Translator Disclaimer
28 January 2004 Standards-compatible compression for automated image recognition in sensor networks and surveillance systems
Author Affiliations +
We show that the standard image compression algorithms are not suitable for compressing images in correlation pattern recognition since they aim at retaining image fidelity in terms of perceptual quality rather than preserving spectrally significant information for pattern recognition. New compression algorithms for pattern recognition are therefore developed, which are based on the modification of the standard compression algorithms to achieve higher compression ratio and simultaneously to enhance pattern recognition performance. This is done by emphasizing middle and high frequency components and discarding low frequency components according to a new developed distortion measure for compression. The operations of denoising, edge enhancement and compression can be integrated in the encoding process in the proposed compression algorithms. Simulation results show the effectiveness of the proposed compression algorithms.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mo Chen, Mark L. Fowler, and Shuqun Zhang "Standards-compatible compression for automated image recognition in sensor networks and surveillance systems", Proc. SPIE 5208, Mathematics of Data/Image Coding, Compression, and Encryption VI, with Applications, (28 January 2004);


Entropy-constrained predictive residual vector quantization
Proceedings of SPIE (December 08 1995)
Image compression by discrete cosine transformation
Proceedings of SPIE (October 09 1998)
Enhancement of transform coding by nonlinear interpolation
Proceedings of SPIE (November 01 1991)
Feedback-based quantization of color images
Proceedings of SPIE (March 23 1994)

Back to Top