Adaptive integrated image segmentation and object recognition
IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)Published 1 January 2000
Bir Bhanu, Jing Peng
Citations127
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A general approach to image segmentation and object recognition that can adapt the image segmentsation algorithm parameters to the changing environmental conditions is presented and the performance improvement over time is shown.
Abstract
The paper presents a general approach to image segmentation and object recognition that can adapt the image segmentation algorithm parameters to the changing environmental conditions. Segmentation parameters are represented by a team of generalized stochastic learning automata and learned using connectionist reinforcement learning techniques. The edge-border coincidence measure is first used as reinforcement for segmentation evaluation to reduce computational expenses associated with model matching during the early stage of adaptation. This measure alone, however, cannot reliably predict the outcome of object recognition. Therefore, it is used in conjunction with model matching where the matching confidence is used as a reinforcement signal to provide optimal segmentation evaluation in a closed-loop object recognition system. The adaptation alternates between global and local segmentation processes in order to achieve optimal recognition performance. Results are presented for both indoor and outdoor color images where the performance improvement over time is shown for both image segmentation and object recognition.
Keywords
Computer Science
Journal of Artificial Intelligence ResearchReinforcement Learning: A Survey
8,831 Citations1996Leslie Pack Kaelbling, Michael L. Littman +1 more
Central issues of reinforcement learning are discussed, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.
Machine LearningSimple statistical gradient-following algorithms for connectionist reinforcement learning
7,386 Citations1992Ronald J. Williams
This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units that are shown to make weight adjustments in a direction that lies along the gradient of expected reinforcement in both immediate-reinforcement tasks and certain limited forms of delayed-reInforcement tasks, and they do this without explicitly computing gradient estimates.
Elsevier eBooksDigital Picture Processing
4,622 Citations1982
The rapid rate at which the field of digital picture processing has grown in the past five years had necessitated extensive revisions and the introduction of topics not found in the original edition.
Addison-Wesley Longman Publishing Co., Inc. eBooksComputer and Robot Vision
3,948 Citations1991Robert M. Haralock, Linda G. Shapiro
This two-volume set is an authoritative, comprehensive, modern work on computer vision that covers all of the different areas of vision with a balanced and unified approach.
Robot Vision
3,632 Citations1986Berthold K. P. Horn
This book presents a coherent approach to the fast-moving field of computer vision, using a consistent notation based on a detailed understanding of the image formation process, and will provide a useful and current reference for professionals working in the fields of machine vision, image processing, and pattern recognition.
Computer Vision Graphics and Image ProcessingImage segmentation techniques
2,226 Citations1985Robert M. Haralick, Linda G. Shapiro
Computer Graphics and Image ProcessingPicture segmentation using a recursive region splitting method
459 Citations1978R. B. Ohlander, Keith Price +1 more
A general segmentation method which can be applied to many different types of scenes and the potential performance of other segmentation techniques on general scenes is discussed.
Connection ScienceFunction Optimization using Connectionist Reinforcement Learning Algorithms
297 Citations1991Ronald J. Williams, Jing Peng
One of these variants, called REINFORCE/MENT, represents a novel but principled approach to reinforcement learning in nontrivial networks which incorporates an entropy maximization strategy.
Artificial IntelligenceRobot shaping: developing autonomous agents through learning
237 Citations1994Marco Dorigo, Marco Colombetti
This paper connects both simulated and real robots to Alecsys, a parallel implementation of a learning classifier system with an extended genetic algorithm to demonstrate that classifier systems with genetic algorithms can be practically employed to develop autonomous agents.
Finding Structure in Reinforcement Learning
176 Citations1994Sebastian Thrun, Anton Schwartz
SKILLS discovers skills, which are partially defined action policies that arise in the context of multiple, related tasks, that are learned by minimizing the compactness of action policies, using a description length argument on their representation.
Computer Vision Graphics and Image ProcessingExpert systems for image processing: Knowledge-based composition of image analysis processes
134 Citations1989Takashi Matsuyama
Two methods of representing image analysis strategies are proposed: one from a software engineering viewpoint and the other from a knowledge representation viewpoint: analysis using the pyramid (multi-resolution) data structure, combination of edge-based and region-based analyses, and so on.
