No abstract

This paper presents application of texture analysis using gray-level co-occurrence matrix (GLCM) for segmentation of oil palm area based on WorldView-2 imagery data. Different parameters of GLCM consisting of five distance spacing and three directions will be calculated, where eight texture features will be extracted. Based on land-use categories determined in WorldView-2 image, the features for oil palm and non-oil palm will be trained and classified using support vector machine (SVM). Segmentation based on 10x10, 20x20, 40x40 and 80x80 window will be determined by using the resulting output of SVM classification. Then, the normalized difference vegetation index (NDVI) of segmentation area will be calculated. Accuracy of oil palm area segmentation will be determined. The resulting segmentation of oil palm area shows a promising result that it can be used for intention of developing automatic oil palm tree counting.

<p class="MsoNormal" style="text-align: left; margin: 0cm 0cm 0pt; layout-grid-mode: char;" align="left"><span class="text"><span style="font-family: ";Arial";,";sans-serif";; font-size: 9pt;">In this paper, an adaptive thresholding technique based on gray level co-occurrence matrix (GLCM) is presented to handle images with fuzzy boundaries. As GLCM contains information on the distribution of gray level transition frequency and edge information, it is very useful for the computation of threshold value. Here the algorithm is designed to have flexibility on the edge definition so that it can handle the object’s fuzzy boundaries. By manipulating information in the GLCM, a statistical feature is derived to act as the threshold value for the image segmentation process. The proposed method is tested with the starfruit defect images. To demonstrate the ability of the proposed method, experimental results are compared with three other thresholding techniques.</span></span><span style="font-family: ";Arial";,";sans-serif";; font-size: 9pt;"></span></p>

No abstract