Open AccessPENDETEKSIAN CITRA DAUN TANAMAN MENGGUNAKAN METODE BOX COUNTING
Author(s) -
Novita Anggraini Juwitarty,
Kosala Dwidja Purnomo,
Kiswara Agung Santoso
Publication year - 2020
Publication title -
majalah ilmiah matematika dan statistika
Language(s) - English
Resource type - Journals
eISSN - 2722-9866
pISSN - 1411-6669
DOI - 10.19184/mims.v20i1.17221
Subject(s) - box counting , fractal dimension , similarity (geometry) , fractal , dimension (graph theory) , mathematics , identification (biology) , image processing , artificial intelligence , image (mathematics) , pattern recognition (psychology) , computer science , computer vision , fractal analysis , botany , biology , combinatorics , mathematical analysis
Different types of plants make identification difficult. Therefore, we need a system that can identify the similarity of the leaves based on a reference leaf. Extraction can be done by taking one part of the plant and the most easily obtained part is the leaf part. Natural objects such as leaves have irregular shapes and are difficult to measure, but this can be overcome by using fractal dimensions. In this research, image detection of plant leaves will be carried out using the box counting method. The box counting method is a method of calculating fractal dimensions by dividing images into small boxes in various sizes. Image detection using fractal dimension values, we know which leaves the match with the reference. In this study,10 species of leave were tested, with each species 10 samples of plant leaves. Image testing of plant leaves uses a variety of r box size, namely 1/2 ,1/4 , 1/8 , 1/16 ,1/32 , 1/64 , 128which obtain an average match accuracy of 44%. Keywords: Box Counting, Fractal dimension