Showing papers on "Feature hashing published in 1997"

Efficient hardware hashing functions for high performance computers

Abstract: Hashing is critical for high performance computer architecture. Hashing is used extensively in hardware applications, such as page tables, for address translation. Bit extraction and exclusive ORing hashing "methods" are two commonly used hashing functions for hardware applications. There is no study of the performance of these functions and no mention anywhere of the practical performance of the hashing functions in comparison with the theoretical performance prediction of hashing schemes. In this paper, we show that, by choosing hashing functions at random from a particular class, called H/sub 3/, of hashing functions, the analytical performance of hashing can be achieved in practice on real-life data. Our results about the expected worst case performance of hashing are of special significance, as they provide evidence for earlier theoretical predictions.

ForeSight: fast object recognition using geometric hashing with edge-triple features

Abstract: We present a new method for the recognition of polyhedral objects from 2D images based on geometric hashing. Rather than the point-based approach of previous geometric hashing implementations, which tend to be rather sensitive to image noise and spurious data, our method is based on triples of connected edges. As well as improving the robustness of the system, the use of higher level feature groupings results in a very efficient specialisation of the geometric hashing paradigm. Theoretical analyses of the ForeSight method show that it is more than ten times as fast as a comparable point-based geometric hashing implementation, while using only one-quarter of the memory. These results were confirmed by practical experiments on a database of 50 real images, in which the recognition rate achieved by ForeSight approached twice that of the conventional method.

Indexing of handwritten document images

Abstract: An important problem in the management of scanned handwritten document image collections, is their indexing or retrieval based on word queries. This paper presents a method for fast localization of query words in handwritten images by an adaptation of the principle of geometric hashing. Specifically, a method of location hashing is presented that uses consecutive features along curves to produce small-sized image hash tables that also enable fast indexing. Handwriting variations are handled by assembling groups of word segments separated by inter-letter spacing, which is automatically estimated from sample pages written by an author. Results are presented that indicate the reduction in search as well as precision and recall possible with location hashing of handwritten words.

Geometric Hashing: error analysis

Abstract: We develop a model for predicting the probability of incorrect, random matches when using a geometric hashing based recognition scheme. To estimate the vote for random matches we approximate the voting function by a discrete function and use the binomial distribution. The resulting probability distribution of votes for random matches is compared with experiments that have a set of artificially generated, randomly distributed points as input. We find that the theoretical model accurately predicts the votes for random matches for most of the object models that we used. For the other models there were only small deviations.