Image analysis – Pattern recognition – Template matching
Patent
1997-01-29
1998-08-11
Mancuso, Joseph
Image analysis
Pattern recognition
Template matching
382155, 382170, G06K 900, G06K 968
Patent
active
057938881
ABSTRACT:
A computer module is interactively trained to recognize patterns of spectral or textural features in imagery. The interactively trained module is based on techniques of knowledge-based image processing and an approach that uses interest images to provide a means of continuous feedback of module performance to the user. The user, in turn, responds by indicating where the module is making mistakes. A set of user indicated examples and counter examples form the inputs to a machine learning program called Functional Template Learning. The trained module is exportable as an independent agent to search large databases for matching patterns. Following retrieval of images having matching patterns, a user can further refine the agent's performance by indicating where mistakes have been made. The overall search tool employing the trained module is capable of prescreening and highlighting images, significantly reducing the workload of analysts attempting to detect regions or objects in imagery.
REFERENCES:
patent: 4075604 (1978-02-01), Degasperi
patent: 5222155 (1993-06-01), Delanoy et al.
patent: 5432902 (1995-07-01), Matsumoto
patent: 5638460 (1997-06-01), Nishimori et al.
Delanoy et al., Machine Learining for a Toolkit for Image Mining, 1-16.
Niblack, et al., "The QBIC Project : Querying Images by Content Using Color, Texture and Shape," Computer Science, (1993, Feb.).
"An Introduction to Multispec", developed by landgrebe and Biehl at Purdue University, School of Electrical Engineering (1995, Feb. 15). (This version was the only version available and the differences from the 1994 version are noted in Appendix C.).
Turk, et al., "Eigenfaces for Recognition, " Journal of Cognitive Neuroscience, 3(1):71-86 (1991).
Huber, H. P., and Casler, K. E., "Initial Analysis of Landsat TM Data for Elk Habitat Mapping," Int. J. Remote Sensing, 11(5):907-912 (1990).
Augusteijn, M., et al., "Performance Evaluation of Texture Measurements for Ground Cover Identification in Satellite Images by Means of a Neutral Network Classifier, " Technical Report EAS-CS-93-8, University of Colorado (1993, Oct.).
Delanoy et al., "Functional Templates and Their Application to 3-D Object Recognition," Proceeding of the 1992 International Conference of Acoustics, Speech, and Signal Processing, San Francisco, Ca (Mar. 23-26, 1992).
Delanoy et al., "Machine Intelligent Gust Front Detection, " The Lincoln Laboratory J., 6(1):187-212 (1993).
Delanoy et al., "Machine Intelligent Automatic Recognition of Critical Mobile Targets in Laser Radar Imagery," The Lincoln Laboratory J., 6(1):161-186 (1993).
Donald F. Specht, "Probabilistic Neural Networks," Neural Networks, 3:109-118 (1990).
Musavi et al., "On The Training of Radial Basis Function Classifiers," Neural Networks, 5:595-603 (1992).
Carpenter et al., "Fuzzy ART: Fast Stable Learning and Categorization of Analog Patterns by an Adaptive Resonance System," Neural Networks, 4:759-771 (1991).
Letter Soliciting Sponsors, Sep. 19 and 28, 1994 with unpublished enclosure by Delanoy et al., "Machine Learning for a Toolkit for Image Mining" Lincoln Laboratory, Massachusetts Institute of Technology, p. 1-16.
Johnson Timothy M.
Mancuso Joseph
Massachusetts Institute of Technology
LandOfFree
Machine learning apparatus and method for image searching does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Machine learning apparatus and method for image searching, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Machine learning apparatus and method for image searching will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-398230