Open AccessContent Based Image Retrieval Using Two Color Feature Extraction
Author(s) -
Fifin Ayu Mufarroha,
Devie Rosa Anamisa,
Anggi Gustiningsih Hapsani
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1569/3/032072
Subject(s) - artificial intelligence , computer science , color histogram , image retrieval , computer vision , color image , content based image retrieval , pattern recognition (psychology) , histogram , feature extraction , feature (linguistics) , automatic image annotation , image (mathematics) , image processing , linguistics , philosophy
Content Based Image Retrieval (CBIR) is a process to search for an image based on the content or features that are inside. Nowadays, many image retrieval applications have been made to meet the needs, so this application can provide convenience in terms of the introduction and search for an image. In this research, we used 10 different objects as image retrieval consists of Bicycle, Cow, Flower, Frangipani, Grape, Horse, Lovebird, Orange, Strawberry, Tree. These objects can be expressed in 10 classes. Our aim using these objects is viewed from the color of every object and the object of a different kind. From that point of view we built a CBIR system by utilizing the main features of the object (image). The main feature is the color feature. In this research, the main process is the extraction of color features with the color histogram and color moments. So in this research it will produce feature extraction by measuring the similarity in the library image. This measurement is done by calculating the closest distance using the euclidean distance method. The data library used in this research is 10 pieces of data, the test data is 50 pieces with 5 pieces for each of these classes. After testing using data and methods described above, the results of accuracy are obtained that the application of the color moments method gets better results than the color histogram method.