Image retrieval based on chain code algorithm using color and texture features

The rapid growth of image retrieval has provided an efficient Content-Based Image Retrieval (CBIR) system to retrieve image accurately. In this paper, a precise retrieval result by exploiting color, texture and shape features is proposed. First, extract the features by color moment and (Hue, Saturation, Value (HSV)) color space as a color feature, and then get the co-occurrence matrix as well as Discrete Wavelet Transform (DWT) for a texture feature. Chain codes algorithm, specifically chain code histogram, is then applied to obtain the codes of the shape feature. Second, collect all these features and store it in the database, where each record represents one image of the dataset. Similarity process is executed to find the images that are more similar to the query image, retrieved images ranked. The dataset applied in this study is WANG that includes 10 classes with each class containing 100 images. Experimental results have revealed that the proposed method outperformed the previous studies with an average of 0.824 in term of precision.