<![CDATA[Image recognition and feature extraction of fruits using histogram methods have garnered significant attention in the fields of agriculture, food industry, and image processing. The Histogram method is an effective approach in automatically identifying unique characteristics of each fruit. Previous studies have demonstrated the success of histogram method in fruit image recognition based on color, texture, and shape. In this research, we propose the use of histogram method for fruit image feature extraction. We utilize secondary data consisting of fruit images such as apple, banana, mango, orange, papaya, melon, and watermelon, obtained from publicly available research datasets. We conduct a literature review to deepen our understanding of the histogram method and implement feature extraction steps such as mean, standard deviation, energy, entropy, and skewness. The authors developed a web-based application using Python programming language with the Django framework to perform fruit image feature extraction. This application allows users to upload fruit images, perform image pre-processing, and extract features using the histogram method. The extracted feature results are stored in a database for further use. Through this application, we successfully extract features from fruit images, such as banana, using the histogram method. The extracted feature results include mean, standard deviation, energy, entropy, and skewness. These results can be utilized in further research and training machine learning models to recognize and classify various types of fruits with high accuracy. Keywords: fruit image recognition, feature extraction, histogram method, image pre-processing, web-based application.]]>
Copyrights © 2023
