International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (E-ISSN 2250-2459, Scopus Indexed, ISO 9001:2008 Certified Journal, Volume 13, Issue 01, January 2023) Manuscript Received: 22 November 2022, Received in Revised form: 27 December 2022, Accepted: 02 January 2023 DOI: 10.46338/ijetae0123_04 28 Tomato Leaf Disease Segmentation Using Clustering Method Based on FATPSO with Multi Features Syaiful Anam 1 , Indah Yanti 2 , Zuraidah Fitriah 3 , M. Hakim Akbar Maulana Assidiq 4 1,2,3,4 Mathematics Department, Brawijaya University, Veteran Street, Malang, East Java, Indonesia Abstract— Early blight is one of diseases that infects tomato leaves. This disease causes a decrease in the production of tomato plants. The early detection of this diseases is very important to maintain the tomato production. Monitoring tomato leaves health manually in large area is very time-consuming and inefficient. The drones and computer vision technology give an alternative in solving this problem. One of the important steps in detecting the tomato leaf disease based on computer vision is the segmentation area of the tomato leaf into the healthy and diseased tomato leaf. The K-means clustering offers an image segmentation method that is simple, fast and works unsupervised. However, the solutions of the K-means clustering often be trapped into the local optimum. The Particle Swarm Optimization (PSO) offers a solution of this problem. However, the performance of PSO depends on the particle velocity of the PSO, if the particle velocity is not determined precisely then the PSO will converge prematurely. Fuzzy Adaptive Turbulence Particle Swarm Optimization (FATPSO) is able to control minimum velocity the PSO particles adaptively for overcoming the premature convergence problem in PSO. The good features from image will increase the accuracy of machine learning algorithm. For this reason, these papers the tomato leaf segmentation based on the FATPSO clustering algorithm with multi features. The fitness function of FATPSO uses an objective function of K-means. The experiments use the image taken manually from garden tomatoes. The images have good quality but they have many varieties in size and color. The next research should be considered to use the image taken by drone to guarantee a robust method of image quality produced by drones. The experimental results show that the FATPSO clustering algorithm with multi features has a better performance than the PSO algorithm with multi feature in the tomato leaf disease segmentation. Keywords— Tomato Leaf Disease, Segmentation, Fuzzy Adaptive Turbulence, Particle Swarm Optimization, Multi feature. I. INTRODUCTION Tomato is a fruit that contains many nutrients that are beneficial for human health, such as vitamin, mineral, antioxidant, fibre, lycopene, carotenoids, polyphenols and beta-carotene [1-5]. Tomatoes can be consumed directly or are cooked first. Beta-carotene and lycopene in tomatoes are useful for reducing the heart attack risk [1]. Some researchers also state that lycopene is able to reduce the prostate cancer risk [4]. The carotenoids and polyphenols in tomatoes are able to avoid from cancer [5]. Tomatoes are naturally able to maintain the level of sugar in the blood which is useful for avoiding diabetes mellitus. Diabetes mellitus type 1 patients who consume tomatoes could decrease the sugar levels in the blood, Tomatoes also could decrease the sugar and fat levels of people with diabetes mellitus type 2 [6]. Tomatoes is also able to keep the eyes health because tomatoes have the beta carotene of contents. The contents of lycopene and lutein in tomato have advantages for eye disorders, for example cataracts [7]. Tomato plants are plants that are prone to diseases in warm and humid weather. One of them is Early Blight Disease, which is a disease that attacks tomato leaves. Early Blight is that results from several species of Alternaria [8]. Leaves that are attacked by Early Blight disease. A sign of Early Blight disease on tomato leaves is the appearance of black spots. This disease can cause all the leaves to fall so that the production of tomatoes decreases or crop failure. The automatic detection of this disease in large areas is an important step in preventing the decreasing of tomato production. Controlling the health of a tomato garden on wide land is a tedious job. It needs much time and is inefficient. The technology of drones and computer vision is a solution to control plant health in large areas and land that is difficult to reach. Diseased tomato leaves segmentation is an important step in controlling the health of tomato plants based on computer vision. The tomato leaves are segmented into two areas which are the healthy area and the diseased area. The K-means algorithm offers a segmentation method that is simple, fast and works without supervision, but the K-means algorithm has problem that is often stuck at the local optimum point which causes inaccurate segmentation results [9]. K-means algorithm can be represented in optimization problem.