Content Based Image Retrieval Using Shape, Color and Texture

The increased need of content based image retrieval technique can be found in a number of different domains such as data mining, education, medical imaging, crime prevention, weather forecasting, remote sensing and management of earth resources. Here, we present the content based image retrieval, using features like texture, shape and color, using wavelets termed as WBCHIR (Wavelet Based Color Histogram Image Retrieval). The results are found to be satisfactory with retrieval efficiency of 85 % and recall of 76.2 %. the feature set used has 72 feature values derived from 4 scale& 6 orientation with mean, standard deviation and energy measures. With increase in image based searching and also increase in volume of image database information on web has been substantially exploited based on visual clues. An effective and computationally efficient algorithms has been topic of internet amongst researches. In this work an image database with more than 1000 images and having atleast 10 categories is used and tested with WBCHIR method.