Two-stage Plant Species Recognition by Combining Local K-NN and Weighted Sparse Representation

TL;DR

This paper introduces a two-stage plant leaf recognition method combining local mean-based classification and weighted sparse representation, improving accuracy and efficiency on large-scale databases.

Contribution

It proposes a novel two-stage classification approach that leverages local geometric centers and weighted sparse coding for improved plant species recognition.

Findings

High recognition accuracy on leaf database

Reduced computational time compared to existing methods

Clear interpretability of the classification process

Abstract

In classical sparse representation based classification and weighted SRC algorithms, the test samples are sparely represented by all training samples. They emphasize the sparsity of the coding coefficients but without considering the local structure of the input data. To overcome the shortcoming, aiming at the difficult problem of plant leaf recognition on the large-scale database, a two-stage local similarity based classification learning method is proposed by combining local mean-based classification method and local WSRC. In the first stage, LMC is applied to coarsely classifying the test sample. nearest neighbors of the test sample, as a neighbor subset, is selected from each training class, then the local geometric center of each class is calculated. S candidate neighbor subsets of the test sample are determined with the first smallest distances between the test sample and each local geometric center. In the second stage, LWSRC is proposed to approximately represent the test sample through a linear weighted sum of all samples of the candidate neighbor subsets. The rationale of the proposed method is as follows: the first stage aims to eliminate the training samples that are far from the test sample and assume that these samples have no effects on the ultimate classification decision, then select the candidate neighbor subsets of the test sample. Thus the classification problem becomes simple with fewer subsets; the second stage pays more attention to those training samples of the candidate neighbor subsets in weighted representing the test sample. This is helpful to accurately represent the test sample. Experimental results on the leaf image database demonstrate that the proposed method not only has a high accuracy and low time cost, but also can be clearly interpreted.