Reflectance based object recognition

Shree K. Nayar

doi:10.1007/BF00128232

1996-03-01

140

PRE

Shree K. Nayar *

Ruud M. Bolle

DOI：10.1007/BF00128232

原文链接

原文求助

摘要

En 中文

Neighboring points on a smoothly curved surface have similar surface normals and illumination conditions. Therefore, their brightness values can be used to compute the ratio of their reflectance coefficients. Based on this observation, we develop an algorithm that estimates a reflectance ratio for each region in an image with respect to its background. The algorithm is efficient as it computes ratios for all image regions in just two raster scans. The region reflectance ratio represents a physical property that is invariant to illumination and imaging parameters. Several experiments are conducted to demonstrate the accuracy and robustness of ratio invariant. The ratio invariant is used to recognize objects from a single brightness image of a scene. Object models are automatically acquired and represented using a hash table. Recognition and pose estimation algorithms are presented that use ratio estimates of scene regions as well as their geometric properties to index the hash table. The result is a hypothesis for the existence of an object in the image. This hypothesis is verified using the ratios and locations of other regions in the scene. This approach to recognition is effective for objects with printed characters and pictures. Recognition experiments are conducted on images with illumination variations, occlusions, and shadows. The paper is concluded with a discussion on the simultaneous use of reflectance and geometry for visual perception.

Keyword:

object representation

physical properties

retinex theory

reflectance ratio

photometric invariant

region ratios

indexing

model acquisition

object recognition

pose estimation