Improving a Leaves Automatic Recognition Process Using PCA

Abstract

In this work we present a simulation of a recognition process with perimeter characterization of a simple plant leaves as a unique discriminating parameter. Data coding allowing for independence of leaves size and orientation may penalize performance recognition for some varieties. Border description sequences are then used, and Principal Component Analysis (PCA) is applied in order to study which is the best number of components for the classification task, implemented by means of a Support Vector Machine (SVM) System. Obtained results are satisfactory, and compared with [4] our system improves the recognition success, diminishing the variance at the same time.

Deep learning for plant identification using vein morphological patterns

“…The goal of automatization in this case is to avoid human experts to handle huge catalogs of plant species and to reduce classification time. Some works are focused on leaf shape [8][9][10][11][12][13][14], some use shape and texture [15], while others consider color and texture [16].…”

Multiscale recognition of legume varieties based on leaf venation images

“…Many works in the current literature deal with the problem of automatically identifying plants by means of foliar image analysis. One of the most common approaches consists in performing shape analysis of the leaves (Agarwal et al, 2006;Camargo Neto, Meyer, Jones, & Samal, 2006;Chaki & Parekh, 2012;Du, Wang, & Zhang, 2007;Im, Nishida, & Kunii, 1998;Solé-Casals, Travieso, Alonso, & Ferrer, 2008). Leaf color and texture can also be taken into consideration.…”

Legume Identification by Leaf Vein Images Classification

“…In the recent literature, many works have been proposed aimed at automatically analyzing leaf images in order to classify them or to perform plant image retrieval. The most common approach consists in considering the leaf shape [1,2,3,4,5,6]. Other works, additionally, take into account the color information [7,8].…”