Abstract
This paper proposes a methodology for plant analysis and identification based on extracting texture features from microscopic images of leaf epidermis. All the experiments were carried out using 32 plant species with 309 epidermal samples captured by an optical microscope coupled to a digital camera. The results of the computational methods using texture features were compared to the conventional approach, where quantitative measurements of stomatal traits (density, length and width) were manually obtained. Epidermis image classification using texture has achieved a success rate of over 96%, while success rate was around 60% for quantitative measurements taken manually. Furthermore, we verified the robustness of our method accounting for natural phenotypic plasticity of stomata, analysing samples from the same species grown in different environments. Texture methods were robust even when considering phenotypic plasticity of stomatal traits with a decrease of 20% in the success rate, as quantitative measurements proved to be fully sensitive with a decrease of 77%. Results from the comparison between the computational approach and the conventional quantitative measurements lead us to discover how computational systems are advantageous and promising in terms of solving problems related to Botany, such as species identification.
Highlights
Texture is associated to the feel of different materials to human touch
When analysing the epidermis surface, the anatomical procedures are relatively simple compared to the preparation of transversal cuts[28], as the process to obtain the leaf surface is done in less than 12 hours, and many samples can be processed at the same time[29]
The aim of this paper is to present an innovative use of microscopic images of leaf epidermis: by extracting texture features and classifying the species by analysing these characteristics
Summary
Texture is associated to the feel of different materials to human touch. Texture image analysis is based on visual interpretation of this feeling[19]. In computational analysis of plant images, assessing texture of leaf surface is related to different characteristics of the plant, e.g. presence and type of trichomas, stomata types, etc., producing different patterns that can be identified The application of such methods has been used in leaf cross-sections (analyzing internal structures) or on the leaf surface (where subsamples of the entire scanned leaf were analyzed)[13,14,15,16,17,18,21]. In order to show the importance of using computational methods to help identify plant species, the same species used in the previous experiments were classified using morphological characteristics They were obtained manually by quantitative measurements using a light photomicroscope and the AxioVision microscope software from Zeiss. To verify the robustness of plant identification methods to handle the variability of plasticity, we analyzed the texture features of leaves from the same species growing in distinct environmental conditions
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call