Concept Of Salience Research Articles

Recognizing Partially Occluded Parts

The problem of recognizing an object from a partially occluded boundary image is considered, and the concept of saliency of a boundary segment is introduced. Saliency measures the extent to which the boundary segment distinguishes the object to which it belongs from other objects which might be present. An algorithm is presented which optimally determines the saliency of boundary segments of one object with respect to those of a set of other objects. An efficient template matching algorithm using templates weighted by boundary segment saliency is then presented and employed to recognize partially occluded parts. The results of these experiments illustrate the effectiveness of the new technique.

Racial Inequality and Salience: An Examination of Blau's Theory of Social Structure

Hypotheses derived from Blau's theory of social structure are tested with his 1970 data set. Rates of interracial marriage are inversely associated with various measures of racial inequality across the largest SMSAS. Racial inequality is associated with racial salience, the predominance of ingroup relations, in the positive direction. The concept of salience is explicitly incorporated in the examination of a theoretical paradox in Blau's theory. This paper discusses and examines the relationship between racial inequality and salience-a collective preference for ingroup association. Salience is defined and used as a behavioral measure, rather than an attitudinal one, indicating the extent to which individuals are more likely to interact with individuals who are similar to themselves. Measures of macrosocial structure-in particular, race consolidation or inequality-are used to explain the variability of racial salience. Earlier findings (Blau et al.) and a theoretical paradox in Blau's theory of social structure are discussed while explicitly incorporating the concept of salience. Two complementary approaches to the study of social structure are considered and the relation between them is examined. One approach describes the network structure of role relations or social associations from a positional perspective (see Burt for a discussion of various approaches to studying network structure), and explicitly treats the distribution of positions or attributes as logically prior to social relations. The second approach is Blau's quantitative conception of macrosocial structure as the distribu

Biased networks and social structure theorems

It is shown that the part of Peter Blau's theory of social structure bearing on heterogeneity can be imbedded within the framework of biased networks, thereby clarifying conceptual aspects of the theory as well as providing a mathematical proof of the most central heterogeneity theorem for a class of networks. The key step is the postulation of a mathematical concept of salience, called an ‘inbreeding bias’ in prior work, which corresponds to Blau's fundamental axiom. In addition, there are derivations and discussions bearing on related topics in the analysis of social structure.