Leaf epidermis images for robust identification of plants

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.

Comparative Morphology of the Leaf Epidermis in Four Species of Meliaceae L. Family

“…[12] discovered that variation in leaf epidermal cell size, shape and thickness form the premise for the taxonomic position of some angiosperm families. More so, [13] revealed that the For the anatomical study of the leaf transverse sections, the principal component analysis revealed that the best descriptors that can be used for easy and correct identification are; epidermal layer, cuticle thickness, epidermal layer thickness, Mesophyll organization, shape of xylem, presence or absence of trichome and trichome type. These characters are diagnostic and can be used in separating the species.…”

Micromorphological Characterization of the Leaf and Rhizome of Agapanthus praecox subsp. praecox Willd. (Amaryllidaceae)

“…Stomata are highly characteristics of the leaf epidermis and occupy prominent position on the leaf surfaces. Da Silva et al [19] stated that combining leaf epidermal data with the quantitative stomata data (density, length, and width) can enhance the information concerning species identification. Both the abaxial and adaxial surfaces of A. praecox are characterized by anomocytic stomata which are amphistomatically distributed and are more abundant on the abaxial than the adaxial surface.…”

Utilization of foliar cuticle morphology for the identification of weedy grasses

“…Scanning electron microscopy (SEM) and light microscopy (LM) have significant implication for taxonomists to identify morphologically complex species (Da Silva et al, ; Khan, Ullah, Khan, Khan, & Rashid, ; Khan, Ul Abidin, et al, ). Reproductive features of the plants species, as well as floral characters, are considered to provide the most valuable characters to taxonomic affinities (Jones, ; Stace, ) but as the grasses do not flower for a greater part of their life cycle and studies also suggest cuticular features are of great value for the identification, systematics, and phylogenetic relationships of the taxa (Bhatia, ; Jamshed, Ullah, Khan, & Hussain, ; Khan, Ahmad, Zafar, & Ullah, ).…”