Analysis of Tomato Ripeness by Color and Texture Using Cielab and K-Means Clustering

Abstract

Humans have limitations, including in the identification of tomatoes. With the nature of limitations, it makes it difficult for humans to identify the ripeness of tomatoes in large quan- tities. So far, the selection and determination of the quality activity of tomatoes is carried out manually, resulting in a less uniform product. Manual identification of tomato ripeness has many disadvantages caused by many factors, such as fatigue, lack of motivation, experience, proficiency and so on. This study aims to create a tomato maturity level analysis system based on color and texture using CIELAB and K-Means clustering as a method to determine tomato maturity precisely and accurately. This system displays five images, namely RGB, CIELAB, K-Means clustering, binary and grayscale images, after entering the tomato image, the image will be processed using the five images and the results of extracting characteristics from the tomato will come out. The accuracy rate of tomato ripeness has an average value of 92.70%. The benefit of this research is that it can save time in classifying tomato ripeness and make it easier to determine tomato ripeness based on color.