7 December 1994 Neural nets and Hough strategies: competitors in image processing
Author Affiliations +
Proceedings Volume 2430, Optical Memory & Neural Networks '94: Optical Neural Networks; (1994) https://doi.org/10.1117/12.195586
Event: Optical Memory and Neural Networks: International Conference, 1994, Moscow, Russian Federation
Abstract
Object segmentation, recognition and localization are challenging because of the large amount of input data and because of the invariances required. We discuss strategies to overcome these problems, considering sensors, algorithms and architectures. Specifically, we address neural nets and Hough strategies. The ability of implicit learning makes neural nets interesting for industrial inspection: compared to classical methods they promise robustness against variations of the input data. Furthermore, no expert is necessary for supervision. The inherent parallelity simplifies the design of algorithms. However, the advantages are counterbalanced by a serious drawback: the high computational complexity -- if images are considered. The ability of optics, to help by its inherent parallelity is limited, because neural architectures are usually space variant and cannot simply be implemented optically. We discuss approaching these problems by feature extraction, by sparse algorithms and by space invariant architectures. A competitive strategy for object recognition and localization is based on probability tables, such as the Hough transform uses: a couple of weak but independent hypotheses can give a safe decision about the kind and the locus of an object. This method requires a learning phase prior to the working phase, as the neural strategy does. In that sense it is similar, however, the computational complexity can be much smaller. This makes it possible to segment, localize and recognize objects invariant against shift, rotation and scale.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Gerd Haeusler, Gerd Haeusler, Dieter Ritter, Dieter Ritter, } "Neural nets and Hough strategies: competitors in image processing", Proc. SPIE 2430, Optical Memory & Neural Networks '94: Optical Neural Networks, (7 December 1994); doi: 10.1117/12.195586; https://doi.org/10.1117/12.195586
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT


Back to Top