19 September 1997 Systolic preprocessor for online morphologic operations
Author Affiliations +
Mathematical morphology is a powerful and widespread tool for image analysis and coding. But for large analysis neighborhoods, it becomes rapidly time consuming on general purpose machines. Many works have been done to decrease the overall complexity by splitting heavy computation tasks into several more efficient ones. Even if significant speedup factors have been achieved using dedicated architectures, the major drawback is that the number of operations required is still dependent on the considered neighborhood size. This paper deals with a systolic network for real time morphological processing since it is able to perform erosions, dilations, openings, and closings during a unique image scan. It implements a new method called 'casual recursive erosion' based on the decomposition of neighborhoods by both dilations and union sets. The resulting architecture presents a low complexity and offers a constant computation time. Reconfigurration of the application only consists in modifying a few array contents. System synthesis onto one FPGA yields very high processing rates.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Olivier Deforges, Olivier Deforges, Nicolas Normand, Nicolas Normand, } "Systolic preprocessor for online morphologic operations", Proc. SPIE 3166, Parallel and Distributed Methods for Image Processing, (19 September 1997); doi: 10.1117/12.279619; https://doi.org/10.1117/12.279619


Real-time depth processing for embedded platforms
Proceedings of SPIE (April 30 2017)
Morphological Cellular Logic Image Processor Architectures
Proceedings of SPIE (January 08 1984)
A 2-D Convolver Architecture For Real-Time Image Processing
Proceedings of SPIE (October 31 1989)
Hardware-based image processing library for Virtex FPGA
Proceedings of SPIE (October 05 2000)
Dynamic hardware video processing platform
Proceedings of SPIE (October 20 1996)

Back to Top