Extracting orientation and scale from smoothly varying textures with application to segmentation

[摘要] (cont.) Additionally, segmentation results and methods for comparing the utility of the different measures are presented. This thesis also considers a novel texture model for representing textured regions with smooth variations in orientation and scale. By utilizing the steerable pyramid of Simoncelli and Freeman, the textured regions of natural images are decomposed into explicit local attributes of contrast, bias, scale, and orientation. Once found, smoothness in these attributes are imposed via estimation of Markov random fields. This combination allows for demonstrable improvements in common scene analysis applications including segmentation, reflectance and shading estimation, and estimation of the radiometric response function from a single grayscale image.

[发布机构] Massachusetts Institute of Technology