【摘 要】
：
A novel self-adaptive image denoising model based on scale correlation and Stein’s unbiased risk estimate-linear expansion of thresholds(SURE-LET)in the nonsubsampled contourlet transform domain is pr
【出 处】
：
Science China(Information Sciences)
论文部分内容阅读
A novel self-adaptive image denoising model based on scale correlation and Stein’s unbiased risk estimate-linear expansion of thresholds(SURE-LET)in the nonsubsampled contourlet transform domain is proposed in this paper.First we implement the multidim
其他文献
Currently,plenty of digital image forensic techniques have been proposed and used as diagnostic tools.It is urgent and significant to assess the reliability of such techniques applied in practical sce
In this paper,we address the problem of recognizing human actions from videos.Most of the existing approaches employ low-level features(e.g.,local features and global features)to represent an action v
从科技期刊插图科学表达的角度出发,针对科技期刊中常见的彩色插图直接转化灰度插图所造成的色标歧义、内容表示不清、图文不一致等问题,结合具体插图案例,分别将错误的图与正确的图的表达方式进行了对比。将彩图分为必须彩色印刷的插图、可渐进转化为灰度的插图、可变通处理的插图三种情况,并分别提出了相应的处理方法。
Vision navigation based on scene matching between real-time images and a reference image has many advantages over the commonly used inertial navigation system(INS),such as no cumulative measurement er
Hand-biometric-based personal identification is considered to be an effective method for automatic recognition. However, existing systems require strict constraints during data acquisition, such as co
系统分析了基于AS3992芯片的RFID系统中的关键技术—阻抗匹配。应用ADS仿真工具,设计了全套的AS3992阻抗匹配方案,仿真得到的功率在30 dbm以上。用频谱仪对设计方案进行验证,测得的发射功率在30 dbm以上,最后用RFID标签实测,应用该匹配方案的RFID系统读取距离达到9 m。
为在特征融合中综合利用数据的类别信息和数据结构中所蕴含的自然鉴别信息,提出一种基于局部稀疏表示和线性鉴别分析的典型相关分析算法.首先利用局部稀疏表示模型,以较小的计算复杂度获取局部稀疏重构矩阵;然后在典型相关分析的框架中实现对局部稀疏结构保持、线性鉴别分析和组合特征相关性的联合优化,增强了融合特征的鉴别能力.在人工数据、多特征手写字数据、人脸数据上的实验表明了所提出方法的有效性.
由于指纹识别技术不断完善和趋于成熟,使其在现代化的智能楼宇管理系统中得到了广泛的应用。介绍了指纹识别模块的硬件结构和指纹识别算法的软件流程,详细研究了在智能电梯的呼梯系统中指纹呼梯的工作过程,实现了呼梯系统的指纹识别功能,丰富了现代化大厦的管理和检测途径,为智能楼宇的安防措施提供了更加可靠的保证。
提出一种融合Gabor小波纹理特征与颜色特征的改进mean shift目标跟踪算法.首先,提取移动目标的颜色特征和纹理特征直方图;其次,基于mean shift算法定义融合相似度系数,对特征空间进行融合并得出目标中心位置;再次,通过定义特征自适应系数来融合基于颜色和纹理特征的目标位置;最后,对上述结果进行处理,得到目标最终位置.实验结果表明,该算法在跟踪目标存在变形、噪声、遮挡时能够得到比较理想的
Achieving convincing visual consistency between virtual objects and a real scene mainly relies on the lighting effects of virtual-real composition scenes.The problem becomes more challenging in lighti