Title: Object Detection at the Optimal Scale with Hidden State Shape
Models
Authors: Jingbin Wang, Vassilis Athitsos, Stan Sclaroff, Margrit
Betke
Date: October 2, 2006
Abstract: Hidden State Shape Models (HSSMs), a variant of Hidden Markov
Models (HMMs), were proposed to detect shape classes of variable structure
in cluttered images. In this paper, we formulate a probabilistic framework
for HSSMs which solves two scale related problems in comparison to the
original method. First, while HSSMs required the scale of the object to be
passed as an input, the method proposed here estimates the scale of the
object automatically. This is achieved by introducing a new term for the
observation probability that is based on a object-clutter feature model.
Second, a segmental HMM is applied to model the duration probability of
each HMM state, which is learned from the shape statistics in a training
set and helps obtain meaningful registration results. Using a segmental
HMM provides a principled way to model dependencies between the scales of
different parts of the object. In object localization experiments on a
dataset of real hand images, the proposed method significantly outperforms
the original HSSMs, reducing the incorrect localization rate from 40% to
15%. The improvement in accuracy becomes more significant if we consider
that the method proposed here is scale-independent, whereas the previous
method takes as input the scale of the object we want to localize.