Image Compression plays a very important role in image processing especially when we have to send the image on the Internet. Images are compressed so that the image can be sent on the Internet with available bandwidth of the network. But sometimes we need important region of the image rather than the whole image. So, we segregate the required region from the image. Spatial regions in images that are most important to the end user are called regions of interest (ROIs). The concept of an ROI is commonly used in medical imaging. For example, the boundaries of a tumor may be defined on an image or in a volume, for the purpose of measuring its size. In this paper we compress the ROI first with lossless compression techniques and then the image will be compressed by lossy compression techniques. After this at other end both the images will be decompressed and compared with one another and the results will be evaluated based on different parameters. ROI based compression is also termed as Intelligent Compression or Efficient Compression.
[1]
Nicole Vincent,et al.
Power Law Dependencies to Detect Regions of Interest
,
2003,
DGCI.
[2]
Antonio Torralba,et al.
Unsupervised Detection of Regions of Interest Using Iterative Link Analysis
,
2009,
NIPS.
[3]
Richard E. Ladner,et al.
Protecting regions of interest in medical images in a lossy packet network
,
2002,
SPIE Medical Imaging.
[4]
P. W. Jones,et al.
Digital Image Compression Techniques
,
1991
.
[5]
R Kikinis,et al.
Semiautomated ROI analysis in dynamic MR studies. Part I: Image analysis tools for automatic correction of organ displacements.
,
1991,
Journal of computer assisted tomography.
[6]
Sheila S. Hemami.
Image Compression—A Review
,
2002
.