Proceedings ArticleDOI
Object recognition from local scale-invariant features
David G. Lowe
- Vol. 2, pp 1150-1157
TLDR
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.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.read more
Citations
More filters
Proceedings ArticleDOI
Scene Modelling, Recognition and Tracking with Invariant Image Features
Iryna Skrypnyk,David G. Lowe +1 more
TL;DR: A complete system architecture for fully automated markerless augmented reality that constructs a sparse metric model of the real-world environment, provides interactive means for specifying the pose of a virtual object, and performs model-based camera tracking with visually pleasing augmentation results is presented.
Book ChapterDOI
PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
TL;DR: It is demonstrated that despite having six degree-of-freedom invariance and lack of training labels, PPF-FoldNet achieves state of the art results in standard benchmark datasets and outperforms its competitors when rotations and varying point densities are present.
Proceedings ArticleDOI
Selection of scale-invariant parts for object class recognition
TL;DR: The evaluation shows that local invariant descriptors are an appropriate representation for object classes such as cars, and it underlines the importance of feature selection.
Posted Content
Understanding image representations by measuring their equivariance and equivalence
Karel Lenc,Andrea Vedaldi +1 more
TL;DR: In this article, the authors investigate three key mathematical properties of representations: equivariance, invariance, and equivalence, and apply these properties to CNNs to reveal insightful aspects of their structure.
Proceedings ArticleDOI
Associating neural word embeddings with deep image representations using Fisher Vectors
TL;DR: This work is using the Fisher Vector as a sentence representation by pooling the word2vec embedding of each word in the sentence by using the new Fisher Vectors derived from HGLMMs to represent sentences.
References
More filters
Journal ArticleDOI
Color indexing
Michael J. Swain,Dana H. Ballard +1 more
TL;DR: In this paper, color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models, and they can differentiate among a large number of objects.
Journal ArticleDOI
Generalizing the hough transform to detect arbitrary shapes
TL;DR: It is shown how the boundaries of an arbitrary non-analytic shape can be used to construct a mapping between image space and Hough transform space, which makes the generalized Houghtransform a kind of universal transform which can beused to find arbitrarily complex shapes.
Journal ArticleDOI
Visual learning and recognition of 3-D objects from appearance
Hiroshi Murase,Shree K. Nayar +1 more
TL;DR: A near real-time recognition system with 20 complex objects in the database has been developed and a compact representation of object appearance is proposed that is parametrized by pose and illumination.
Journal ArticleDOI
Local grayvalue invariants for image retrieval
Cordelia Schmid,Roger Mohr +1 more
TL;DR: This paper addresses the problem of retrieving images from large image databases with a method based on local grayvalue invariants which are computed at automatically detected interest points and allows for efficient retrieval from a database of more than 1,000 images.
Journal ArticleDOI
A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry
TL;DR: A robust approach to image matching by exploiting the only available geometric constraint, namely, the epipolar constraint, is proposed and a new strategy for updating matches is developed, which only selects those matches having both high matching support and low matching ambiguity.