Translator Disclaimer
1 September 1993 Generating edge detectors from a training ensemble
Author Affiliations +
Abstract
Our objective is to automatically generate an efficient edge detector given an ensemble of training images with known edge maps. This paper shows how to construct linear machines for edge detection from such an ensemble. Linear machines categorize data vectors into N categories by maximizing N - 1 linear functions (convolutions). The detector, that derives from artificial images with step edges, is significantly different from that derived from Canny's criteria. These differences suggest a new theory for edge detectors -- optimal operators that generate a fixed width response to edges. The preliminary suboptimal results from applying our linear machine are already comparable to that of the state of the art in edge detection.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
David B. Sher and Davin Milun "Generating edge detectors from a training ensemble", Proc. SPIE 1962, Adaptive and Learning Systems II, (1 September 1993); https://doi.org/10.1117/12.150584
PROCEEDINGS
12 PAGES


SHARE
Advertisement
Advertisement
Back to Top