I.J. Image, Graphics and Signal Processing, 2014, 7, 10-18 Published Online June 2014 in MECS (http://www.mecs-press.org/) DOI: 10.5815/ijigsp.2014.07.02 Copyright © 2014 MECS I.J. Image, Graphics and Signal Processing, 2014, 7, 10-18 Image Retrieval Based on Color, Shape, and Texture for Ornamental Leaf with Medicinal Functionality Images Kohei Arai, Indra Nugraha Abdullah, Hiroshi Okumura Graduate School of Science and Engineering, Saga University, Saga, Japan Abstract—This research is focusing on ornamental leaf with dual functionalities, which are ornamental and medicinal functionalities. However, only few people know about the medicinal functionality of this plant. In Indonesia, this plant is also easy to find because mostly cultivates in front of the house. If its medicinal function and that easiness are taken into consideration, this leaf should be an option towards the full chemical-based medicines. This image retrieval system utilizes color, shape, and texture features from leaf images. HSV-based color histogram, Zernike complex moments, and Dyadic wavelet transformation are the color, shape, and texture features extractor methods, respectively. We also implement the Bayesian automatic weighting formula instead of assignment of static weighting factor. From the results, this proposed method is very powerful from any rotation, lighting, and perspective changes. Index Terms—Image retrieval, hsv histogram, zernike moments, dyadic wavelet, bayesian weighting, ornamental leaf, medicinal leaf. I. INTRODUCTION Human has a duty to preserve the nature. One of the examples is to preserve the existence of the plant. There is a necessity cycle between human and plant. Plant produces oxygen from photosynthesis process, and human provides carbon dioxide that vital for plant. Logically, human will experience problems when number of the plant is gradually reducing. This research uses leaf from ornamental plant as a plant that need to be preserved. Ornamental leaf because of its main function as ornament certainly has sale value. Maintaining the preservation of this plant will give many benefits in many aspects to the human itself. Based on International Union for Conservation of Nature and Natural Resources, the number of identified plant species in the world which consist of Mosses (M), Ferns and Allies (FA), Gymnosperms, Flowering Plants (FP), Red and Green Algae (RGA) is about 307.674 species [1]. Fig. 1 shows the number details. Fig 1: Column charts number of identified plant species On the other side, the approximate number of unidentified species is 86.429 species. It consists of Flowering Plants with 83.400 species, Ferns and Allies with 3.000 species, Mosses with 29 species [2]. Considering the highest number possessed by Flowering Plants, identification of the plants, which include also ornamental plant, has become a challenge for us. As recognition step of unidentified species, this research is focusing on ornamental leaf that functioned as medicinal leaf. However, only few people know about its function as a treatment of the disease. In Indonesia, this plant is also easy to find because mostly cultivates in front of the house. If its medicinal function and that easiness are taken into consideration, this plant should be an initial treatment or an option towards full chemical- based medicines. Identification of leaf image is possibly done through identification of some leaf features, i.e. color, shape, and texture. Previously, most of the researchers were using shape and texture feature to identify the leaf. In 2000, Wang et.al [3] proposed leaf image retrieval using shape features. Leaf shape characterized by centroid-contour distance curve and object eccentricity functions. The eccentricity is used for rank the leaves and its best ranked result is further re-rank again using the centroid-contour distance curve. Followed by Park, Hwang, Nam [4] in 2007, they were employing curvature scale scope corner detection method to detect the leaf venation. Categorization of the selected points is managed by calculating the density of feature 0 50000 100000 150000 200000 250000 300000 FP M FA RGA Number of species