Abstract
An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Keywords
Artificial intelligenceComputer visionCognitive neuroscience of visual object recognitionPattern recognition (psychology)Invariant (physics)3D single-object recognitionComputer scienceAffine transformationComputationSearch engine indexingFeature extractionMathematicsAlgorithm
Affiliated Institutions
Related Publications
Object Recognition using Local Affine Frames on Distinguished Regions
A novel approach to appearance based object recognition is introduced. The proposed method, based on matching of local image features, reliably recognises objects under very dif...
Local feature view clustering for 3D object recognition
There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to...
Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes
Following recent advances in detection, context modeling, and tracking, scene understanding has been the focus of renewed interest in computer vision research. This paper presen...
Affine invariant model-based object recognition
New techniques are described for model-based recognition of the objects in 3-D space. The recognition is performed from single gray-scale images taken from unknown viewpoints. T...
Object class recognition by unsupervised scale-invariant learning
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible const...
Publication Info
- Year
- 1999
- Type
- article
- Pages
- 1150-1157 vol.2
- Citations
- 15989
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
15989
OpenAlex
Cite This
David Lowe
(1999).
Object recognition from local scale-invariant features.
, 1150-1157 vol.2.
https://doi.org/10.1109/iccv.1999.790410
Identifiers
- DOI
- 10.1109/iccv.1999.790410