Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. Computer Science and Artificial Intelligence Lab (CSAIL)
  3. Artificial Intelligence Lab Publications
  4. AI Memos (1959 - 2004)
  5. View-Based Strategies for 3D Object Recognition

View-Based Strategies for 3D Object Recognition

Thumbnail Image
Download
Name

AIM-1518.pdf

Size

1.09 MB

Format

Adobe PDF

Checksum (MD5)

5dc93163a71295c0d4da317f38cb8224

Thumbnail Image
Download
Name

AIM-1518.ps

Size

1.39 MB

Format

PostScript

Checksum (MD5)

5c5c4cb63a7e14e4076fc963f209077c

Author(s)
Sinha, Pawan
•
Poggio, Tomaso
Date Issued
April 21, 1995
Series/Report no.
AIM-1518
CBCL-106
Abstract
A persistent issue of debate in the area of 3D object recognition concerns the nature of the experientially acquired object models in the primate visual system. One prominent proposal in this regard has expounded the use of object centered models, such as representations of the objects' 3D structures in a coordinate frame independent of the viewing parameters [Marr and Nishihara, 1978]. In contrast to this is another proposal which suggests that the viewing parameters encountered during the learning phase might be inextricably linked to subsequent performance on a recognition task [Tarr and Pinker, 1989; Poggio and Edelman, 1990]. The 'object model', according to this idea, is simply a collection of the sample views encountered during training. Given that object centered recognition strategies have the attractive feature of leading to viewpoint independence, they have garnered much of the research effort in the field of computational vision. Furthermore, since human recognition performance seems remarkably robust in the face of imaging variations [Ellis et al., 1989], it has often been implicitly assumed that the visual system employs an object centered strategy. In the present study we examine this assumption more closely. Our experimental results with a class of novel 3D structures strongly suggest the use of a view-based strategy by the human visual system even when it has the opportunity of constructing and using object-centered models. In fact, for our chosen class of objects, the results seem to support a stronger claim: 3D object recognition is 2D view-based.
Subjects
3D object recognition
object representations
Persistent DSpace Link
http://hdl.handle.net/1721.1/7194
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.