J.K. Aggarwal, J. Ghosh, D. Nair, I. Taha, A Comparative Study of Three Paradigms for Object Recognition - Bayesian Statistics, Neural Networks and Expert Systems, Advances in Image Understanding, K. Bowyer and N. Ahuja, Eds, IEEE Computer Society Press, 1996, pp. 241-262. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Perceptual Organization Approach Based On.. - Vasseur, Pegard.. (Correct)
....the color of an object, we may set Q to the set consisting of all possible colors. Then we can define the m function which assigns an evidential weight to each subset A of Q. This function is also called basic probability assignment. Thus if Q is a frame of discernment, then a function m : 2 Q [0,1] is called basic probability assignment or weight function if : m( 0 (1) and m A A ( 1 Q (2) Then m is equal to 0 for the empty set and to 1 when the evidence is complete. This quantity measures the belief that one commits exactly to A, not to the total belief that one commits to A. ....
....one commits exactly to A, not to the total belief that one commits to A. To obtain the measure of the total belief committed to A, one must add to m(A) the quantities m(B) for all proper subsets B of A : Bel(A m B B A ) 3) If Q is a frame of discernment, then a function Bel : 2 Q [0,1] is a credibility function if and only if it satisfies the following conditions : 8 Bel( 0 Bel( Q) 1 n 0 and every collection A 1 , A 2 , A n of subsets of Q, Bel(A A Bel( A n I i i I I n I 1 1 1 1 ULU I L ) 4) In the same way, the plausibility ....
J.K. Aggarwal, J. Ghosh, D. Nair, I. Taha, A Comparative Study of Three Paradigms for Object Recognition - Bayesian Statistics, Neural Networks and Expert Systems, Advances in Image Understanding, K. Bowyer and N. Ahuja, Eds, IEEE Computer Society Press, 1996, pp. 241-262.
Geometry-based Automatic Object Localization and 3-D Pose Detection - Magnor (2002) (Correct)
....hardware to achieve fast object recognition and 3 D pose estimation. 1. Introduction The vast number of algorithms developed to extract information on the existence, position, and pose of a specific object in an image reveals the importance of the problem, but also the magnitude of the challenge [12, 1]. In this work, a rather brute force object recognition technique is presented that yields reliable detection results while offering the potential to be implemented on fast, parallelprocessing graphics hardware [8, 11, 13] Given the 3 D geometry of an object, the proposed recognition scheme ....
J. Aggarwal, J. Ghosh, D. Nair, and I. Taha. A comparative study of three paradigms for object recognition - bayesian statistics, neural networks and expert systems. In Image Understanding: A Festschrift for Azriel Rosenfeld, pages 241-- 262. IEEE Computer Society Press, 1996.
Multi-Modal Human Robot Interaction for Map Generation - Ghidary, Nakata, Saito.. (2001) (2 citations) (Correct)
....Base Geometric Map Attributed Topological Map Infrared Human Detector Figure 1. Architecture of system showing detailed modules of host computer and mobile robot. into one of many a priori known object types, and determining object characteristics such as pose, is a difficult problem [10]. Due to limited success in obtaining a general and comprehensive solution to automatic object recognition it seems that human robot collaboration can provide intermediate solutions by robot sharing human s knowledge. In this paper we describe an interface for human robot interaction that ....
J. Aggarwal, J. Ghosh, D. Nair and I. Taha, "A Comparative Study of Three Paradigms for Object Recognition: Bayesian Neural Networks and Expert systems", Advances in Image Understanding, IEEE Computer Society Press, pp. 241-262, 1996
A Neuro-Symbolic Hybrid Intelligent Architecture with Applications - Ghosh, Taha (1999) Self-citation (Ghosh Taha) (Correct)
.... approaches in the learning community from the theory of neural network ensembles and modular networks [31] to multistrategy learning [26] Hybridization in a broader sense is seen in e orts to combine two or more of neural network, Bayesian, GA, fuzzy logic and knowledge based systems [25, 1, 35, 4]. The goal is again to incorporate diverse sources and forms of information and to exploit the somewhat complementary nature of di erent methodologies. The main form of hybridization of interest in this chapter involves the integration of symbolic and connectionist approaches [24, 35] 15] 6, ....
Aggarwal, J. K., Ghosh, J., Nair, D., and Taha, I. (1996). A comparative study of three paradigms for object recognition - bayesian statistics, neural networks and expert systems. In Boyer, K. and Ahuja, N., editors, Advances In Image Understanding: A Festschrift for Azriel Rosenfeld, pages 241-262. IEEE Computer Society Press.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC