图像处理耦合模板定位的答题卡识别研究与应用

当前大多数机器阅卷中采用的识别算法基于模糊识别,即针对某类型的试卷,更换多种试卷或者同种试卷不同采集方式下很难准确对应,具有一定的局限性。对此,本文提出一个基于OpenCV耦合模板定位的答题卡识别机制。首先基于人机交互划定学号区与客观题区;然后基于图像处理算法定位得到填涂位置,评价填涂结果,完成答题卡识别。本系统模板制作模块由C#编程实现,答题卡识别由C++和OpenCV实现。最后测试本文机制性能,结果表明：与基于模糊识别的普通方法相比,本文机制具有更好的定位效果和识别准确度。     

一种答题卡客观题识别算法

在保证阅卷质量的前提下,网上阅卷系统不仅极大地减少了教师的工作量,而且 降低了对试卷纸张质量的要求,节约能源。但是,网上阅卷系统中的客观题识别效果对答题卡 图像质量和排版有很强的依赖。为此,提出一种鲁棒的客观题识别算法。首先,考虑到用户填 涂时可能偏离填涂区域,或者用户图像和模板图像位置匹配出现的误差,提出了滑动窗口策略 重新定位实际的填涂区域,消除相关的偏差。然后,通过分析各选项的直方图,并引入加权平 均灰度消除单个选项中填涂不均匀的影响。对同一题下的每个选项进行比较,使得识别算法有 很强的局部适应性,克服使用全局识别策略带来的参数选择困难。实验结果表明,该算法兼容 性好,可以适用于不同排版类型的答题卡客观题识别,鲁棒性强,识别精度高,适用于各种扫 描质量和不同填涂质量的答题卡。     

基于Hough变换的答题卡识别

针对光电式阅卷机价格昂贵,使用成本高,设备利用率低的缺点,提出一种基于Hough变换的答题卡识别方法。运用数字图像处理的手段,对答题卡图像进行灰度拉伸、图像滤波、图像二值化等预处理;依据Hough变换的直线建立选项网;根据填涂区域的几何属性进行识别判断。测试结果表明,该算法对于答题卡的识别具有高效率、高准确率、使用方便、成本低廉的特点,具有一定的应用价值。     

扫描阅卷系统中模板定制和图像聚类方法的研究

为了适应答题卡多样化需求和提高答题卡图像识别的准确率,提出了扫描阅卷系统中模板定制和图像聚类方法。首先基于人机交互方式进行模板定制,定义填涂区域属性和答题卡结构信息,并开发了模板制作器,实现答题卡模板文件的制作和管理;其次给出基于K-means改进算法的扫描阅卷系统中图像聚类方法,选择局部聚集密度最大的数据点作为初始聚类中心以得到全局较优的聚类结果,并通过计算区分度进行聚类结果评价;最后基于VC++和MS SQL Server2000开发了基于K-means改进算法的扫描阅卷系统,并对该系统进行了实验测试。测试结果表明,采用K-means改进算法进行扫描阅卷时能够得到稳定的图像聚类结果,大大提高了客观题阅卷准确率,具有较高的实用价值。     

基于计算机视觉的自动阅卷系统的设计

基于计算机视觉技术设计了一个自动阅卷系统,为解决试卷填涂信息识别问题和自动判卷问题,提出了基于感知哈希技术的试卷填涂信息识别算法和基于图像比较近似度结果的判卷算法。通过系统实现与测试,系统拥有较快的处理速度、较高的准确性和易用性。     

基于人脸识别的医院智能支付风险控制算法设计

针对医院智能支付设备移动支付时存在人脸和指纹生物特征识别准确率低，导致移动支付失效和终端设备安全性下降的问题，设计基于人脸识别的医院智能支付系统算法。首先，分别采用手机摄像头和指纹传感器进行人脸图像和指纹图像采集并进行预处理；然后采用匹配级融合基于稀疏表示的人脸识别算法和基于细化图像的特征提取算法，由此得到人脸指纹G-WMF匹配层融合算法，,以计算出人脸指纹的匹配分数，并在最短时间内进行人脸指纹最佳权重分配，最终与人脸指纹数据库进行匹配，由此实现生物特征快速准确识别。实验结果表明，人脸和指纹的权重系数分别为0.3和0.7,识别率为极大值时，说明权重系数为最佳权重系数。单模人脸识别算法和指纹识别算法的识别率分别为86.4%和88.3%,比本算法的识别率分别低了12.8%和10.9%;相较于相同均值融合算法，本算法的识别率高出了11.5%。由此可知，本算法的识别率更高，可在移动支付系统中进行应用，提升系统安全性和稳定性。     

