An Additive Latent Feature Model for Transparent Object Recognition

TitleAn Additive Latent Feature Model for Transparent Object Recognition
Publication TypeConference Paper
Year of Publication2009
AuthorsFritz, Mario., Darrell, Trevor., Black, Michael., Bradski, Gary., and Karayev, Sergey
Conference NameNIPS
Date Published12/2009
Keywordsmachine learning, object recognition, transparent objects

Existing methods for recognition of object instances and categories based on quan-
tized local features can perform poorly when local features exist on transparent
surfaces, such as glass or plastic objects. There are characteristic patterns to the
local appearance of transparent objects, but they may not be well captured by dis-
tances to individual examples or by a local pattern codebook obtained by vector
quantization. The appearance of a transparent patch is determined in part by the
refraction of a background pattern through a transparent medium: the energy from
the background usually dominates the patch appearance. We model transparent lo-
cal patch appearance using an additive model of latent factors: background factors
due to scene content, and factors which capture a local edge energy distribution
characteristic of the refraction. We implement our method using a novel LDA-
SIFT formulation which performs LDA prior to any vector quantization step; we
discover latent topics which are characteristic of particular transparent patches and
quantize the SIFT space into transparent visual words according to the latent topic
dimensions. No knowledge of the background scene is required at test time; we
show examples recognizing transparent glasses in a domestic environment.