Journal Article10.1109/34.55107
Partial shape recognition: a landmark-based approach
Nirwan Ansari,Edward J. Delp +1 more
137
TL;DR: A method of recognizing partially occluded objects is presented in which each object is represented by a set of landmarks and it is shown that any invariant function under a similarity transformation is a function of the sphericity.
read more
Abstract: A method of recognizing partially occluded objects is presented in which each object is represented by a set of landmarks. Given a scene consisting of partially occluded objects, a model object in the scene is hypothesized by matching the landmarks of the model with those in the scene. A measure of similarity between two landmarks is needed to perform this matching. A local shape measure, sphericity, is introduced. It is shown that any invariant function under a similarity transformation is a function of the sphericity. To match landmarks between the model and the scene, a table of compatibility is constructed. A technique, known as hopping dynamic programming, is described to guide the landmark matching through the compatibility table. The location of the model in the scene is estimated with a least-squares fit among the matched landmarks. A heuristic measure is then computed to decide if the model is in the scene. >
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Matching and retrieval of distorted and occluded shapes using dynamic programming
TL;DR: The algorithm treats noise and shape distortions by allowing matching of merged sequences of consecutive small segments in a shape with larger segments of another shape, while being invariant to translation, scale, orientation, and starting point selection.
Object representation and recognition in shape spaces
TL;DR: A shape space based approach for invariant object representation and recognition that is invariant to similarity transformations and is relatively insensitive to noise and occlusion, potentially used for 3D object recognition.
85
The roles of endstopped and curvature tuned computations in a hierarchical representation of 2D shape.
TL;DR: A model of shape-selective neurons whose shape- selectivity is achieved through intermediate layers of visual representation not previously fully explored is proposed and successfully test a biologically plausible hypothesis on how to connect early representations based on Gabor or Difference of Gaussian filters and later representations closer to object categories without the need of a learning phase.
Local search algorithms for geometric object recognition: optimal correspondence and pose
J. Ross Beveridge
- 01 Jan 1993
TL;DR: This hybrid algorithm combines the closed-form weak-perspective pose and iterative 3D pose algorithms to efficiently solve matching problems involving perspective, and permits a mobile robot to successfully update its estimated pose relative to these landmarks.
60
The Tractability of Segmentation and Scene Analysis
TL;DR: It is shown that relaxing the no range information condition also produces an NP-complete problem, and that the variational approach to segmentation, based on minimising a criterion combining the overall variance of regions and the number of regions, also gives rise to an NP -complete problem.
60
References
•Book
Aspects of multivariate statistical theory
Robb J. Muirhead
- 01 Jan 1982
TL;DR: In this paper, the authors present a set of standard tests on Covariance Matrices and Mean Vectors, and test independence between k Sets of Variables and Canonical Correlation Analysis.
Some informational aspects of visual perception.
TL;DR: Special types of lawfulness which may exist in space at a fixed time, and which seem particularly relevant to processes of visual perception are focused on.
Three-dimensional object recognition
Paul J. Besl,Ramesh Jain +1 more
TL;DR: In this paper, a precise definition of the 3D object recognition problem is proposed, and basic concepts associated with this problem are discussed, and a review of relevant literature is provided.
1.2K
On edge detection
V. Torre,Tomaso Poggio +1 more
- 01 Aug 1984
TL;DR: It is shown that numerical differentiation of images is an ill-posed problem in the sense of Hadamard, and that this part of edge detection consists of two steps, a filtering step and a differentiation step.
1K
On Edge Detection
Vincent Torre,Tomaso A. Poggio +1 more
TL;DR: It is shown that numerical differentiation of images is an ill-posed problem in the sense of Hadamard, and that this part of edge detection consists of two steps, a filtering step and a differentiation step.
920