发布: 2017年12月05日第7卷第23期 DOI: 10.21769/BioProtoc.2630 浏览次数: 6577
评审: Trinadh Venkata Satish TammanaAnonymous reviewer(s)
Abstract
The identification of plant species is not a trivial task, since it is carried out by experts and depends on the presence of fruits, flowers and leaves. However, fruits and flowers are not available throughout the year, while leaves are accessible most of the year. In order to assist the specialized work of species identification, methods of texture image analysis are used to extract characteristics from samples of imaged leaves and thus predict the species. Texture image analysis is a versatile and powerful technique able to extract measurements from patterns in the images. Using this technique, recent research has found a close relationship between texture and plant species (da Silva et al., 2015 and 2016). Here, we describe the procedure to extract texture features from microscopic images of leaves using Fourier (Cosgriff, 1960; Azencott, 1997; Gonzalez and Woods, 2006). It is important to highlight that other methods for texture extraction can be used as well.
This protocol is split into two parts: (A) leaf epidermal dissociation and (B) automatic method for leaf epidermal image analysis.
Background
The protocol for plant material dissociation was described by Franklin (1945) for wood; botanical anatomists have adapted the method for leaf epidermal dissociation. Dissociation methods allow the visualization of the epidermal cells as well as their attachments in a clearer way than diaphanization and epidermal imprints methods. In addition to the dissociation method described herein, there are others using Jeffrey’s solution (1:1 solution of chromic acid and nitric acid, each at 10%) or only nitric acid (Johansen, 1940), but these methods use strong acids and more hazardous to human health and the environment. Moreover, in our experience, epidermal dissociation with Franklin solution is more effective for a greater number of species.
As leaf epidermal traits have a great taxonomic value, texture analysis from epidermal images can be a suitable method for plant identification, once texture analysis is a powerful technique that allows the extraction of measurements from patterns in the images. In the study realized by (da Silva et al., 2016), three different methods were used in the process of texture feature extraction from leaf epidermal images: Fourier descriptors, corrosion-inspired texture analysis and local binary patterns; among them, Fourier descriptors were the best option, achieving higher success rate in plant species identification. A brief description of the methods for epidermal dissociation and texture feature extraction from microscopic epidermal images using Fourier descriptors has been reported in (da Silva et al., 2016).
Materials and Reagents
Equipment
Software
Procedure
文章信息
版权信息
© 2017 The Authors; exclusive licensee Bio-protocol LLC.
如何引用
da Silva, N. R., Oliveira, M. W. D. S., Filho, H. A. D. A., Pinheiro, L. F. S., Kolb, R. M. and Bruno, O. M. (2017). Automatic Leaf Epidermis Assessment Using Fourier Descriptors in Texture Images. Bio-protocol 7(23): e2630. DOI: 10.21769/BioProtoc.2630.
分类
植物科学 > 植物细胞生物学 > 细胞成像
细胞生物学 > 组织分析 > 组织成像
您对这篇实验方法有问题吗?
在此处发布您的问题,我们将邀请本文作者来回答。同时,我们会将您的问题发布到Bio-protocol Exchange,以便寻求社区成员的帮助。
提问指南
+ 问题描述
写下详细的问题描述,包括所有有助于他人回答您问题的信息(例如实验过程、条件和相关图像等)。
Share
Bluesky
X
Copy link




