基于测量的量子图像识别研究  

Research on quantum image recognition based on measurement

作　　者：周晓彦[1,2] 安星星 王珂 嵇福高 

机构地区：[1]南京信息工程大学江苏省气象探测与信息处理重点实验室,南京210044 [2]南京信息工程大学江苏省气象传感网技术工程中心,南京210044

出　　处：《电子测量与仪器学报》2017年第10期1679-1686,共8页Journal of Electronic Measurement and Instrumentation

基　　金：国家自然科学基金(61201444)资助项目

摘　　要：目前,已有的量子相似度比较算法:1)逐个比较图像对应位置的像素值;2)将两幅图像分别用量子态表示,再将两幅图像进行连接(意味着将两个量子态连接成一个态),再进行相关的量子操作。所提出的比较算法,是在不连接图像的基础上,将图像用量子态表示,进行控制交换(c-Swap)操作,再进行量子测量,根据测量结果判断两幅图像的相似度。将所提的量子相似度比较算法应用到量子手势识别中,实验结果表明所提算法在识别问题上具有可行性。在经典领域中,手势识别的流程比较复杂。而在量子领域中,无需提取手势的颜色、纹理、特征等步骤,直接可以将手势进行二值化表示,再根据所提的图像相似度算法来实现手势识别。At present, the existing quantum similarity comparison： one is to compare the pixel values of the image＇ s corresponding position one by one ; the other is to represent two images by quantum states, then the two images are connected （ it means that the two quantum states are connected to a state）, and the relevant quantum operation is carried out. The proposed algorithm is based on the non- connected image, the image is represented by quantum states. Next, the control swap （c-Swap） operation is performed, then the quantum measurement is carried out, and the similarity of two images is determined according to the measurement result. The proposed quantum similarity comparison algorithm is applied to quantum gesture recognition, and the experimental results show that the proposed algorithm is feasible in identifying the problem. In the classic field, the process of gesture recognition is more complex. In the quantum field, there is no need to extract the gestures of the color, texture, features and other steps. The gesture can be binarized directly, and then the gesture recognition is achieved according to the proposedimage similarity algorithm.

关 键 词：量子图像识别 c-Swap操作 量子测量 量子手势识别 

分 类 号：TP306[自动化与计算机技术—计算机系统结构]