Title :
Extracting and Labeling Boundary Segments in Natural Scenes
Author_Institution :
Department of Computer and Information Science, University of Massachusetts, Amherst, MA 01003; IBM Scientific Center, Cambridge, MA 02139.
Abstract :
This paper describes a set of algorithms used to perform segmentation of natural scenes through boundary analysis. The techniques include preprocessing, differentiation using a very simple operator, relaxation using case analysis, and postprocessing. The system extracts line segments as connected sets of edges, labels them, and computes features for them such as length and confidence.
Keywords :
Algorithm design and analysis; Computer vision; Feature extraction; Image analysis; Image generation; Image processing; Image segmentation; Labeling; Layout; Pixel; Boundary analysis; case analysis; computer vision; confidence generation; image processing; labeling; relaxation; segmentation;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.1980.4766966
