Image retrieval of wood species by color, texture, and spatial information

Abstract

In this paper, we present an image retrieval method that integrates the color, textural and spatial information of images to facilitate the retrieval effect. Nine parameters are extracted based on the HSV, GLCM, LRE models, and wavelet, fractal algorithms, which include: hue, saturation, value, contrast, angular second moment, sum of variances, long run emphasis, fractal dimension, and wavelet horizontal energy proportion. Then with a maximal similarity measure, the nine parameters are used to retrieve wood species, and the results show that the retrieval effectiveness can be improved by combining these features.