Object recognition
From Wikipedia, the free encyclopedia
 |
This article only describes one highly specialized aspect of its associated subject. Please help improve this article by adding more general information. (October 2009) |
 |
This article may contain parts which are misleading. Please help clarify this article according to any suggestions provided on the talk page. |
| Feature detection | |
|---|---|
 Output of a typical corner detection algorithm |
|
| Edge detection | |
| Canny | |
| Canny-Deriche | |
| Differential | |
| Sobel | |
| Interest point detection | |
| Corner detection | |
| Harris operator | |
| Shi and Tomasi | |
| Level curve curvature | |
| SUSAN | |
| FAST | |
| Blob detection | |
| Laplacian of Gaussian (LoG) | |
| Difference of Gaussians (DoG) | |
| Determinant of Hessian (DoH) | |
| Maximally stable extremal regions | |
| Ridge detection | |
| Affine invariant feature detection | |
| Affine shape adaptation | |
| Harris affine | |
| Hessian affine | |
| Feature description | |
| SIFT | |
| SURF | |
| GLOH | |
| LESH | |
| Scale-space | |
| Scale-space axioms | |
| Implementation details | |
| Pyramids | |
Object recognition in computer vision is the task of finding a given object in an image or video sequence. Humans recognize a multitude of objects in images with little effort, despite the fact that the image of the objects may vary somewhat in different view points, in many different sizes / scale or even when they are translated or rotated. Objects can even be recognized when they are partially obstructed from view. This task is still a challenge for computer vision systems in general.
Contents |
[edit] Approaches based on CAD-like object models
Edge detection, primal sketch, Marr, Mohan and Nevatia, Lowe, Faugeras
[edit] Recognition by parts
Binford (generalized cylinders), Biederman (geons), Dickinson, Forsyth and Ponce
[edit] Appearance-based methods
Histograms: Swain and Ballard, Schiele and Crowley, Schneiderman and Kanade, Linde and Lindeberg, Koenderink and van Doorn, Dalal and Triggs
[edit] Approaches based on interest points
[edit] Scale-invariant feature transform
David Lowe pioneered the computer vision approach to extracting and using scale-invariant SIFT features from images to perform reliable object recognition.
[edit] SURF
[edit] Bag of words representations
[edit] Other approaches
Template matching, gradient histograms, intraclass transfer learning, explicit and implicit 3D object models, global scene representations, shading, reflectance, texture, grammars, topic models, biologically inspired object recognition[1]
Window-based detection, 3D cues, context, leveraging internet data, unsupervised learning, fast indexing[2]
[edit] Applications
Object recognition methods has the following applications:
[edit] Surveys
Daniilides and Eklundh, Edelman
[edit] See also
- 3D single object recognition
- Scale-invariant feature transform (SIFT)
- SURF
- Histogram of oriented gradients
- Boosting methods for object categorization
- Bag of words model in computer vision
[edit] References
- ^ 6.870 Object Recognition and Scene Understanding
- ^ CS395T: Visual Recognition and Search
- ^ Brown, M., and Lowe, D.G., "Recognising Panoramas," ICCV, p. 1218, Ninth IEEE International Conference on Computer Vision (ICCV'03) - Volume 2, Nice,France, 2003
- ^ Li, L., Guo, B., and Shao, K., " Geometrically robust image watermarking using scale-invariant feature transform and Zernike moments," Chinese Optics Letters, Volume 5, Issue 6, pp. 332-335, 2007.
- ^ Se,S., Lowe, D.G., and Little, J.J.,"Vision-based global localization and mapping for mobile robots", IEEE Transactions on Robotics, 21, 3 (2005), pp. 364-375.
