An efficient content-based image retrieval system integrating wavelet-based image sub-blocks with dominant colors and texture analysis

摘要: There is a great need of developing efficient content-based image retrieval systems (CBIR) because the availability large databases. Three new to retrieve images using color and texture features are proposed. The divided into equal sized non-overlapping tiles. discrete wavelet transform, HSV feature, cumulative histogram, dominant descriptor (DCD) Gray level co-occurrence matrix (GLCM) applied partitions. An integrated matching scheme based on Most Similar Highest Priority (MSHP) principle used compare query database images. adjacency bipartite graph formed sub-blocks in database. proposed techniques indeed outperform other schemes terms average precision recall. developed able perform scale, translation, rotation invariant between In future, we reduce semantic gap local high-level user semantics achieve higher accuracy.