Journal ArticleDOI
Affinity: A relative approach to region finding
TLDR
A region growing process is described, suitable for an initial, syntactic overview of a visual scene, designed to function on scenes where nonuniform surfaces discourage absolute thresholding techniques.About:
This article is published in Computer Graphics and Image Processing.The article was published on 1976-06-01. It has received 18 citations till now. The article focuses on the topics: Region growing & Thresholding.read more
Citations
More filters
Journal ArticleDOI
Hierarchy in picture segmentation: a stepwise optimization approach
J.-M. Beaulieu,M. Goldberg +1 more
TL;DR: A segmentation algorithm based on sequential optimization which produces a hierarchical decomposition of the picture that can be viewed as a tree, where the nodes correspond to picture segments and where links between nodes indicate set inclusions.
Journal ArticleDOI
Segmenting Images Using Localized Histograms and Region Merging
TL;DR: A working system for segmenting images of complex scenes is presented that integrates techniques that have evolved out of many years of research in low-level image segmentation at the University of Massachusetts and elsewhere.
Journal ArticleDOI
Computational techniques in the visual segmentation of static scenes
TL;DR: The complexities encountered in applying segmentation techniques to color images of natural scenes involving complex textured objects are analyzed and new ways of using the techniques to overcome some of the problems are explored.
Journal ArticleDOI
Region segmentation: Signal vs semantics
Takeo Kanade,Takeo Kanade +1 more
TL;DR: A model of image understanding is presented to provide a paradigm in which the problem of region segmentation can be discussed, and the importance of exploiting the physical level of knowledge, the bridge between a picture and a scene, is emphasized.
Journal ArticleDOI
Image segmentation schema for low-level computer vision
Tetsuo Asano,Naokazu Yokoya +1 more
TL;DR: Two distinct approaches to image-segmentation are described, both of which take the form of so-called region-growing algorithms, which are based on a binary relation named relative similarity relation which reflects relative properties in an image.
References
More filters
Generating Semantic Descriptions From Drawings of Scenes With Shadows
TL;DR: This report reproduces a thesis of the same title submitted to the Department of Electrical Engineering, Massachusetts Institute of Technology, in partial fulfillment of the requirements for the degree of Doctor of Philosophy, September 1972.
Journal ArticleDOI
Scene analysis using regions
TL;DR: One of the vision projects of the Stanford Research Institute Artificial Intelligence Group is described, which uses regions as basic data and progresses by successive partitioning of the picture toward an interpretable “goal partition”, which is then explored by a heuristic decision tree.
Proceedings ArticleDOI
Decomposition of a visual scene into three-dimensional bodies
TL;DR: This work considers visual scenes composed by the optical image of a group of bodies that can be treated as a two-dimensional array of numbers, or as a function of two variables.
Journal ArticleDOI
Decision theory and artificial intelligence: I. A semantics-based region analyzer
TL;DR: Mathematical decision theory can be combined with heuristic techniques to attack Artificial Intelligence problems and Bayesian decision theory is seen to provide a mechanism for including problem dependent (semantic) information in a general system.
The Summer Vision Project
TL;DR: A hard metal cutting bit is useful both for rough cutting and for finishing, and comprises a polygonal member having parallel opposite main faces, and on at least one of the main faces a fillet that extends continuously about the edge of themain face.