搜索结果: 46-60 共查到“知识库 计算机图象处理”相关记录2947条 . 查询时间(4.172 秒)
Incorporation of a-priori information in planning the next best view
Optical Three-dimensional Measurement Close Range Acquisition Planning Automation
2015/8/25
The widespread use of optical 3D measurement in inspection and prototyping continues to demand improved strategies for planning the next best view (NBV). During the scanning process, better viewpoints...
THE IMAGE INTEGRATED DATABASE FOR WEATHER STUDY USING MT. SAKURAJIMA
Observations Volcanoe Meteorology
2015/8/24
Mt. Sakurajima is a volcano located about 10km east from Kagoshima University. We are continuing observation of this Sakurajima
volcano with a web camera since December 2000. The picture is taken fr...
为了保留图像分析时的像素点位置关系及降维处理,把一维压缩感知理论推广到二维,建立了二维可稀疏信号的压缩测量模型,研究了一种二维信号的自适应梯度下降重构AGDR(Adaptive Gradient Descent Recursion)算法,由此提出了一种图像分层特征提取与检索方法.首先对图像在RGB颜色空间上进行网格离散划分,通过分层算子对图像进行分层映射,定义一种基于颜色网格空间的扩展灰度共生矩阵...
Accurate and robust image superresolution by neural processing of local image representations
superresolution neural networks image sequence processing
2015/7/29
Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require iterative minimization ...
Kriging插值算法被广泛应用于地学各领域，有着极其重要的现实意义，但在面对大规模输出网格及大量输入采样点时，不可避免地遇到了性能瓶颈。利用OpenCL和OpenMP在异构平台上实现了CPU与GPU协同加速普通Kriging插值。针对Kriging插值中采样点的不规则分布及CPU和GPU由于体系结构差异对其的不同适应性，提出一种基于不同设备间计算性能的差异和数据分布特点的负载均衡方法。试验结果表...
八通道MSVD构造及其在多聚焦图像融合中的应用
图像融合 矩阵奇异值分解 多尺度分析 多聚焦图像
2016/12/29
针对经典的SVD在图像处理中的不足,提出了一种八通道多尺度奇异值分解(Multi-resolution Singular Value Decomposition,MSVD)构造方法,并把它应用于多聚焦图像融合中.首先,在经典SVD的基础上,利用矩阵分块的方法,提出了一种八通道多尺度SVD的构造方法.其次,对参加融合的多聚焦图像进行八通道MSVD分解,得到高层低频和各层七个方向的高频,对分解的低频子...
AUTOMATED UPDATE OF ROAD DATABASES USING AERIAL IMAGERY AND ROAD CONSTRUCTION DATA
Change Detection Database GIS Imagery
2015/5/18
The update of geodata is an important task in order to ensure a high level of data quality in Geographic Information Systems (GIS).
Today, this work is carried out mostly manually by an operator, who...
针对交互式图像分割人工标记示例匮乏、不同目标区域难以均衡标记,单一分类器难以获得有效分割结果的问题,提出一种多分类器集成学习的交互式图像分割方法.采用多元自适应回归样条(MARS)方法构造第一个分类器;同时引入光滑薄板样条回归函数(TPSR)构造与之互补的第二个分类器,综合组成bagging集成学习器,以降低单一分类器对噪声的敏感度并进一步提高人工标记样本特征空间的利用率.随后,基于半监督学习中的...
Performance analysis of EM-MPM and K-means clustering in 3D ultrasound breast image segmentation
segmentation EM-MPM ultrasound
2015/1/20
Mammographic density is an important risk factor for breast cancer, detecting and screening at an early stage could help save lives. To analyze breast density distribution, a good segmentation algorit...
Multiresolution image fusion is an emerging area of research for use in military and commercial applications. While many methods for image fusion have been developed, improvements can still be made. I...
3D ENDOSCOPY VIDEO GENERATED USING DEPTH INFERENCE: CONVERTING 2D TO 3D
image processing computer vision 3d endoscopy converting 2d to 3d
2015/1/20
A novel algorithm was developed to convert raw 2-dimensional endoscope videos into 3-dimensional view. Minimally invasive surgeries aided with 3D view of the invivo site have shown to reduce errors an...
3D EM/MPM MEDICAL IMAGE SEGMENTATION USING AN FPGA EMBEDDED DESIGN IMPLEMENTATION
FPGA 3D image
2015/1/20
This thesis presents a Field Programmable Gate Array (FPGA) based embedded system which is used to achieve high speed segmentation of 3D images. Segmenta- tion is performed using Expectation-Maximizat...
3D Image Segmentation Implementation on FPGA Using EM/MPM Algorithm
3D Image FPGA Hardware Implementation EM/MPM Algorithm
2015/1/20
In this thesis, 3D image segmentation is targeted to a Xilinx Field Programmable Gate Array (FPGA), and verified with extensive simulation. Segmentation is performed using the Expectation-Maximization...
A Multi-stage Non-cooperative Iris Recognition Approach with Enhanced Template Security
Non-cooperative iris recognition biometric template security
2015/1/20
Biometrics identi es/veri es a person using his/her physiological or behavioral characteristics. It is becoming an important ally for law enforcement and homeland security. Among all the biometric mod...