1 March 1992 Model-based edge position and orientation measurement using neural networks
Author Affiliations +
Abstract
This paper proposes a new model fit type edge feature measurement method. In this new method, an accurate edge model, which explains well the practical edge gray level patterns in an actually observed image, is made by considering the point spread function in the image recording process as well as the edge features, that is, edge position and orientation. This method consists of two preparation steps and a measurement step. Step 1: Gray level patterns with various edge features values are generated on an edge pixel and its surrounding pixels based on this model. Step 2: The gray levels are fed, as teaching signals, into error back propagation type neural networks with a 3-layer structure. The mapping parameters used to determine the edge features are obtained from the gray level patterns. Step 3: The edge features are calculated by feeding the gray levels in an observed image into the networks after learning. Experimental results proved that this method can determine edge position and orientation with a high accuracy of 0.07 pixels and 0.8 degree(s), respectively.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hiroshi Naruse, Hiroshi Naruse, Mitsuhiro Tateda, Mitsuhiro Tateda, Atsushi Ide, Atsushi Ide, } "Model-based edge position and orientation measurement using neural networks", Proc. SPIE 1608, Intelligent Robots and Computer Vision X: Neural, Biological, and 3-D Methods, (1 March 1992); doi: 10.1117/12.135113; https://doi.org/10.1117/12.135113
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Neural model for feature matching in stereo vision
Proceedings of SPIE (February 01 1991)
Using logic in a model-based approach to object recognition
Proceedings of SPIE (February 01 1992)
ANN-implemented robust vision model
Proceedings of SPIE (February 01 1991)
Vision as Causal Activation and Association
Proceedings of SPIE (December 11 1985)
Segmentation using models of expected structure
Proceedings of SPIE (February 01 1991)
Connectionist learning procedure for edge detector
Proceedings of SPIE (February 01 1992)

Back to Top