RIA: Deformable Kernel Filtering for Early Visual Processing

在视觉分析的第一步中，分析早期视觉、简单图像属性，如亮度、颜色、纹理、立体视差、运动模式，并测量和提取图像的边界、线和其他显著的视觉结构。许多理论和经验论证表明，所有早期视觉任务都可能通过共享共同计算结构的算法来完成：与不同方向、尺度和形状的核进行卷积，然后进行简单的准局部非线性运算。这样的核可以被生成为从任务规范合成的模板核的变形(旋转、缩放、拉伸)。在过去的两年里，一种基于奇异值分解(SVD)的方法被提出，以使这种连续参数滤波变得可行--它已被证明用于二维旋转和缩放。本研究致力于(1)在包括3D旋转、缩放、拉伸和曲率变化的新情况下演示该方法；(2)将该方法应用于各种早期视觉任务的滤镜生成，包括纹理和运动分析；(3)探索基于连续参数滤波的新的早期视觉算法；(4)了解滤镜设计技术与奇异值分解方法之间的联系。//

In the first step of visual analysis, early vision, simple image properties such as brightness, color, texture, stereoscopic disparity, motion patterns are analyzed and boundaries, lines, and other salient visual structures of the image are measured and extracted. A number of theoretical and empirical arguments point to the possibility that all early vision tasks may be accomplished by algorithms sharing a common computational structure: convolution with kernels of different orientations, scales, and shapes followed by simple quasi-local nonlinear operations. Such kernals may be generated as deformations (rotations, scalings stretchings) of a template kernel which is synthesized from task specifications. In the last two years a method based on singular value decomposition (SVD) has been proposed to make such continuous-parameter filtering feasible- it has been demonstrated for rotations and scaling in 2 dimensions. This research endeavours to(1) demonstrate the method in new situations including 3D rotations and scalings stretchings and changes of curvature, (2) apply the method to generating filters for various early vision tasks including texture and motion analysis, (3) explore new early vision algorithms made possible by continuous-parameter filtering, (4) understand the connections between filter-design techniques and the SVD method. //