Combination Independent Content Feature with Watermarking Annotation for Medical Image Retrieval

The number of medical images produced in cardiology and radiology department etc. is rising strongly. New challenges arise in efficient medical data management issues, such as information retrieval and security. A novel method of combining watermarking annotation with independent content feature (ICF) for medical image retrieval is proposed. ICF is extracted by independent component analysis (ICA) to represent medical images, and the digital watermark carrying patient' information text is imperceptibly embedded. Experimental results show that the scheme employs locally salient information from medical image, and it has good retrieval performance, and watermarking algorithm used in the scheme has robustness property to the JPEG compression.