Building Specified Web-Searching Image Database Using Quantization-Color-Size Histogram

Users usually search images in different web image search engines by inputting a specified keyword. However, the true images, drawing images, sometimes contemporary images exist in search results. To solve this problem, this paper proposed a simple color feature by using the histogram method for building image databases. First, after removing the smaller size and clipart of images from the database, the proposed method uses color quantization and calculates the sum of continuous intervals from the quantization-color-size histogram to get the global color feature. If the image is conformed to the global feature then the image can be saved in the database. As a result, our proposed method has the high accuracy and effectively filters the web-searching results to form the desired image database.