一种环状编码标记点的设计及解码算法

针对近景摄影测量中对编码标志点的精确定位和准确识别的要求,提出一种环状编码标记点的设计和识别算法。在传统环状编码标记点的基础上添加3个定位符,用于确定标志点的精确位置和增加标志点的数量。解码时先检测定位符坐标及其在标志点中的位置,然后对编码标志点进行透视变换以实现图像校正的目的,最后用提出的基于圆环扫描的方法进行解码。实验结果表明,该算法对任意旋转角度下的编码标志点均能有较好的检测识别效果;当摄像机与标记平面的夹角小于65°时,其识别准确率可达99.3%;在复杂背景情况下的平均识别准确率为97.4%,误识别率为1.25%,识别平均速率为2.15 s/幅。     

移动设备佩戴位置自适应识别的跌倒检测方法

随着智能手机的普及,使用移动设备检测跌倒事件正变得越来越有意义。移动设备的佩戴位置作为一种重要的情境信息,影响着跌倒检测活动的识别效果。为此,提出一种移动设备佩戴位置自适应识别的人体跌倒检测方法,首先采用旋转模式分量和姿态角融合的特征提取方法,利用加速度计和陀螺仪数据计算出旋转半径、角速度幅度、姿态角并提取特征,然后用LR（Logistic Regression）模型将其分类得到移动设备的佩戴位置;随后根据位置自适应调整一种基于时序分析的跌倒检测方法。实验结果表明,该方法的移动设备佩戴位置平均识别率为95.32%,在不同位置,时序跌倒检测算法的准确率均在92%以上。与传统跌倒检测方法相比,该方法在不同佩戴位置均有更好的跌倒检测识别效果。     

基于特征融合的掌纹识别算法应用研究

研究掌纹准确识别问题,由于光照强度、位置移动、采集设备等影响,采集掌纹图像的分辨率较低。单一掌纹特征提取方法难以全面描述掌纹信息,导致掌纹识别率低。为了提高了掌纹识别率,提出一种基于Gabor滤波和LBP算法相融合的掌纹识别方法。首先对采集掌纹进行预处理,然后分别采用Gabor滤波和LBP算法进行特征提取,最后采用神经网络建立掌纹识别器。仿真结果表明,相对于单一特征提取算法,融合特征算法不仅提高了掌纹识别率,同时加快掌纹识别速度,能够很好满足实时掌纹识别系统的要求。     

采用深度图像信息和SLVW的手语识别

为了实现手语视频中手语字母的准确识别,提出了一种基于DI_CamShift和SLVW的算法。该方法将Kinect作为手语视频采集设备,在获取彩色视频的同时得到其深度信息;计算深度图像中手语手势的主轴方向角和质心位置,通过调整搜索窗口对手势进行准确跟踪;使用基于深度积分图像的Ostu算法分割手势,并提取其SIFT特征;构建了SLVW词包作为手语特征,并用SVM进行识别。通过实验验证该算法,其单个手语字母最好识别率为99.87%,平均识别率96.21%。     

Activity logging using lightweight classification techniques in mobile devices

Automated activity recognition enables a wide variety of applications related to child and elderly care, disease diagnosis and treatment, personal health or sports training, for which it is key to seamlessly determine and log the user’s motion. This work focuses on exploring the use of smartphones to perform activity recognition without interfering in the user’s lifestyle. Thus, we study how to build an activity recognition system to be continuously executed in a mobile device in background mode. The system relies on device’s sensing, processing and storing capabilities to estimate significant movements/postures (walking at different paces—slow, normal, rush, running, sitting, standing). In order to evaluate the combinations of sensors, features and algorithms, an activity dataset of 16 individuals has been gathered. The performance of a set of lightweight classifiers (Naïve Bayes, Decision Table and Decision Tree) working on different sensor data has been fully evaluated and optimized in terms of accuracy, computational cost and memory fingerprint. Results have pointed out that a priori information on the relative position of the mobile device with respect to the user’s body enhances the estimation accuracy. Results show that computational low-cost Decision Tables using the best set of features among mean and variance and considering all the sensors (acceleration, gravity, linear acceleration, magnetometer, gyroscope) may be enough to get an activity estimation accuracy of around 88 % (78 % is the accuracy of the Naïve Bayes algorithm with the same characteristics used as a baseline). To demonstrate its applicability, the activity recognition system has been used to enable a mobile application to promote active lifestyles.     

