Open AccessAnalisis Seleksi Citra Mirip dengan Memanfaatkan Konsep CBIR dan Algoritma Threshold
Author(s) -
Abdul Haris Rangkuti
Publication year - 2011
Publication title -
comtech/comtech
Language(s) - English
Resource type - Journals
eISSN - 2476-907X
pISSN - 2087-1244
DOI - 10.21512/comtech.v2i2.2819
Subject(s) - computer science , image retrieval , sorting , pattern recognition (psychology) , image (mathematics) , content based image retrieval , artificial intelligence , histogram , value (mathematics) , process (computing) , image histogram , mathematics , image processing , image texture , algorithm , machine learning , operating system
Content base image retrieval (CBIR) is the concept of image retrieval by comparing the existing image on the sample to that of the database (query by example). CBIR process based on color is carried out using adaptive color histogram concept, while one based on shape is performed using moment concept. Following up the process results, a sorting process is done based on a threshold value of the sample image through the utilization threshold algorithm. The image displayed is be sorted from the one that is nearly similar to the query image (example) to the resemblance of the lowest (aggregation value). The threshold value of the query image used as reference is compared with the aggregation value of the image database. If the comparison in the search for similarities by using the concept of fuzzy logic approaches 1, the comparison between the threshold value and the aggregation value is almost the same. Otherwise, if it reaches 0, the comparison results in a lot of differences.