Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Journal of Optical Technology

Object recognition using quantum holography with neural-net preprocessing

Chu Kiong Loo, Mitja Peruš, Horst Bischof

Published May 1, 2005• 5 citations
Publisher

Abstract

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. © 2005 Optical Society of America

DOI
10.1364/jot.72.000358

Related papers

Simulated quantum-optical object recognition from high-resolution images

Chu Kiong Loo, M. Peruš, Horst Bischof

A holographic experimental procedure assuming use of quantum states of light is simulated. It uses merely interference-based image storage and nonunitary image retrieval realized by wave function collapse. Successful results of computational view-invariant recognition of object images are presented. As in neural net theory, recognition is selective reconstruction of an image from a database of many concrete images (simultaneously stored in an associative memory) after presentation of a different version of that image. That is, in the first step, we store many high-resolution images of objects into quantum memory (a hologram). In the second step, we present a “nonlearned” noisy image version. We thereby trigger memory-influenced reorganization of the state of the system so that it finally encodes those corrected object images that correspond to the newly presented version. The holographic procedure seems to be implementable with present-day quantum optics.

Optics and Spectroscopy•Aug 1, 2005•2 citations

Associative Memory Based Image and Object Recognition by Quantum Holography

Chu Kiong Loo, Mitja Peruš, Horst Bischof

A quantum associative memory, much more natural than those of “quantum computers”, is presented. Neural-net-like processing with real-valued variables is transformed into processing with quantum waves. Successful computer simulations of image storage and retrieval are reported. Our Hopfield-like algorithm allows quantum implementation with holographic procedure using present-day quantum-optics techniques. This brings many advantages over classical Hopfield neural nets and quantum computers with logic gates.

Open Systems & Information Dynamics•Sep 1, 2004•13 citations

Quantum-implementable selective reconstruction of high-resolution images

Mitja Peruš, Horst Bischof, H. John Caulfield +1 more

This paper, written for interdisciplinary audience, presents computational image reconstruction implementable by quantum optics. The input-triggered selection of a high-resolution image among many stored ones, and its reconstruction if the input is occluded or noisy, has been successfully simulated. The original algorithm, based on the Hopfield associative neural net, was transformed in order to enable its quantum-wave implementation based on holography. The main limitations of the classical Hopfield net are much reduced with the simulated new quantum-optical implementation.

arXiv:quant-ph/0401016•Applied Optics•Nov 20, 2004•37 citations

Investigation of Quantum Algorithms for Face Detection and Recognition Using a Quantum Neural Network

Sergey M. Gushanskiy, Viktor Potapov

This article presents the most common image recognition algorithms implemented for a quantum neural network, consider them and draw a conclusion which algorithm is preferable to use in this or that case. Currently, there is a rapid increase in interest in quantum algorithms for pattern recognition, since the first quantum computers have already appeared. This is because the use of quantum algorithms since the advent of quantum computers has allowed an exponential increase in the speed of solving NP-complete problems. Paper decide the some problems of finding and creation of approaches for the functioning of quantum calculation processes and prototypes of quantum devices in the framework of quantum image processing. A method for storing and processing image components in quantum systems is proposed, which potentially will give a significant step toward in efficiency in comparison with existing classical ones and provide a solution to a number of complex problems.

International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)•May 17, 2021•7 citations

Quantum Bio-inspired Invariant Object Recognition Model on System-on-a-Chip (SoC)

Loo Chu Kiong, Teh Joo Peng

This paper presents the first attempt of designing a physical quantum-like `brain' for humanoid and experimentally proves a 2D invariant object recognition model inspired by the image processing along the human visual pathway: retina, lateral geniculate nucleus (LGN) and primary visual cortex (V1). It also describes storing the output of the model in quantum holographic memory (a hologram) and the method to reconstruct the visual representation. The work is implemented as system-on-a-chip in field-programmable gate array (FPGA).