Energy-aware disk scheduling for soft real-time I/O requests

In this work, we develop energy-aware disk scheduling algorithm for soft real-time I/O. Energy consumption is one of the major factors which bar the adoption of hard disk in mobile environment. Heat dissipation of large scale storage system also calls for an energy-aware scheduling technique to further increase the storage density. The basic idea in this work is to properly determine the I/O burst size so that device can be in standby mode between consecutive I/O bursts and that it can satisfy the soft real-time requirement. We develop an elaborate model which incorporates the energy consumption characteristics, overhead of mode transition in determining the appropriate I/O burst size and the respective disk operating schedule. Efficacy of energy-aware disk scheduling algorithm greatly relies on not only disk scheduling algorithm itself but also various operating system and device firmware related concerns. It is crucial that the various operating system level and device level features need to be properly addressed within disk scheduling framework. Our energy-aware disk scheduling algorithm successfully addresses a number of outstanding issues. First, we examine the effect of OS and hard disk firmware level prefetch policy and incorporate its effect in our disk scheduling framework. Second, our energy aware scheduling framework can allocate a certain fraction of disk bandwidth to handle sporadically arriving non real-time I/O’s. Third, we examine the relationship between lock granularity of the buffer management and energy consumption. We develop a prototype software with energy-aware scheduling algorithm. In our experiment, proposed algorithm can reduce the energy consumption to one fourth if we use energy-aware disk scheduling algorithm. However, energy-aware disk scheduling algorithm increases buffer requirement significantly, e.g., from 4 to 140 KByte. We carefully argue that the buffer overhead is still justifiable given the cost of DRAM chip and importance of energy management in modern mobile devices. The result of our work not only provides the energy efficient scheduling algorithm but also provides an important guideline in capacity planning of future energy efficient mobile devices. This paper is funded by KOSEF through Statistical Research Paper for Complex System at Seoul National University.     

Improving performance on object recognition for real-time on mobile devices

Augmented reality has been on the rise due to the proliferation of mobile devices. At the same time, object recognition has also come to the fore. In particular, many studies have focused on object recognition based on markerless matching. However, most of these studies have focused on desktop systems, which can have high performance in terms of CPU and memory, rather than investigating the use of mobile systems, which have been previously unable to provide high-performance object recognition based on markerless matching. In this paper, we propose a method that uses the OpenCV mobile library to improve real-time object recognition performance on mobile systems. First, we investigate the original object recognition algorithm to identify performance bottlenecks. Second, we optimize the algorithm by analyzing each module and applying appropriate code enhancements. Last, we change the operational structure of the algorithm to improve its performance, changing the execution frequency of the object recognition task from every frame to every four frames for real-time operation. During the three frames in which the original method is not executed, the object is instead recognized using the mobile devices accelerometer. We carry out experiments to reveal how much each aspect of our method improves the overall object recognition performance; overall, experimental performance improves by approximately 800 %, with a corresponding reduction of approximately 1 % in object recognition accuracy. Therefore, the proposed technique can be used to significantly improve the performance of object recognition based on markerless matching on mobile systems for real-time operation.     

The more you learn,the less you store: Memory-controlled incremental SVM for visual place recognition

The capability to learn from experience is a key property for autonomous cognitive systems working in realistic settings. To this end, this paper presents an SVM-based algorithm, capable of learning model representations incrementally while keeping under control memory requirements. We combine an incremental extension of SVMs [43] with a method reducing the number of support vectors needed to build the decision function without any loss in performance [15] introducing a parameter which permits a user-set trade-off between performance and memory. The resulting algorithm is able to achieve the same recognition results as the original incremental method while reducing the memory growth. Our method is especially suited to work for autonomous systems in realistic settings. We present experiments on two common scenarios in this domain: adaptation in presence of dynamic changes and transfer of knowledge between two different autonomous agents, focusing in both cases on the problem of visual place recognition applied to mobile robot topological localization. Experiments in both scenarios clearly show the power of our approach.     

Simultaneous measurements of posture and movements of head and trunk by continuous three-dimensional registration

The postures of three groups of employees were measured: straddle carrier drivers, crane operators and office employees. This type of sedentary work can be characterized as being highly static. Using a continuous three-dimensional registration device, the postures and movements of head and trunk were recorded simultaneously. The results show that the adopted postures and patterns of movement were predominantly imposed by the workplace. The posture of the crane operators was the most static compared to the other occupations. The most adopted posture in the sagittal plane for crane operators was trunk flexion of 5° and head flexion of 60°. Typically, a straddle carrier driver rotated his head more than 45° to the left or right for 28% of the day, which far exceeded that of the other groups. The measuring device provides accurate and reproducible data that can subsequently be used for calculating the postural load and for ergonomic analysis.     

一种新型红外多点触摸识别算法

近年来,多点触摸技术逐渐成为最为重要的人机交互设备,得到了广泛的应用。本文提出一种新型红外多点触摸识别算法原型,该算法同时在两个不同坐标体系中对用户的触摸进行识别,克服了传统红外触摸屏在识别多点触摸时存在的伪触摸点的问题,实验证明该算法提高了红外触摸屏的多点触摸识别率。     

Collaboration among mobile agents for efficient energy allocation in mobile grid

The use of mobile devices in grid environments may have two interaction aspects: devices are considered as users of grid resources or as grid resources providers. Due to the limitation constraints on energy and processing capacity of mobile devices, their integration into the Grid is difficult. In this paper, we investigate the cooperation among mobile devices to balance the energy consumption and computation workloads. Mobile devices can have different roles such as buyer devices and seller devices. In the mobile grid, the energies of mobile devices are uneven, energy-poor devices can exploit other devices with spare energy. Our model consists of two actors: A buyer device agent represents the benefits of mobile buyer device that intends to purchase energy from other devices. A seller device agent represents the profits of mobile seller device that is willing to sell spare energy to other devices. The objective of optimal energy allocation in mobile grid is to maximize the utility of the system without exceeding the energy capacity, expense budget and the deadline. A collaboration algorithm among mobile agents for efficient energy allocation is proposed. In the simulation, the performance evaluation of collaboration algorithm among mobile agents is conducted.     

结合图像识别的移动增强现实系统设计与应用

目的 在移动互联网时代下,移动增强现实应用得到越来越快的发展。然而户外场景中存在许多相似结构的建筑,且手机的存储和计算能力有限,因此应用多集中于室内小范围环境,对于室外大规模复杂场景的适应性较弱。对此,建立一套基于云端图像识别的移动增强现实系统。方法 为解决相似特征的误匹配问题,算法中将重力信息加入到SURF和BRISK特征描述中去,构建Gravity-SURF和Gravity-BRISK特征描述。云端系统对增强信息进行有效管理,采用基于Gravity-SURF特征的VLAD方法对大规模图像进行识别;在智能终端上的应用中呈现识别图像的增强信息,并利用识别图像的Gravity-BRISK特征和光流结合的方法对相机进行跟踪,采用Unity3D渲染引擎实时绘制3维模型。结果 在包含重力信息的4 000幅户外图像的数据库中进行实验。采用结合重力信息的特征描述算法,能够增强具有相似特征的描述符的区分性,并提高匹配正确率。图像识别算法的识别率能达到88%以上,识别时间在420 ms左右;光流跟踪的RMS误差小于1.2像素,帧率能达到23 帧/s。结论 本文针对室外大规模复杂场景建立的基于图像识别的移动增强现实系统,能方便对不同应用的增强现实数据进行管理。系统被应用到谷歌眼镜和新闻领域上,不局限于单一的应用领域。结果表明,识别算法和跟踪注册算法能够满足系统的精度和实时性要求。