一种基于量子机制的图像显著性检测方案

J4 ›› 2017, Vol. 34 ›› Issue (3): 305-315.

一种基于量子机制的图像显著性检测方案

杨春蕾,普杰信,董永生,刘中华,梁灵飞

河南科技大学信息工程学院，河南洛阳 471000

收稿日期:2015-10-16 修回日期:2015-12-18 出版日期:2017-05-28 发布日期:2017-05-22
通讯作者: 普杰信（1959-），河南鹿邑人，博士，教授，博士生导师，主要研究方向为计算机视觉与模式识别、神经智能信息处理。 E-mail:pjx2014stu@163.com
作者简介:杨春蕾（1980-），河南开封人，博士生，主要研究方向为图像显著性检测、量子信息处理、模式识别。E-mail: cleiyang@126.com
基金资助:
Supported by International S & T Cooperation Program of China(国家国际科技合作计划, 2011DFR10480), National Natural Science Foundation of China(国家自然科学基金, U1504610)、Key Project of Science and Technology of Henan Province(河南省科技攻关计划, 142107000021)

An image saliency detection scheme based on quantum mechanism

Department of Information Engineering, Henan University of Science and Technology, Luoyang 471000, China

Received:2015-10-16 Revised:2015-12-18 Published:2017-05-28 Online:2017-05-22

摘要/Abstract

摘要： 提出了一种与传统方法相比效率更高的量子图像显著性检测方案。为了在量子计算机中表示和存储RGB图像，并计算不同像素间的反差，此方案采用3量子位描述颜色信息，把22n×2图像矩阵编码为量子叠加态；结合Hadamard门和受控旋转算子，计算基态概率幅可反映像素在RGB三通道上的全局颜色反差；通过有限次数的投影测量可得到像素的归一化颜色反差及位置信息，并构建显著图。给出了相关量子电路的实现和复杂度分析。与多种传统显著性检测算法进行了对比实验，结果表明提出的方案具有良好的检测效果和更高的检测效率。

关键词: 量子计算；图像显著性检测；量子反差；显著图

Abstract: A quantum image saliency detection scheme is proposed, which is more efficient than the traditional methods. In order to represent and store RGB images in on quantum computers and calculate the contrast between different pixels, the scheme adopts three-qubits to describe color information. The 22n×2 image matrix is encoded as a quantum superposition state. Combined with Hadamard gate and controlled rotation operator, the global color contrasts of pixels in RGB three-channels are mapped into the probability amplitude of computational basis states, and the saliency map is achieved using a finite number of projective measurementsthe saliency map is constructed. The realization of related quantum circuits and complexity analysis are presented. The contrast experiments are carried out with several traditional saliency detection algorithms. Results show that the proposed scheme has good detection effect and higher detection efficiency.

Key words: quantum computation; image saliency detection; quantum contrast; saliency map

中图分类号:

杨春蕾普杰信董永生刘中华梁灵飞. 一种基于量子机制的图像显著性检测方案[J]. J4, 2017, 34(3): 305-315.

参考文献

[1] S.E. Venegas-Andraca and S. Bose. Storing, processing and retrieving an image using quantum mechanics [C]. Proceedings of SPIE Conference of Quantum Information and Computation, 2003, Vol. 5105: 134-147, 2003. [2]J.I. LatorreImage compression and entanglement[J].Quantum Physics, 2005, 1(051003):1-4 [3] P.Q. Le, A. M. Iliyasu, F. Dong, K. Hirota. A flexible representation and invertible transformations for images on quantum computers [C]. New Advances in Intelligent Signal Processing, 2011, 372: 179-202. [4]P.Q. Le,AM. Iliyasu,F. Dong,K. Hirota. Fast geometric transformations on quantum images[J].International Journal of Applied Mathematics, 2010, 40(3):113-123 [5]P.Q. Le,AM. Iliyasu,F. Dong,K. Hirota. Efficient color transformations on quantum image[J].Journal of formatics, 2011, 15(6):698-706 [6]Simona Caraiman, Vasile I.MantaImage segmentation on a quantum computer[J].Quantum Information Processing, 2015, 14(5):1693-1715 [7] Sun Yangguang.Quantum statistical edge detection using path integral monte carlo simulation [C]. Communications in Computer and Information Science, 2014, 472: 430-434. [8] F.Yan, P. Q. Le, A. M. Iliyasu. Assessing the similarity of quantum images based on probability measurements [C]. 2012 IEEE World Congress on Computational Intelligence, 2012, Brisbane: 1-6. [9]F.Yan,AM. Iliyasu,C. Fatichah,et al.. Quantum image searching based on probability distributions[J].Journal of quantum information science, 2012, 2(3):55-60 [10]Wang Ning, Lin Song.A watermarking strategy for quantum image based on least significant bit[J].量子电子学报, 2015, 32(3):263-269 [11]Su Feng, Liu Xiang, Long Huabao et al.Sampling number of reconstruction arithmetic based on quantum correlated imaging[J].量子电子学报, 2015, 32(3):144-149 [12] A.Borji, L. Itti. State-of-the-art in visual attention modeling [C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 185-207. [13] Yun Zhai, Mubarak Shah.Visual attention detection in video sequences using spatiotemporal cues [C]. Proceedings of the 14th Annual ACM International Conference on Multimedia, 2006: 815–824. [14]Tong Na, Lu Huchuan, Zhang Lihe.Saliency detection with multi-scale superpixels[J].IEEE Signal Processing Letters, 2014, 21(9):1035-1039 [15] Yang Chuan, Zhang Lihe, Lu, Huchuan et al.Saliency detection via graph-based manifold ranking [C]. Computer Vision and Pattern Recognition (CVPR), 2013:3166-3172. [16]Fan, Qiang, Qi, Chun.Two-stage salient region detection by exploiting multiple priors[J].Journal of Visual Communication and Image Representation, 2014, 25(8):1823-1834 [17] Zhu Wangjiang, Liang Shuang, Wei, Yichen.Saliency optimization from robust background detection[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014:2814-2821. [18]Xie Yulin, Lu Huchuan, Yang Ming-Hsuan.Bayesian saliency via low and mid level cues[J].Image Processing, 2013, 22(5):1689-1698 [19] Jiang Bowen, Zhang Lihe, Lu, Huchuan.Saliency detection via absorbing Markov Chain[C]. IEEE International Conference on Computer Vision, 2013:1665-1672. [20] Margolin Ran, Tal Ayellet, Zelnik-Manor Lihi.What makes a patch distinct? [C]. Computer Vision and Pattern Recognition (CVPR), 2013:1139-1146. [21] Shi Keyang, Wang Keze, Lu Jiangbo et al.Pisa: Pixelwise image saliency by aggregating complementary appearance contrast measures with spatial priors[C]. Computer Vision and Pattern Recognition (CVPR), 2013:2115-2122. [22] Jiang Huaizu, Wang Jingdong, Yuan, Zejian et al.Salient object detection: A discriminative regional feature integration approach[C]. Computer Vision and Pattern Recognition (CVPR), 2013:2083--2090.