Learning of Optimal Illumination for Material Classification

Reflectance Modeling in Machine Vision: Applications in Image Analysis and Synthesis

“…While the benefit of using angular-resolved reflectance measurements instead of single images has previously been reported in the literature (Lindner & Puente León (2007); Jehle et al (2010); Wang et al (2009);Gruna & Beyerer (2011)), using reflectance measurements in combination with modeling and simulating complex machine vision systems is a new research field and has the potential to be subject of future works.…”

“…In a similar approach in Peers et al (2006), heated acrylic is used to roughen the texture of a hemispherical mirror in order to obtain a more diffuse reflection. Another way to solve the problem of inhomogeneous illumination is to use prospective shading correction techniques as employed by Jehle et al (2010).…”

“…To account for geometric dependencies on the measured reflectance, photometric stereo is applied to estimate the surface normal at each pixel and to transform the measurements to the local surface reference frame. Jehle et al (2010) used a random forest classifier to learn optimal illumination directions for material classification by using embedded feature selection. For illumination series acquisition, an illumination device very similar to the one presented in this chapter is used.…”

Learning Discriminative Illumination and Filters for Raw Material Classification with Optimal Projections of Bidirectional Texture Functions

“…The passive approach aims to study material perception in order to classify materials from regular images via statistical learning [1,21,18]. The active approach, especially in machine vision, employs any useful visual features for classification, such as 2D slices of BRDFs [34,13], BRDF projections [9], polarization [3], and spectral reflectance [10,26]. To our knowledge, there has been no prior work using BTF for material classification.…”

“…Our method is closely related to two recent works [9,13] which also seek optimal illumination for material classification. However, they focused on point-wise material classification using BRDF features only.…”