Genetic Learning for Adaptive Image Segmentation
110 Citations1994Bir Bhanu, Sungkee Lee
Genetic Learning for Adaptive Image Segmentation presents the first closed-loop image segmentation system that incorporates genetic and other algorithms to adapt the segmentation process to changes in image characteristics caused by variable environmental conditions.
IEEE Transactions on Pattern Analysis and Machine IntelligenceClosed-loop object recognition using reinforcement learning
108 Citations1998Jing Peng, Bir Bhanu
Creating Advice-Taking Reinforcement Learners
104 Citations2007Richard Maclin, Jude Shavlik
Machine LearningCreating advice-taking reinforcement learners
101 Citations1996Richard Maclin, Jude Shavlik
This work presents and evaluates a design that addresses this shortcoming by allowing a connectionist Q-learner to accept advice given, at any time and in a natural manner, by an external observer, and presents experimental results that indicate the method is more powerful than a naive technique for making use of advice.
IEEE Aerospace and Electronic Systems MagazineImage understanding research for automatic target recognition
97 Citations1993Bir Bhanu, Terry Jones
The authors identify several IU problems that need to be resolved in order to enhance the effectiveness of ATR-based weapon systems and conclude that technological gains in developing robust ATR systems will lead to significant advances in many other areas of applications of image understanding.
Computer Graphics and Image ProcessingRegion extraction using convergent evidence
91 Citations1979David L. Milgram
Scenes consisting of spatially compact regions which contrast with their surrounds can be segmented by extracting connected components of above-threshold values whose borders match the positions of edges, illustrating how the redundancy of different information sources aids segmentation.
IEEE Transactions on Aerospace and Electronic SystemsAdaptive image segmentation using genetic and hybrid search methods
75 Citations1995Bir Bhanu, Sungkee Lee +1 more
The multiobjective optimization demonstrates the ability of the adaptive image segmentation system to provide high quality segmentation results in a minimal number of generations.
Reading checks with multilayer graph transformer networks
56 Citations2002Y. Le Cun, Léon Bottou +1 more
A new machine learning paradigm called multilayer graph transformer network is proposed that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as input and produce graphs as output.
Pattern RecognitionRecognition of occluded objects: A cluster-structure algorithm
56 Citations1987Bir Bhanu, John Ming
This paper applies clustering methods to a new problem domain and presents a new method based on a cluster-structure approach for the recognition of 2-D partially occluded objects, which allows the identification of all parts of the model which match in the Occluded scene.
Shortest path segmentation: a method for training a neural network to recognize character strings
37 Citations2003Christopher J. C. Burges, O. Matan +6 more
A method which combines dynamic programming and a neural network recognizer for segmenting and recognizing character strings and has achieved a per-zip-code raw recognition rate of 81% on a 2368 handwritten zip-code test set.
Word normalization for on-line handwritten word recognition
32 Citations1994Yoshua Bengio, Yann LeCun
A geometrical model of the word spatial structure is fitted to the pen trajectory using the EM algorithm and the fitting process maximizes the likelihood of the trajectory given the model and a set a priors on its parameters.
IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)Delayed reinforcement learning for adaptive image segmentation and feature extraction
32 Citations1998Jing Peng, Bir Bhanu
A robust closed-loop system based on "delayed" reinforcement learning that systematically controls feedback in a multilevel vision system and shows promise in approaching a long-standing problem in the field of computer vision and pattern recognition.
Recursive region segmentation by analysis of histograms
29 Citations2005Steven A. Shafer, Takeo Kanade
Word normalization for online handwritten word recognition
23 Citations2002Yoshua Bengio, Y. Le Cun
A geometrical model of the word spatial structure is fitted to the pen trajectory using the expectation-maximisation algorithm, which maximizes the likelihood of the trajectory given the model and a set a priors on its parameters.
Defense Technical Information Center (DTIC)The Phoenix Image Segmentation System: Description and Evaluation
18 Citations1982Kenneth Laws, Shafer, Steven +2 more
This report summarizes application for which PHOENIX is suited, the history and nature of the algorithm, details of the Testbed implementation, the manner in which PH oenIX is invoked and controlled, the type of results that can be expected, and suggestions for further development.