IEEE Conference on Robotics, Automation and Mechatronics (RAM)•Sep 1, 2008•4 citations

A quantum Hopfield neural network model and image recognition

Ge Liu, Wenping Ma, Hao Cao +1 more

Abstract Quantum computing is a new mode that follows the laws of quantum mechanics. It performs computational tasks based on the control of quantum units. From the view of computable problems, quantum computers can only solve the problems that traditional computers can solve, but considering the efficiency of computation, due to the existence of quantum superposition, some known quantum algorithms are exponentially faster than traditional general-purpose computers. In this article, we combine quantum computing with a classical neural network to design a quantum Hopfield network. Each neuron is initialized to a specified state and evolved into a steady state. The output result is one of patterns in a training set. We also present an application of this protocol in image recognition. The simulation results show that this network works in the quantum environment and the output images are correct, therefore the feasibility of this protocol is verified.

Laser Physics Letters•Feb 27, 2020•14 citations
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. © 2005 Optical Society of America
A holographic experimental procedure assuming use of quantum states of light is simulated. It uses merely interference-based image storage and nonunitary image retrieval realized by wave function collapse. Successful results of computational view-invariant recognition of object images are presented. As in neural net theory, recognition is selective reconstruction of an image from a database of many concrete images (simultaneously stored in an associative memory) after presentation of a different version of that image. That is, in the first step, we store many high-resolution images of objects into quantum memory (a hologram). In the second step, we present a “nonlearned” noisy image version. We thereby trigger memory-influenced reorganization of the state of the system so that it finally encodes those corrected object images that correspond to the newly presented version. The holographic procedure seems to be implementable with present-day quantum optics.
A quantum associative memory, much more natural than those of “quantum computers”, is presented. Neural-net-like processing with real-valued variables is transformed into processing with quantum waves. Successful computer simulations of image storage and retrieval are reported. Our Hopfield-like algorithm allows quantum implementation with holographic procedure using present-day quantum-optics techniques. This brings many advantages over classical Hopfield neural nets and quantum computers with logic gates.
This paper, written for interdisciplinary audience, presents computational image reconstruction implementable by quantum optics. The input-triggered selection of a high-resolution image among many stored ones, and its reconstruction if the input is occluded or noisy, has been successfully simulated. The original algorithm, based on the Hopfield associative neural net, was transformed in order to enable its quantum-wave implementation based on holography. The main limitations of the classical Hopfield net are much reduced with the simulated new quantum-optical implementation.
This article presents the most common image recognition algorithms implemented for a quantum neural network, consider them and draw a conclusion which algorithm is preferable to use in this or that case. Currently, there is a rapid increase in interest in quantum algorithms for pattern recognition, since the first quantum computers have already appeared. This is because the use of quantum algorithms since the advent of quantum computers has allowed an exponential increase in the speed of solving NP-complete problems. Paper decide the some problems of finding and creation of approaches for the functioning of quantum calculation processes and prototypes of quantum devices in the framework of quantum image processing. A method for storing and processing image components in quantum systems is proposed, which potentially will give a significant step toward in efficiency in comparison with existing classical ones and provide a solution to a number of complex problems.
This paper presents the first attempt of designing a physical quantum-like `brain' for humanoid and experimentally proves a 2D invariant object recognition model inspired by the image processing along the human visual pathway: retina, lateral geniculate nucleus (LGN) and primary visual cortex (V1). It also describes storing the output of the model in quantum holographic memory (a hologram) and the method to reconstruct the visual representation. The work is implemented as system-on-a-chip in field-programmable gate array (FPGA).
Abstract Quantum computing is a new mode that follows the laws of quantum mechanics. It performs computational tasks based on the control of quantum units. From the view of computable problems, quantum computers can only solve the problems that traditional computers can solve, but considering the efficiency of computation, due to the existence of quantum superposition, some known quantum algorithms are exponentially faster than traditional general-purpose computers. In this article, we combine quantum computing with a classical neural network to design a quantum Hopfield network. Each neuron is initialized to a specified state and evolved into a steady state. The output result is one of patterns in a training set. We also present an application of this protocol in image recognition. The simulation results show that this network works in the quantum environment and the output images are correct, therefore the feasibility of this protocol is verified.