Name
Abstract | ||
|---|---|---|
THE GOAL OF IMAGE UNDERSTANDING BY COMPUTER IS TO IDENTIFY OBJECTS IN VIS- UAL IMAGES AND (IF NECESSARY) TO DETERMINE THEIR LOCATION AND ORIENTATION. OBJECTS ARE IDENTIFIED BY COMPARING DATA EXTRACTED FROM IMAGES TO AN A PRIORI DESCRIPTION OF THE OBJECT OR OBJECT CLASS IN MEMORY. IT IS A GENER- ALLY ACCEPTED PREMISE THAT, IN MANY DOMAINS, THE TIMELY AND APPROPRIATE USE OF KNOWLEDGE CAN SUBSTANTIALLY REDUCE THE COMPLEXITY OF MATCHING IMAGE DATA TO OBJECT DESCRIPTIONS. BECAUSE OF THE VARIETY AND SCOPE OF KNOWLEDGE RELEVANT TO DIFFERENT OBJECT CLASSES, CONTEXTS AND VIEWING CONDITIONS, BLACKBOARD ARCHITECTURES ARE WELL SUITED TO THE TASK OF SELECTING AND APPLYING THE RELEVANT KNOWLEDGE TO EACH SITUATION AS IT IS ENCOUNTERED. THIS PAPER REVIES TEN YEARS OF WORK ON THE UMASS VISIONS SYSTEM AND ITS BLACKBOARD-BASED HIGH-LEVEL COMPONINT, THE SCHEMA SYSTEM. SCHEMA COULD IN- TERPRET COMPLEX NATURAL SCENCES WHEN GIVEN CAREFULY CRAFTED KNOWLEDGE BASES DESCRIBING THE DOMAIN, BUT ITS APPLICATION IN PRACTICE WAS LIMITED BY THE PROBLEM OF MODEL (KNOWLEDGE BASE)ACQUISITION. EXPERIENCE WITH THE SCHEMA SYSTEM CONVINCED US THAT LEARNING TECHNIQUES MUST BE EMBEDDED IN VISION SYSTEMS OF THE FUTURE TO REDUCE OR ELLIMINATE THE KNOWLEDGE ENGINEERING ASPECTS OF SYSTME CONSTRUCITON. THE SCHEMA LEARNING SYSTEM (SLS) IS A SUPER VISED LEARNING SYSTEM FOR ACQUIRING KNOWLEDGE-DIRECTED OBJECT RECOGNITION (CONTROL) STRATEGIES FROM TRAINING IMAGES. |
Year | DOI | Venue |
|---|---|---|
1993 | 10.1142/S0218001493000169 | International Journal of Pattern Recognition and Artificial Intelligence |
Keywords | DocType | Volume |
object class,knowledge relevant,object descriptions,given carefuly crafted knowledge,knowledge base,schema learning system,relevant knowledge,knowledge engineering aspects,different object classes,computer vision,acquiring knowledge-directed object recognition | Journal | 7 |
Issue | Citations | PageRank |
2 | 14 | 1.18 |
References | Authors | |
7 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bruce A. Draper | 1 | 2001 | 207.57 |
| A. Hanson | 2 | 1348 | 304.11 |
| edward m riseman | 3 | 181 | 50.97 |