复杂环境下基于角点回归的全卷积神经网络的车牌定位

车牌定位是车牌识别系统中核心部分,具有较高的研究和应用价值。尽管近些年来该研究取得了很大的进展,但仍无法很好地解决低亮度、低分辨率和车辆倾斜等环境下的定位问题。本文提出了一种新的全卷积神经网络,通过回归车牌角点的方式准确地进行车牌定位。为了保证训练的有效性,对45 000幅含有车牌的图像进行人工标注。同时,对标注的图像随机进行平移、缩放、旋转和加噪,提高训练样本的数量和多样性。在本文构建的卡口图像数据集和复杂环境数据集上与两种方法进行了比较,验证了本文方法的有效性。     

局部不变特征点的精度指标

目的 作为计算机视觉的热门研究方向,局部不变特征算法的发展已趋于成熟、稳定,然而目前几乎所有特征点提取算法都没有给出特征点的精度指标.针对这一缺陷,提出一种特征点精度指标-特征点波动区间.方法 性质稳定的点在干扰条件下仍具有较好的精度,即小范围的波动区间,因此,以当前最热门的SIFT(scale-invariant feature transform)特征点为例,在图像加入噪声,发生光照变换,发生模糊变换以及同时进行噪声、光照及模糊处理这四种情况下分别分析同一算法提取的不同特征点的波动情况,进而得到不同特征点的波动区间.结果 实验得到16个稳定检出特征点,其中点2,3,4,11,13这5个点可以在不同干扰条件下的波动范围都较小,而点2则只在模糊条件下波动较小,在其余干扰下波动较大.特征点虽然已经过特征提取,但仍具有不同的波动区间,其优劣也不尽相同.不同的特征点的波动区间并不相同,但仍有一部分特征点在不同干扰条件下均保持较高的提取精度.结论 波动区间能很好地表征每个特征点的提取精度.由于此前只有针对特征点算法的评价指标,而没有针对特征点自身性质的评价方法,因此本文提出的特征点波动区间将为诸如设备标定、视觉测量、精简特征库等相关后续工作打下良好基础.     

CRF和词典相结合的蒙古文地名识别研究

蒙古语在命名实体识别方面开展过人名的识别,但在地名的识别方面还没有开展相应的研究。首次实现了基于条件随机场模型的蒙古文地名识别。首先从蒙古语黏着性特点分析入手,研究了蒙古语语料库中地名的存在形式以及各类地名的特点,针对蒙古语语料库中地名的特点,在词汇特征、指示词特征、特征词特征等特征基础上引入了词性特征。之后通过地名词典补召了未识别的地名。以内蒙古大学开发的100万词规模的标注语料库为训练数据,该模型的地名识别性能达到了94.68%的准确率、84.40%的召回率和89.24%的F值。     

一种云存储环境下保障数据机密性的方法

为保证用户数据的机密性,业界普遍将数据加密后存储在云端。提出了一种云存储系统中保障数据机密性的方法,其特点有:(1)加解密系统部署于云存储服务器的前端,在客户端和云存储服务器之间对用户数据进行加解密;(2)对用户数据的加解密是实时进行的,在数据上传的传输过程中进行加密,在数据下载的传输过程中进行解密;(3)加解密系统对用户端和云服务器端是透明的。当前广泛使用的基于HTTP协议传输的云存储系统如Amazon S3、OpenStack Swift等可以直接使用该方法。测试结果表明:本方法在不降低数据传输吞吐率的基础上,能有效卸载云存储系统的数据加解密负担。     

Seniors and Information Technology in China

Technology, particularly information technology (IT), is changing rapidly and offers many advantages for users. IT has the potential to improve one’s quality of life, but only if used. Research has shown that, in most developed and developing nations, senior use of IT lags behind that of other segments of society. This “gray divide” is a concern for government, business, and others. Concern about senior adoption and use of IT has been the motivation for numerous studies and is the motivation for this study of Chinese seniors. This exploratory study examines urban Chinese seniors’ IT use, computers and mobile phones in particular, but also their attitudes and behaviors as they relate to the use of those devices. More specifically it examines several potential factors that motivate or hinder senior’s use of information technology, including self-efficacy, satisfaction, comfort with technology, and both positive and negative attitudes. This study provides some insight into the quantity and diversity of Chinese senior technology use in urban China. Particularly noteworthy, the study found that technology ownership was quite high, and in general the Chinese seniors studied had positive attitudes and beliefs concerning information technology. This is generally good news for the Chinese government, which must efficiently provide services for the growing population of Chinese seniors, as well as for businesses that wish to capitalize on one of the largest senior populations in the world.     

