This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
papers:simard-99 [2007/02/02 08:45] leonb |
papers:simard-99 [2007/07/24 19:13] leonb |
||
---|---|---|---|
Line 2: | Line 2: | ||
// | // | ||
- | Signal processing and pattern recognition algorithms make extensive use of convolution. In many cases, computational accuracy is | + | Signal processing and pattern recognition algorithms make extensive use of convolution. |
+ | In many cases, computational accuracy is | ||
not as important as computational speed. In feature extraction, | not as important as computational speed. In feature extraction, | ||
for instance, the features of interest in a signal are usually quite | for instance, the features of interest in a signal are usually quite | ||
Line 26: | Line 27: | ||
</ | </ | ||
- | @inproceedings{simard-99, | + | @incollection{simard-99, |
author = {Simard, Patrice and Bottou , L\' | author = {Simard, Patrice and Bottou , L\' | ||
title = {Boxlets: a fast convolution algorithm for neural networks and signal processing}, | title = {Boxlets: a fast convolution algorithm for neural networks and signal processing}, | ||
Line 40: | Line 41: | ||
==== Notes ==== | ==== Notes ==== | ||
- | Maybe the most famous use of boxlets is the computation of the features of the Viola-Jones | + | Maybe the most famous use of boxlets is the computation of the features of the Viola-Jones |
- | | + | |
- | * **[2]** Paul S. Heckberg: | + | |
+ | * **[2]** Paul Viola, Michael Jones: Robust Real-time Object Detection, // | ||
+ | * **[3]** Paul S. Heckberg: | ||
conference on Computer graphics//, 20:315-321, Dallas, 1986 | conference on Computer graphics//, 20:315-321, Dallas, 1986 |