Object recognition using quantum holography with neural-net preprocessing
It is computationally demonstrated how quantum associative networks, implemented using quantum holography, could be harnessed for object recognition. These simulated quantum nets alone execute efficient image recognition, i.e., reconstruction of an image selected from associative memory (hologram)....
Main Authors: | , , |
---|---|
格式: | 文件 |
出版: |
Optical Society of America
2005
|
主题: |
_version_ | 1825719049038856192 |
---|---|
author | Loo, C.K. Perus, M. Bischof, H. |
author_facet | Loo, C.K. Perus, M. Bischof, H. |
author_sort | Loo, C.K. |
collection | UM |
description | It is computationally demonstrated how quantum associative networks, implemented using quantum holography, could be harnessed for object recognition. These simulated quantum nets alone execute efficient image recognition, i.e., reconstruction of an image selected from associative memory (hologram). However, optically implementable neural-net preprocessing of object-images is needed for appearance-based viewpoint-invariant recognition of objects. We present computer simulation results of two methods: Moore-Penrose orthogonalization and encoding of object-images with Gabor wavelets. A computer-supported quantum Gabor-wavelet holography is proposed. |
first_indexed | 2024-03-06T05:13:42Z |
format | Article |
id | um.eprints-5176 |
institution | Universiti Malaya |
last_indexed | 2024-03-06T05:13:42Z |
publishDate | 2005 |
publisher | Optical Society of America |
record_format | dspace |
spelling | um.eprints-51762017-07-08T07:56:43Z http://eprints.um.edu.my/5176/ Object recognition using quantum holography with neural-net preprocessing Loo, C.K. Perus, M. Bischof, H. T Technology (General) It is computationally demonstrated how quantum associative networks, implemented using quantum holography, could be harnessed for object recognition. These simulated quantum nets alone execute efficient image recognition, i.e., reconstruction of an image selected from associative memory (hologram). However, optically implementable neural-net preprocessing of object-images is needed for appearance-based viewpoint-invariant recognition of objects. We present computer simulation results of two methods: Moore-Penrose orthogonalization and encoding of object-images with Gabor wavelets. A computer-supported quantum Gabor-wavelet holography is proposed. Optical Society of America 2005 Article PeerReviewed Loo, C.K. and Perus, M. and Bischof, H. (2005) Object recognition using quantum holography with neural-net preprocessing. Journal of Optical Technology (JOT), 72 (5). pp. 358-363. ISSN 1070-9762, http://www.opticsinfobase.org/jot/abstract.cfm?id=84246 |
spellingShingle | T Technology (General) Loo, C.K. Perus, M. Bischof, H. Object recognition using quantum holography with neural-net preprocessing |
title | Object recognition using quantum holography with neural-net preprocessing |
title_full | Object recognition using quantum holography with neural-net preprocessing |
title_fullStr | Object recognition using quantum holography with neural-net preprocessing |
title_full_unstemmed | Object recognition using quantum holography with neural-net preprocessing |
title_short | Object recognition using quantum holography with neural-net preprocessing |
title_sort | object recognition using quantum holography with neural net preprocessing |
topic | T Technology (General) |
work_keys_str_mv | AT loock objectrecognitionusingquantumholographywithneuralnetpreprocessing AT perusm objectrecognitionusingquantumholographywithneuralnetpreprocessing AT bischofh objectrecognitionusingquantumholographywithneuralnetpreprocessing |