Lossy/Lossless Region-of-Interest Image Coding (ISR IP)
For more information, contact ISR External Relations Director
Jeff Coriale at firstname.lastname@example.org or 301.405.6604.
Nariman Farvardin, Eiji Atsumi
Researchers at the University of Maryland have developed an efficient image compression method for transmission or storage where one or more regions of interest are emphasized. The regions of interest can be selected either by the user or system that is initially encoding the image, or by the user or system that receives and decodes the image.
For example, if user A is sending a photograph of five people to user B, user A could select the face of one person in the photograph as a region of interest. The entire image would then begin to be transmitted to user B; however on user B's computer the resolution of the selected face would be improved faster than the resolution of the remaining portions of the photograph. Similarly, user B who is receiving the photograph, could identify a second face that would also be transmitted faster and with higher resolution.
Transmission times and storage requirements may be reduced because the areas of lower resolution, i.e. the areas not selected as regions of interest, may contain less data. Other applications for the invention include digital cameras and digitally reproduced motion pictures.
If you would like to license this intellectual property, have questions, would like to contact the inventors, or need more information, contact ISR External Relations Director Jeff Coriale at email@example.com or 301.405.6604.
Published June 17, 2007