To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
An Evolvable Hardware Chip for Illumination Enhancement in Computer Vision for Surface Roughness Estimation |
|
Author |
M. Rajaram Narayanan, S.Gowri, A.Velayutham |
| Citation |
Vol. 6 No. 2 pp. 59~64 |
|
Abstract |
Machine vision has evolved to become a mainstream automation tool, enabling computers to replace human vision in high speed and precision manufacturing techniques. Images usually acquired through modern cameras may be contaminated by a variety of noise sources and decreasing intensity and in most cases the type of noise and state of lighting are also not known a priori. In this paper, the design of image operator for illumination enhancement and noise filtering using evolutionary approach is presented. The advantage of the proposed structure is that it is evolved from primitives. The evolvable hardware (EHW) configuration uses reconfigurable Xilinx Virtex2 FPGA xc4000 architecture. The developed image operator is tested for its performance by applying it on images of surfaces of machined components grabbed using vision systems with linearly decreasing intensity. The evolutionary enhanced image is then processed and a relationship between the feature of the surface image and the actual surface roughness is obtained using polynomial networks. Comparing with the stylus method, the constructed computer vision system is useful method for measuring the surface roughness with faster, lower environment noise and lower price in computer integrated manufacturing process (CIM). |
|
Keywords |
Machine Vision, Evolvable hardware, Image Enhancement, Surface Roughness. |
|
URL |
