Efficient Image Retrieval with Jpeg2000 and Dwt- Based Downscaling

Content-based image indexing complexity often depends on image dimensions and data size. Reducing image dimensions before indexing affects the overall feature extraction and indexing complexity, as well as the retrieval performance. In this paper, the effects of Discrete Wavelet Transform (DWT) based downscaling on semantic retrieval performance are investigated via dedicated experiments. Several images are collected from various sources and experimental databases are generated by applying JPEG2000 compression and DWT-based downscaling. Certain images are queried through the databases based on their color, texture, and shape features in the retrieval performance experiments. The evaluation results show that DWT-based downscaling does not have significant impact on color and texture-based retrieval in general, while it degrades edge-based retrieval performance significantly. The results also verify that JPEG2000 compression does not affect texture and edge-based retrieval performance, although it decreases the color-based image retrieval performance.