Abstract

Traditional approaches to document object location use a single locator that is expected to locate as many instances of the object class of interest as possible. However, if the class includes subclasses with diverse visual characteristics or is not characterized by easily computable visual features, it is difficult for the single locator to account for wide variation in object characteristics within the class. As a result, increasingly complex models of objects to be located are used. An alternative approach is to combine the decisions of multiple locators, each of which is suitable for certain image conditions. This approach utilizes a collection of simple locators that complement one another, rather than relying on one complex locator. An effective method for combining the location results is vital to the success of this approach. This thesis presents a theory of combining the results of multiple document object locators tuned to different object characteristics. The purpose of the ...

Citations

3341	Pattern Classification and Scene Analysis - Duda, Hart - 1973
3116	A tutorial on hidden Markov models and selected applications in speech recognition - Rabiner - 1989
1639	A Mathematical Theory of Evidence - Shafer - 1976
425	Neural network ensembles - Hansen, Salamon - 1990
379	Computer and Robot Vision - Haralick, Shapiro - 1992
377	Unsupervised texture segmentation using gabor filters - Jain, Farrokhnia - 1991
284	C.Y.: Several methods for combining multiple classifiers and their applications in handwritten character recognition - Xu, Krzyzak, et al. - 1992
278	The Hearsay-II Speech-Understanding System: IntegraKnowledge to Resolve Uncertainty - Hayes-Roth, Lesser, et al. - 1980
267	When networks disagree: ensemble methods for hybrid neural networks - Perrone, Cooper - 1993
255	Rule-Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project - Buchanan, Shortliffe - 1984
248	Decision Combination in Multiple Classifier Systems - Ho, Hull, et al. - 1994
174	Theory of Committees and Elections - Black - 1958
168	Hierarchical clustering schemes - Johnson
142	Person Identification Using Multiple Cues - Brunelli, Falavigna - 1995
107	A Method of Combining Multiple Experts for the Recognition of Unconstrained Handwritten Numerals - Huang, Suen - 1995
102	Blackboard Systems: The Blackboard Model of Problem Solving and the Evolution of Blackboard Architectures,” The AI Magazine - Nii - 1986
94	Combining the Results of Several Neural-Network Classifiers. Neural Networks 7: 777–781 - Rogova - 1994
81	Integrating Region Growing and Edge Detection - Pavlidis, Liow - 1990
52	Computational methods for a mathematical theory of evidence - Barnett - 1981
46	Combining Multiple Neural Networks by Fuzzy Integral for Robust Classification - Cho, Kim - 1995
38	Handwritten numerical recognition based on multiple algorithms - Kimura, Shridhar - 1991
37	A threshold selection method from gray-scale histograms - Otsu - 1978
32	The Integration of Image Segmentation Maps Using Region and Edge Information - Chu, Aggarwal - 1993
32	Low-level image segmentation: an expert system - Nazif, Levine - 1984
31	ªA Theory of Multiple Classifier Systems and Its Application to Visual Word Recognition,º - Ho - 1992
31	Fuzzy measures and fuzzy integrals – a survey - Sugeno - 1977
31	J.M.: Information fusion in computer vision using the fuzzy integral - Tahani, Keller - 1990
23	A Course in Fuzzy - Wang - 1995
19	Address Block Location on Envelopes Using Gabor Filters - Jain, Bhattacharjee - 1992
18	A theoretical analysis of the application of majority voting to pattern recognition - Lam, Krzyzak - 1994
18	Document Image Binarization: Evaluation of Algorithms - Palumbo, Swaminathan, et al. - 1986
17	A theory of classifier combination: the neural network approach - Lee, Srihari - 1995
16	A Comparison of Two Approaches for Combining the Votes of Cooperating Classifiers - Franke, Mandler - 1992
16	Evidence combination techniques for robust classification of short-duration oceanic signals - Ghosh, Deuser, et al. - 1992
16	Object recognition in visually complex environments: an architecture for locating address blocks on mail pieces - Ching-Huei, Palumbo, et al.
14	A combination of statistical and syntactical pattern recognition applied to classification of unconstrained handwritten numerals - Duerr, Haettich, et al. - 1980
14	Using generic geometric models for intelligent shape extraction - Fua, Hanson - 1987
14	Associative Switch for Combining Multiple Classifiers - Xu, Krzyzak, et al. - 1994
13	Multiple binary decision tree classifiers - Shlien - 1990
12	Multiscale document page segmentation using soft decision integration - Etemad, Doermann, et al. - 1995
12	Postal address block location in real time - Palumbo, Srihari, et al. - 1992
11	A theory of fuzzy measures: representations, the Choquet integral, and null sets - Murofushi, Sugeno - 1991
11	Why progress in machine vision is so slow - Pavlidis - 1992
10	Integration of neural networks and decision tree classifiers for automated cytology screening - Lee, Hwang, et al. - 1991
10	A multi-classifier combination strategy for the recognition of handwritten cursive words - Plessis, Sicsu, et al. - 1993
9	Preprocessing and presorting of envelope images for automatic sorting using OCR - Downton, Leedham - 1990
9	Combination of multiple classifiers with measurement values - Huang, Suen - 1993
9	Integrating Vision Modules: Stereo, shading, grouping, and line labeling - Pankanti, Jain - 1995
9	Recognizing address blocks on mail pieces: specialized tools and problem-solving architecture - Srihari, Wang, et al. - 1987
8	Fuzzy-set-based hierarchical networks for information fusion in computer vision. Neural Networks - Krishnapuram, Lee - 1992