Thai Herb Leaf Image Recognition System (THLIRS)

Abstract

There are many kinds of Thai herb species, so it very difficult to identify them all. The objective of this research was to build a computer system that could recognize some Thai herb leaves, using a process called the Thai herb leaf image recognition system (THLIRS). The system consisted of four main components: 1) image acquisition, 2) image preprocessing, 3) recognition and 4) display of results. In the image acquisition component, the system used a digital camera to take a leaf picture with white paper as the background. A one-baht coin was photographed beside the leaf in order to provide a scale for comparison. In the image preprocessing component, the system applied several image-processing techniques to prepare a suitable image for the recognition process. In the recognition component, the system extracted 13 features from the leaf image and used a k-nearest neighbor (k-NN) algorithm in the recognition process. In the result display component, the system displayed the results of the classification. The experiment involved 32 species of Thai herbs, with more than 1,000 leaf images. The system was trained with 656 herb leaf images and was tested using 328 leaf images for a training dataset and 30 leaf images for an untrained dataset. The precision rate of the THLIRS of the training dataset was 93.29, 5.18 and 1.53% for match, mismatch and unknown, respectively. Moreover, the precision rate of the THLIRS of the untrained data set was 0, 23.33 and 76.67% for match, mismatch and unknown, respectively.