Communications of the ACM - Special issue on parallelism
Designing efficient algorithms for parallel computers
Designing efficient algorithms for parallel computers
Algorithmic Techniques for Computer Vision on a Fine-Grained Parallel Machine
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient histogramming on hypercube SIMD machines
Computer Vision, Graphics, and Image Processing
Object recognition by computer: the role of geometric constraints
Object recognition by computer: the role of geometric constraints
Perceptual Organization and Visual Recognition
Perceptual Organization and Visual Recognition
A Real-Time Matching System for Large Fingerprint Databases
IEEE Transactions on Pattern Analysis and Machine Intelligence
Use neural networks to determine matching order for recognizing overlapping objects
Pattern Recognition Letters
A Parallel Algorithm for Graph Matching and Its MasPar Implementation
IEEE Transactions on Parallel and Distributed Systems
Geometric Hashing: An Overview
IEEE Computational Science & Engineering
Using extended feature objects for partial similarity retrieval
The VLDB Journal — The International Journal on Very Large Data Bases
Visualizing geographic information: VisualPoints vs CartoDraw
Information Visualization
Fuzzy geometric relations to represent hierarchical spatial information
UAI'94 Proceedings of the Tenth international conference on Uncertainty in artificial intelligence
Parallel geometric hashing for robust iris indexing
Journal of Real-Time Image Processing
| Hi-index | 4.11 |
The parallelizability of geometric hashing is explored, and two algorithms are presented. Geometric hashing uses the collection of models in a preprocessing phase (executed off line) to build a hash table data structure. The data structure encodes the model information in a highly redundant, multiple-viewpoint way. During the recognition phase, when presented with a scene and extracted features, the hash table data structure indexes geometric properties of the scene features to candidate models. The first uses: parallel hypercube techniques to route information through a series of maps and building-block parallel algorithms. The second algorithm uses the Connection Machine's large memory resources and achieves parallelism through broadcast facilities from the front end. The discussion is confined to the problem of recognizing dot patterson embedded in a scene after they have undergone translation, rotation, and scale changes.