Graph Cut Segmentation Methods Revisited with a Quantum Algorithm

The design and performance of computer vision algorithms are greatly influenced by the hardware on which they are implemented. CPUs, multi-core CPUs, FPGAs and GPUs have inspired new algorithms and enabled existing ideas to be realized. This is notably the case with GPUs, which has significantly changed the landscape of computer vision research through deep learning. As the end of Moores law approaches, researchers and hardware manufacturers are exploring alternative hardware computing paradigms. Quantum computers are a very promising alternative and offer polynomial or even exponential speed-ups over conventional computing for some problems. This paper presents a novel approach to image segmentation that uses new quantum computing hardware. Segmentation is formulated as a graph cut problem that can be mapped to the quantum approximate optimization algorithm (QAOA). This algorithm can be implemented on current and near-term quantum computers. Encouraging results are presented on artificial and medical imaging data. This represents an important, practical step towards leveraging quantum computers for computer vision.

[1]  Kai Lu,et al.  QSobel: A novel quantum image edge extraction algorithm , 2014, Science China Information Sciences.

[2]  Vasil S. Denchev,et al.  Training a Binary Classifier with the Quantum Adiabatic Algorithm , 2008, 0811.0416.

[3]  Kendall Preston,et al.  Coherent optical computers , 1972 .

[4]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Moncef Gabbouj,et al.  Quantum mechanics in computer vision: Automatic object extraction , 2013, 2013 IEEE International Conference on Image Processing.

[6]  Rupak Biswas,et al.  From the Quantum Approximate Optimization Algorithm to a Quantum Alternating Operator Ansatz , 2017, Algorithms.

[7]  Mark J. Schnitzer.  Biological computation: Amazing algorithms , 2002, Nature.

[8]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[9]  Stuart Hadfield,et al.  The Quantum Approximation Optimization Algorithm for MaxCut: A Fermionic View , 2017, 1706.02998.

[10]  Simone Severini,et al.  Hierarchical quantum classifiers , 2018, npj Quantum Information.

[11]  Ron Unger,et al.  Biological Computation , 2011 .

[12]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[13]  Lijiang Chen,et al.  Quantum digital image processing algorithms based on quantum measurement , 2013 .

[14]  A. Harrow,et al.  Quantum Supremacy through the Quantum Approximate Optimization Algorithm , 2016, 1602.07674.

[15]  Lov K. Grover.  A fast quantum mechanical algorithm for database search , 1996, STOC '96.

[16]  Mingyue Ding,et al.  A new quantum edge detection algorithm for medical images , 2009, International Symposium on Multispectral Image Processing and Pattern Recognition.

[17]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  E. Farhi,et al.  A Quantum Approximate Optimization Algorithm , 2014, 1411.4028.

[19]  Thierry Paul,et al.  Quantum computation and quantum information , 2007, Mathematical Structures in Computer Science.

[20]  Catherine D. Schuman,et al.  A Survey of Neuromorphic Computing and Neural Networks in Hardware , 2017, ArXiv.

[21]  Tomás Babej,et al.  A quantum alternating operator ansatz with hard and soft constraints for lattice protein folding , 2018, 1810.13411.

[22]  D. R. Fulkerson,et al.  Maximal Flow Through a Network , 1956 .

[23]  Zhenyu Wu,et al.  Graph theoretic approach to segmentation of MR images , 1991, Electronic Imaging.

[24]  Leo Zhou,et al.  Quantum Approximate Optimization Algorithm: Performance, Mechanism, and Implementation on Near-Term Devices , 2018, Physical Review X.

[25]  H. Neven,et al.  Quantum Algorithms for Fixed Qubit Architectures , 2017, 1703.06199.

[26]  David A. Hounshell,et al.  Science and research policy at the end of Moore’s law , 2018, Nature Electronics.

[27]  Peter W. Shor,et al.  Algorithms for quantum computation: discrete logarithms and factoring , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

[28]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[29]  Dorothea Wagner,et al.  Between Min Cut and Graph Bisection , 1993, MFCS.

[30]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[31]  Jun Li,et al.  Hybrid Quantum-Classical Approach to Quantum Optimal Control. , 2016, Physical review letters.

[32]  R. Feynman.  Simulating physics with computers , 1999 .

[33]  Hartmut Neven,et al.  NIPS 2009 Demonstration: Binary Classification using Hardware Implementation of Quantum Annealing , 2009 .

[34]  Peter Elias,et al.  A note on the maximum flow through a network , 1956, IRE Trans. Inf. Theory.

[35]  Blake R. Johnson,et al.  Unsupervised Machine Learning on a Hybrid Quantum Computer , 2017, 1712.05771.

[36]  W. Macready,et al.  Image recognition with an adiabatic quantum computer I. Mapping to quadratic unconstrained binary optimization , 2008, 0804.4457.