基于差值区域的实时人脸定位

为了解决红外图像人脸跟踪鲁棒性差的问题,提出一种基于差值区域的实时人脸检测和定位方法,该方法主要是利用改进帧间差分法得到一帧差分图像,然后对差分图像进行预处理,确定"类"瞳孔的位置,进而标记出人脸差值区域,对该区域归一化后应用AdaBoost方法进行验证,从而得到人脸的准确定位。研究结果证明:该系统定位方法比直接应用AdaBoost方法有更好的实时性,该方法的各个环节都满足实时性要求,为红外条件下的人脸跟踪系统提供了有效的解决方案。

Temporal and spatial differences and imbalance of China's urbanization development during 1950-2006

A better understanding of the regional disparity and imbalance characteristics of China's urbanization development is the important premise for constituting correct policy and strategy and promoting the healthy and sustainable development of urbanization in the 21st century. The regional differences of China's urbanization level have close relations with natural conditions of landform and climate etc.,the urbanization level reduces with the eleva-tion of topography and decrease of precipitation. According to the statistical data set of ur-banization in 1950-2006,the temporal change course of inter-provincial disparity of Chinese urbanization level since the founding of New China in 1949 was studied,and then the inter-regional and intra-regional disparities of urbanization development were analyzed by the Theil index and its nested decomposition method,to grasp the dynamic change of spatial disparities of China's urbanization level on the whole. Using the imbalance index model,the imbalance status of urban population distribution relative to total population,grain output,total agricultural output value,gross output value of industry,tertiary industrial output value as well as gross regional product was discussed,to hold the balance characteristics of urbanization development relative to the regional development conditions from the macroscopic scales.

基于形变模型的三维人脸建模方法概述

提出一种改进的分区域差值算法,能有效的缩短一般人脸模型的轮廓变换时间。在图像拼接算法中,使用新的加权因子,使重叠区域能平稳的过渡,并且不出现亮度跃变现象。采用新的全视角人脸纹理生成流程,使人脸纹理更加逼真。实验证明,这些改进使三维人脸重建在时间和真实感方面均有较明显的提高。

Trends and Regional Variations in Carbon Productivity across China

This paper utilizes the Theil and decoupling indices to analyze variation in carbon productivity as well as the factors that influence regional carbon productivity in China and proposes carbon emission reduction countermeasures. The authors conclude that most provinces exhibit year-on-year rising carbon productivity, a trend which decreases moving from east to western China. When applied to carbon productivity, the Theil index presents distinct regional differences. Moreover, the regional variance in carbon productivity is consistently reduced in eastern China and becomes smaller in central China. The difference, however, grows in western China. Carbon productivity grows with the highest speed in central China and the lowest speed in western China. Overall variation in carbon productivity mainly arises from intra-regional difference, whereas inter-regional difference mainly contributed by eastern China. In recent years; both the decoupling index, a dynamic value equal to the rate of change rate in carbon emissions divided by the rate of change in GDP during a given period of time, and carbon productivity vary in different economic development stages. Even if under the same decoupling state, carbon productivity remains different in three regions, i.e., that of the eastern region is higher than the other two regions .

基于非下采样剪切波变换的医学图像边缘融合算法研究

图像融合过程中时常存在边缘点严重丢失的情况,为了解决这一问题,改善图像融合后的效果,本文提出了一种新的非下采样剪切波变换(NSST)融合算法。首先,将已配准的医学图像利用剪切波分解成一系列高低频子带系数;然后,利用区域最大差值比较法融合低频系数,高频系数则利用改进边缘能量法和边缘强度法进行融合;最后,通过剪切波逆变换实现对融合系数的重构得到融合图像,并选择信息熵(IE),缘强度(ES),空间频率(SF),标准差(SD)四个参数来评价融合后的图像;与其余四种算法相比,本文算法融合效果较好,在空间频率以及边缘强度指标上表现尤为突出,其余指标处于中上水平;与刘健提出的基于改进型NSST变换的图像融合方法相比,4组实验空间频率分别提高了6.4%,9.2%,1.4%,2.5%,标准差分别提高了1.8%,-1.1%,6.7%,-0.8%;信息熵分别提高了-0.8%,1.4%,-0.8%,0.5%;边缘强度分别提高了2.8%,0.6%,1.5%,3.4%。实验结果表明,本算法得到的融合图像在清晰度,对比度以及边缘信息丰富性等方面表现优良,具有良好的应用前景。