التفاصيل البيبلوغرافية
| العنوان: |
Memory-Based Recognition for 3-D Objects |
| المؤلفون: |
Randal Nelson |
| المساهمون: |
The Pennsylvania State University CiteSeerX Archives |
| المصدر: |
ftp://ftp.cs.rochester.edu/pub/u/nelson/1996_iuw_rec.ps.gz |
| سنة النشر: |
1996 |
| المجموعة: |
CiteSeerX |
| مصطلحات موضوعية: |
Key Words, Object recognition, Memory-based representations, Visual learning |
| الوصف: |
Memory-based object recognition methods work by comparing an object against many representations stored in a memory, and finding the closest match. However matches are generally made to representations of complete objects, hence such methods tend to be sensitive to clutter and occlusion and require good global segmentation for success. We describe a method that combines an associative memory with a Hough-like evidence combination technique, allowing local segmentation to be used. This resolves the clutter and occlusion sensitivity of traditional memorybased methods, without encountering the space problems that plague voting methods for high DOF problems. The method is based on the two stage use of a general purpose associative memory and semiinvariant local objects called keys. Experiments using keys based on a curve segmentation process are reported, using both polyhedral and curved objects. Key Words: Object recognition, Memory-based representations, Visual learning. 1 Introduction. |
| نوع الوثيقة: |
text |
| وصف الملف: |
application/postscript |
| اللغة: |
English |
| Relation: |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.50.7219 |
| الاتاحة: |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.50.7219 |
| Rights: |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
| رقم الانضمام: |
edsbas.82239965 |
| قاعدة البيانات: |
BASE |