Transformation-Invariant Embedding for Image Analysis

Abstract. Dimensionality reduction is an essential aspect of visual processing. Traditionally, linear dimensionality reduction techniques such as principle components analysis have been used to find low dimensional linear subspaces in visual data. However, sub-manifolds in natural data are rarely linear, and consequently many recent techniques have been developed for discovering non-linear manifolds. Prominent among these are Local Linear Embedding and Isomap. Unfortunately, such techniques currently use a naive appearance model that judges image similarity based solely on Euclidean distance. In visual data, Euclidean distances rarely correspond to a meaningful perceptual difference between nearby images. In this paper, we attempt to improve the quality of manifold inference techniques for visual data by modeling local neighborhoods in terms of natural transformations between images--for example, by allowing image operations that extend simple differences and linear combinations. We in...

• Type: Conference
• Year: 2004
• Where: ECCV
• Authors: Ali Ghodsi, Jiayuan Huang, Dale Schuurmans
• Keywords: Computer Vision, Dimensional Linear Subspaces, Dimensionality Reduction Techniques, ECCV 2004, Local Linear Embedding, Manifold Inference Techniques, Visual Data