A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to the theory of neural computation
Introduction to the theory of neural computation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Two-dimensional signal and image processing
Two-dimensional signal and image processing
Digital image processing (2nd ed.)
Digital image processing (2nd ed.)
Custom DSP design of a GSM speech coder
Journal of VLSI Signal Processing Systems
Anatomy of a Silicon Compiler
Hi-index | 0.00 |
A customized processor for real time image convolution hasbeen designed to increase the performance of an instrument forautomated cereal grain quality assessment. Image convolutionrequires an extensive amount of calculation capacity and acorresponding amount of data transfers, hard to achieve with standardprocessors in real time. Therefore, a tailored architecture with astreamlined dataflow has been developed with emphasis on a systemdesign perspective. The designed processor has a sustainedcalculation capacity of 1 GMAC/s and on-chip line buffers reducethe amount of external data transfers. Hence, the complexity of thedesigned processor has been increased to gain a lower complexity ofthe complete system. To achieve powerful and versatile filtering thesize of the programmable kernel functions have been maximized to15 × 15.