|
DSpace at MIT >
Computer Science and Artificial Intelligence Lab (CSAIL) >
Artificial Intelligence Lab Publications >
AI Memos (1959 - 2004) >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1721.1/6516
|
| Title: | Recognition by Linear Combinations of Models |
| Authors: | Ullman, Shimon
Basri, Ronen |
| Issue Date: | 1-Aug-1989 |
| Series/Report no.: | AIM-1152 |
| Abstract: | Visual object recognition requires the matching of an image with a set of models stored in memory. In this paper we propose an approach to recognition in which a 3-D object is represented by the linear combination of 2-D images of the object. If M = {M1,...Mk} is the set of pictures representing a given object, and P is the 2-D image of an object to be recognized, then P is considered an instance of M if P = Eki=aiMi for some constants ai. We show that this approach handles correctly rigid 3-D transformations of objects with sharp as well as smooth boundaries, and can also handle non-rigid transformations. The paper is divided into two parts. In the first part we show that the variety of views depicting the same object under different transformations can often be expressed as the linear combinations of a small number of views. In the second part we suggest how this linear combinatino property may be used in the recognition process. |
| URI: | http://hdl.handle.net/1721.1/6516 |
| Appears in Collections: | AI Memos (1959 - 2004)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| AIM-1152.ps | | 3628Kb | PostScript | View/Open | | AIM-1152.pdf | | 2579Kb | Adobe PDF | View/Open |
|
This item is protected by original copyright
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|