A timing controller embedded driver IC with 3.24‐Gbps eDP interface for chip‐on‐glass TFT‐LCD applications

This paper presents a timing controller embedded driver (TED) IC with 3.24‐Gbps embedded display port (eDP), which is implemented using a 45‐nm high‐voltage CMOS process for the chip‐on‐glass (COG) TFT‐LCD applications. The proposed TED‐IC employs the input offset calibration scheme, the zero‐adjustable equalizer, and the phase locked loop‐based bang‐bang clock and data recovery to enhance the maximum data rate. Also, the proposed TED‐IC provides efficient power management by supporting advanced link power management feature of eDP standard v1.4. Additionally, the smart charge sharing is proposed to reduce the dynamic power consumption of output buffers. Measured result demonstrates the maximum data rate of 3.24 Gbps from a 1.1 V supply voltage with a 7.9‐inch QXGA 60‐Hz COG‐LCD prototype panel and 44% power saving from the display system.     

Two‐way multi‐view 2‐D/3‐D display combining LC lens and HVxDP panel using novel pixel arrangement

We have developed a two‐way multi‐view 2‐D/3‐D display combining a liquid crystal lens and horizontally and vertically x times‐density pixels (HVxDP) arrangement. The two‐way multi‐view display features the same display resolution in 2‐D and 3‐D modes and a quite small color moiré for landscape and portrait, respectively, when using the HVxDP arrangement. In this paper, we realized suitable 3‐D properties for achieving a good balance between 3‐D moiré and 3‐D crosstalk for landscape and portrait by a two‐way liquid crystal lens with two kinds of focal lengths for the edge part and the center part of the lens.     

Rendering of HDR images to improve brightness discrimination

The impression of quality of images can be enhanced on a high dynamic range (HDR) displays. Generally, a conventional 8‐bit image can be processed to an HDR image by inverse tone mapping operators. Among the operators, brightness discrimination mapping by applying brightness adaptation model attempted to mimic the human visual system. In this paper, we use a brightness adaptation model to derive a brightness discrimination mapping algorithm for HDR displays. The proposed algorithm maximizes a function, which represents the local and global brightness discrimination range by exploiting characteristics of the human visual system. Enhancement of details is verified by visualizing HDR images from dark to bright regions. Improvement of dynamic range is quantified by measuring increased discrimination ratio.     

High-quality image restoration from partial mixed adaptive-random measurements

A novel framework to construct an efficient sensing (measurement) matrix, called mixed adaptive-random (MAR) matrix, is introduced for directly acquiring a compressed image representation. The mixed sampling (sensing) procedure hybridizes adaptive edge measurements extracted from a low-resolution image with uniform random measurements predefined for the high-resolution image to be recovered. The mixed sensing matrix seamlessly captures important information of an image, and meanwhile approximately satisfies the restricted isometry property. To recover the high-resolution image from MAR measurements, the total variation algorithm based on the compressive sensing theory is employed for solving the Lagrangian regularization problem. Both peak signal-to-noise ratio and structural similarity results demonstrate the MAR sensing framework shows much better recovery performance than the completely random sensing one. The work is particularly helpful for high-performance and lost-cost data acquisition.     

Towards understanding the gamification upon users’ scores in a location-based social network

Online social platform, such as Wikipedia and Foursquare, has been increasingly exploded due to not only various useful services provided but also social gaming mechanisms that can keep users actively engaged. For example, users are awarded ”virtual goods” like badges and points when they contribute to the community in the network by voluntarily sharing ideas and other information. In this paper, we aim to examine the effectiveness of a social gamification mechanism, named user scores, designed in Foursquare which is one of most popular location-based social networks. A user’s score in Foursquare is an aggregate measure based on recent check-in activities of the user, which reflects a snapshot summary of the user’s temporal and spatial behaviors. Whenever a user checks in to a venue, a list of scores of the user’s friends are visible to the user via a ”leaderboard” which ranks these users’ scores in a descending order. Given a pair of friends who participate in a score competition in such a gimification mechanism, we identify if one user’s scores have significant influence on the other user’s scores by utilizing the Granger Causality Test. To understand what types of users and what types of friends tend to participate in the score competition (i.e., their check-ins are more likely driven by such a gamification mechanism), we extract users’ features (e.g. user’s degree) as well as the features of pairs of friends (e.g., number of common friends, score similarity and ranking difference) to examine whether these features have correlations with those pairs of users who are identified as being involved in the score game. The identified influence on user scores has the important implication on applications including friend and venue recommendations in location-based social networks.