Accession Number:

ADA295704

Title:

Computational Problems in Image Analysis, Multiple Object Recognition, and Speech Recognition

Descriptive Note:

Final rept. 1 Feb 1993-15 Jan 1995

Corporate Author:

BROWN UNIV PROVIDENCE RI

Personal Author(s):

• Gidas, Basilis

Report Date:

1995-04-13

Pagination or Media Count:

9.0

Abstract:

During the period of the grant, 2193 - 11595, we developed 1 a Bayesian framework for object detection and tracking the algorithm was successfully tested on real-data in the detection and tracking of vehicles on a highway 2 a recognition algorithm based on stochastic hierarchical, context-free-grammars type, object representation the study has required the development of feasible pruning techniques for dynamic programming 3 a new acoustic model for speech recognition based on a wavelet representation of the acoustic-signal, and nonparametric prediction techniques.

Descriptors:

• *IMAGE PROCESSING
• *PATTERN RECOGNITION
• *SPEECH RECOGNITION
• ACOUSTIC SIGNALS
• ALGORITHMS
• BAYES THEOREM
• COMPUTATIONS
• DATA MANAGEMENT
• DYNAMIC PROGRAMMING
• HEURISTIC METHODS
• IMAGE MOTION COMPENSATION
• MATHEMATICAL MODELS
• NONPARAMETRIC STATISTICS
• OPTIMIZATION
• PREDICTIONS
• STOCHASTIC PROCESSES
• TARGET DETECTION
• TARGET RECOGNITION
• TRACKING
• VEHICLES

Subject Categories:

• Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE