Ekstraksi Ciri Warna, Bentuk, dan Tekstur untuk Temu Kembali Citra Ikan

Siti Fatimah, Sony Hartono Wijaya

Fishes are the most numerous and diverse of the major vertebrate groups causing difficulties in fish image recognition. Therefore, feature extraction in content-based image retrieval is needed to obtain pattern or fish features. This research uses freshwater fish images categorized based on the family. This research started with collected fish images from Axelrod’s Mini-Atlas of Freshwater Aquarium Fishes Mini-Edition. The first step in this research is segmented fish images with expectation maximization algorithm for grouping color contained into images. Next step is image extraction method by using three image visual features (color, shape, texture). Color feature extraction with Fuzzy Color Histogram (FCH) method is used through computing the membership function using Cauchy function. Shape feature is extracted using Hough Transform Circle and Co-occurrence Matrix method is computed for texture feature extraction. Similarity value between image query and images in database is then computed based on its features (color, shape, and texture) using cosine similarity. Those features were combined with Bayesian Network Model. Average precision value on all families fish images database for color, shape, texture and bayesian network are 0.2586, 0.2589, 0.2479, 0.2639 respectively. However, they don’t significantly different.

Keywords:              fishes, feature extraction, content-based image retrieval (CBIR), fuzzy color histogram, hough transform circle, bayesian network model

Ekstraksi Ciri Warna, Bentuk, dan Tekstur untuk Deteksi Citra Hewan

Idaliana Kusumaningsih, Sony Hartono Wijaya

This paper introduces image extraction method by using three image visual features (color, shape, texture). In this research, fuzzy color histogram for color feature extraction is used through computing the membership function using Cauchy function. In fuzzy color histogram, one color may belong to two bins histogram or more with different membership functions. Then, shape feature is extracted using edge direction histogram, where each image is processed using Sobel edge detection, and then the direction is mapped into a defined bin histogram. For texture feature extraction, the process uses co-occurrence Matrix with computing the values of energy, moment, entropy, maximum probability, contrast, correlation and homogeneity. Recall and precision value resulted in this research shows that the largest average precision value is obtained from searching process using index combination (color, shape, texture) of feature extraction.

Keywords: feature extraction, fuzzy color histogram, edge direction histogram, co-occurrence matrix

Penerapan Spatial Decision Tree untuk Identifikasi Lahan Mangrove Menggunakan Algoritme C4.5

Napthalena, Imas Sukaesih Sitanggang, Sony Hartono Wijaya

Mangrove forests have a lot of benefits for life, such as beach abration protector, building material and fuel, as well as meal supplier for plankton. Therefore, mangrove forest should be protected and developed. Mangrove forests are located along tropical and subtropical beach that are influenced by tide water. East Kalimantan is one of provinces in Kalimantan that has potential coast territory for mangrove’s growth. In one region there are some districts which have larger mangrove potency than neighbor districts. For that, it is required a spatial analysis for mangrove area identification in order to be able to know description of potential region for mangrove’s growth. One of techniques in extracting knowledge in spatial database is spatial data mining.This research uses a spatial data mining method, especially spatial decision tree using C4.5 algorithm to develop a classifier to predict new data of mangrove area. This research applies the Spatial Join Index (SJI) and the complete operator to apply conventional classification technique in spatial database. The SJI is created using topological relation to find relation between two spatial objects, then the result is simplified using complete operator. The result of this research shows that classes of mangrove area are described by some attributes : slope, topography, substrat, and landuse. The classifier contains 23 rules with 60,66% accuracy.

Keywords: spatial decision tree, C4.5 algorithm, spatial join index, complete operator

Temu Kembali Informasi (Information Retrieval)

Apakah Temu Kembali Informasi itu?

Salton (1989): “Information-retrieval systems process files of records and requests for information, and identify and retrieve from the files certain records in response to the information requests. The retrieval of particular records depends on the similarity between the records and the queries, which in turn is measured by comparing the values of certain attributes to records and information requests.”

Temu Kembali Informasi mempelajari algoritma dan model untuk memperoleh informasi dari koleksi dokumen

Temu Kembali Informasi merupakan sistem untuk merepresentasikan, menyimpan, mengorganisasikan, dan memproses informasi (Beeza-Yates & Ribeiro-Neto)