Abstract
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 different viewing conditions. First, distinguished regions of data-dependent shape are robustly detected. On these regions, local affine frames are established using several affine invariant constructions. Direct comparison of photometrically normalised colour intensities in local, geometrically aligned frames results in a matching scheme that is invariant to piecewise-affine image deformations, but still remains very discriminative. The potential of the approach is experimentally verified on COIL-100 and SOIL-47 – publicly available image databases. On SOIL-47, 100 % recognition rate is achieved for single training view per object. On COIL-100, 99.9% recognition rate is obtained for 18 training views per object. Robustness to severe occlusions is demonstrated by only a moderate decrease of recognition performance in an experiment where half of each test image is erased. 1
Keywords
Affine transformationArtificial intelligenceDiscriminative modelRobustness (evolution)Affine shape adaptationPattern recognition (psychology)Computer visionCognitive neuroscience of visual object recognitionInvariant (physics)MathematicsComputer science3D single-object recognitionMatching (statistics)Object (grammar)Affine combinationGeometryStatistics
Affiliated Institutions
Related Publications
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...
Video Google: a text retrieval approach to object matching in videos
We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a s...
Matching shapes
We present a novel approach to measuring similarity between shapes and exploit it for object recognition. In our framework, the measurement of similarity is preceded by (1) solv...
Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions
‘Invariant regions’ are image patches that automatically deform with changing viewpoint as to keep on covering identical physical parts of a scene. Such regions are then describ...
Joint induction of shape features and tree classifiers
We introduce a very large family of binary features for two-dimensional shapes. The salient ones for separating particular shapes are determined by inductive learning during the...
Publication Info
- Year
- 2002
- Type
- article
- Pages
- 9.1-9.10
- Citations
- 197
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
197
OpenAlex
Cite This
Štěpán Obdržálek,
Jiřı́ Matas
(2002).
Object Recognition using Local Affine Frames on Distinguished Regions.
, 9.1-9.10.
https://doi.org/10.5244/c.16.9
Identifiers
- DOI
- 10.5244/c.16.9