Accession Number : ADA295440

Title :   Multistrategy Learning for Image Understanding.

Descriptive Note : Final technical rept. 30 Sep 93-29 Dec 94,

Corporate Author : CALIFORNIA UNIV RIVERSIDE

Personal Author(s) : Bhanu, Bir

PDF Url : ADA295440

Report Date : 15 FEB 1995

Pagination or Media Count : 205

Abstract : Current Image Understanding (IU) algorithms and systems lack the flexibility and robustness to successfully handle complex real-world situations. Robust 3-D object recognition, in real-world applications operating under changing environmental conditions, remains one of the important but elusive goals of IU research. We believe that an innovative combination of IU and Machine Learning (ML) techniques will lead to the advancement of the IU filed in general. IU itself has come to a certain state of maturity, in that we have today a good understanding of the essential components, their functionality, and the architectural issues involve. IU processes are commonly separated into three hierarchical layers, called the low, intermediate, and high level. At each of these levels. ML techniques can be employed selectively to improve the overall recognition performance. By introducing adaptation of task parameters; maintenance of internal representations and hypotheses pertaining to the observed reality: and learning new concepts and recognition strategies. The incorporation of learning into IU algorithms and systems will results in adaptation and robustness capability since learning provides automatic knowledge acquisition and continuous improvement of recognition system performance. (AN)

Descriptors :   *IMAGE PROCESSING, *PATTERN RECOGNITION, MATHEMATICAL MODELS, ALGORITHMS, OPTIMIZATION, STRATEGY, PARAMETERS, COMPARISON, REASONING, TARGET RECOGNITION, LEARNING MACHINES, THREE DIMENSIONAL, INFRARED IMAGES, ADAPTIVE SYSTEMS, KNOWLEDGE BASED SYSTEMS, HYPOTHESES, TARGET DETECTION, HIERARCHIES, PIXELS, MULTISENSORS, MARKOV PROCESSES, IMAGE REGISTRATION, IMAGE DISSECTION.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE