A Tradeoff Between Accuracy and Speed for K-Means Seed Determination

With a sharp increase in the information volume, analyzing and retrieving this vast data volume is much more essential than ever. One of the main techniques that would be beneficial in this regard is called the Clustering method. Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible. One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm. The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters. Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time. Besides, the selection of appropriate initial seeds can reduce the cluster’s inconsistency. In this paper, we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm. For this purpose, a new method is proposed considering the average distance between objects to determine the initial seeds. Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm. The experimental results showed that our proposed approach outperforms the Chithra with 1.7% and 2.1% in terms of clustering accuracy for Wine and Abalone detection data, respectively. Furthermore, achieved results indicate that comparing with the Reverse Nearest Neighbor (RNN) search approach, the proposed method has a higher convergence speed.     

优化特征提取的互动式人脸活体检测研究

针对人脸识别系统中出现的通过照片或视频“欺诈”解锁问题，提出一种活体检测方法，通过随机指令判断被检测对象是否为真人。利用HOG特征和随机森林算法对摄像头采集的图像进行人脸检测，预测脸部68个特征点位置，把68个特征点位置和脸部位置的相对位置归一化后作为姿态的特征，提取的姿态特征与SVM分类器相结合，训练出分类效果较好的头部姿态估计分类器。通过多次实验，对特征提取方法进行优化，进一步提高检测准确率。最后，使用随机互动式命令序列对被检测人发出指令，实现活体检测。该方法对头部姿态估计具有较高的鲁棒性，并且可以有效地防范照片和视频认证攻击。     

In-situ deflectometic measurement of transparent optics in precision robotic polishing

In the ultra-precision manufacturing of large optics, industrial robots have the potential to become an intelligent and economical choice of surface polishing. However, the transport of the workpieces between the polishing platform and the measurement instrument seriously limits the manufacturing efficiency. Therefore, an in-situ measurement system based on the monoscopic deflectometry is developed to determine the form quality of the optical lenses during rough polishing. Stray light reflected from the lower surface of transparent lenses may degrade the measuring quality, thus an effective absolute phase retrieval algorithm is developed to decouple the superposed fringes associated with the upper and lower surfaces. Then, the form of the upper surface under polishing can be reconstructed to guide the subsequent polishing. Experimental results demonstrate that the accuracy of the method is comparable to that of the coordinate measuring machine, consequently the manufacturing efficiency and reliability of large optical workpieces can be greatly improved.     

两种多层穿梭车系统的性能比较分析

物流配送中心订单响应速度的加快,对订单拣选系统提出了更高的要求。多层穿梭车系统因其柔性强、效率高等特点,近年来得到了广泛应用。多层穿梭车系统具有两种形式--基于转载车和基于环形输送线,二者均可实现货物的快速拣选,但在系统吞吐量和订单完成周期方面存在差异,致使企业决策者难以进行系统选择。基于上述原因,本文比较两种多层穿梭车系统的性能差异。建立两个系统的开环排队网络模型,然后求解系统吞吐量、订单完成周期,通过仿真验证了排队论模型的准确性,通过试验对两种系统的性能进行对比分析。结果表明,系统吞吐量与层数、巷道数相关,层数越多,巷道数越少,转载车系统相对于环线系统优势越显著;订单完成周期与层数、订单到达率相关,层数越多,订单到达率越低,转载车系统相对于环线系统越具优势。     

Expert system for problem solving in distance university education: The successful case of the subject “operations management”

Acquiring the skills needed to solve certain types of problems is one of the main challenges of distance university education, demanding extra motivation from students to tackle it. New technology should be one of our great allies in addressing these problems. This article proposes an expert system with a web‐based problem‐solving simulator for a multidevice environment in order to allow students to access an unlimited number of problems with their corresponding solutions, immediately, anytime and anywhere. The types of problems that can be used are those based on quantitative methods with a fixed methodology to be followed. A successful case study was carried out for the subject Operations Management at the Distance University of Madrid (UDIMA), with three different problem simulators having been developed. The results were very satisfactory compared with previous academic years in terms of motivation. A decrease in students that did not sit the final examination was observed, as was an increase in the number of visits to the Moodle classroom. Students also responded positively in their assessments of the initiative.     

基于文本与语义相关性分析的图像检索

为了更加有效地检索到符合用户复杂语义需求的图像，提出一种基于文本描述与语义相关性分析的图像检索算法。该方法将图像检索分为两步：基于文本语义相关性分析的图像检索和基于SIFT特征的相似图像扩展检索。根据自然语言处理技术分析得到用户文本需求中的关键词及其语义关联，在选定图像库中通过语义相关性分析得到“种子”图像；接下来在图像扩展检索中，采用基于SIFT特征的相似图像检索，利用之前得到的“种子”图像作为查询条件，在网络图像库中进行扩展检索，并在结果集上根据两次检索的图像相似度进行排序输出，最终得到更加丰富有效的图像检索结果。为了证明算法的有效性，在标准数据集Corel5K和网络数据集Deriantart8K上完成了多组实验，实验结果证明该方法能够得到较为精确地符合用户语义要求的图像检索结果，并且通过扩展算法可以得到更加丰富的检索结果。     

结合细粒度特征与深度卷积网络的手绘图检索

目的 传统的手绘图像检索方法主要集中在检索相同类别的图像，忽略了手绘图像的细粒度特征。对此，提出了一种新的结合细粒度特征与深度卷积网络的手绘图像检索方法，既注重通过深度跨域实现整体匹配，也实现细粒度细节匹配。方法 首先构建多通道混合卷积神经网络，对手绘图像和自然图像分别进行不同的处理；其次通过在网络中加入注意力模型来获取细粒度特征；最后将粗细特征融合，进行相似性度量，得到检索结果。结果 在不同的数据库上进行实验，与传统的尺度不变特征（SIFT）、方向梯度直方图（HOG）和深度手绘模型Deep SaN（sketch-a-net）、Deep 3DS（sketch）、Deep TSN（triplet sketch net）等5种基准方法进行比较，选取了Top-1和Top-10，在鞋子数据集上，本文方法Top-1正确率提升了12%，在椅子数据集上，本文方法Top-1正确率提升了11%，Top-10提升了3%，与传统的手绘检索方法相比，本文方法得到了更高的准确率。在实验中，本文方法通过手绘图像能在第1幅检索出绝大多数的目标图像，达到了实例级别手绘检索的目的。结论 提出了一种新的手绘图像检索方法，为手绘图像和自然图像的跨域检索提供了一种新思路，进行实例级别的手绘检索，与原有的方法相比，检索精度得到明显提升，证明了本文方法的可行性。