The new integrated color and texture based image retrieval using neuro-fuzzy approach

In this paper we introduce the new integrated color and texture based image retrieval technique using neuro-fuzzy approach for content based image retrieval. Most of the image retrieval systems are still incapable of providing retrieval result with high retrieval accuracy and less computational complexity. To address this problem, we developed color and texture based neural network-fuzzy logic approach for content based image retrieval using 2D-wavelet transform. The system performance improved by the learning and searching capability of the neural network combined with the fuzzy interpretation. This overcomes the vagueness and inconsistency due to human subjectivity. Multiresolution analysis using 2D-DWT can decompose the image into components at different scales, so that the coarest scale components carry the global approximation information while the finer scale components contain the detailed information. The empirical results show that the precision improved from 67% to 98% and average recall rate of 67% to 98% for the general purpose database size of 10000 images compared with existing approaches.