Digital image processing algorithms are usually designed for the raw
format, that is on an uncompressed representation of the image.
Therefore prior to transforming or processing a compressed format,
decompression is applied; then, the result of the processing
application is finally re-compressed for further transfer or storage.
The change of data representation is resource-consuming in terms of
computation, time and memory usage. In the wide format printing
industry, this problem becomes an important issue: e.g. a 1 m2 input color image, scanned at 600 dpi exceeds 1.6 GB in its raw representation. However, some image processing algorithms can be performed in the compressed-domain, by applying an equivalent
operation on the compressed format.
This paper is presenting an innovative application of the halftoning processing operation by screening, to be applied on JPEG-compressed image. This compressed-domain transform is performed by computing the threshold operation of the screening algorithm in the DCT domain. This algorithm is illustrated by examples for different halftone masks. A pre-sharpening operation, applied on a JPEG-compressed low quality image is also described; it allows to de-noise and to enhance the contours of this image.