Semi-supervised object recognition based on Connected Image Transformations

doi:10.1016/j.eswa.2013.06.029

Return

Semi-supervised object recognition based on Connected Image Transformations

2013-12-01

PRE

Steven Van Vaerenbergh *

Ignacio Santamarı́a

Paolo Emilio Barbano

DOI：10.1016/j.eswa.2013.06.029

Original

Original request for help

Save

Abstract

En 中文

We present a novel semi-supervised classifier model based on paths between unlabeled and labeled data through a sequence of local pattern transformations. A reliable measure of path-length is proposed that combines a local dissimilarity measure between consecutive patters along a path with a global, connectivity-based metric. We apply this model to problems of object recognition, for which we propose a practical classification algorithm based on sequences of Connected Image Transformations (CIT). Experimental results on four popular image benchmarks demonstrate how the proposed CIT classifier outperforms state-of-the-art semi-supervised techniques. The results are particularly significant when only a very small number of labeled patterns is available: the proposed algorithm obtains a generalization error of 4.57% on the MNIST data set trained on 2000 randomly chosen patterns with only 10 labeled patterns per digit class. (C) 2013 Elsevier Ltd. All rights reserved.

Keywords:

Semi-supervised classification

Object recognition

Connectivity

Deformation models

Low-density separation

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.