

北京工商大学 计算机与信息工程学院, 北京 100048

Author(s):

CHEN Xiaomeng, WANG Yu, XIAO Hongbing

School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China

关键词:

可变局部边缘模式; 边缘特征提取; 植物物种识别

Keywords:

varied local edge patterns; extraction of edge feature; identification of plant species

分类号:

TP317.41

DOI:

10.11992/tis.201709024

摘要:

绿色植物物种识别在生态环境保护、中药制取、农业与园艺应用等方面有着重要的应用前景和潜在的经济价值。边缘是一种直观、简单、有效的对象识别特征，文中针对传统边缘算子方向少，尺度单一，操作不灵活等缺点，使用一种具有多尺度、多方向属性的圆形局部边缘模式算子(varied local edge pattern，VLEP)提取植物图像的边缘特征，同时考虑阈值细分的思想，在自建的绿色植物物种数据库上进行的实验结果表明，该算法不仅可以弥补传统算子由于边缘方向少、尺度单一导致丢失边缘信息的缺陷，同时可以有效用于绿色植物物种识别。

Abstract:

The identification of green plant species has the potential for important applications and economic value in many respects, such as protection of the environmental ecology and preparation of traditional Chinese medicine, as well as agricultural and horticultural applications. The edge of an object is an intuitive, simple, and effective object recognition feature. To overcome the shortcomings of traditional edge operators, such as few directions, single scale, and inflexible operation, in this paper, we propose a green-plant-species recognition algorithm based on circular local edge patterns, which has multiple scales and multiple directional features. We conducted a series of experiments to consider threshold subdivisions in the self-built green-plant-species database. The results show that the proposed algorithm effectively complements the edge information that is lost by the fewer edge directions and single scale of traditional edge operators, and can be effectively applied to identify green plant species.