Semi-supervised handwritten digit recognition using very few labeled data

We propose a novel semi-supervised classifier for handwritten digit recognition problems that is based on the assumption that any digit can be obtained as a slight transformation of another sufficiently close digit. Given a number of labeled and unlabeled images, it is possible to determine the class membership of each unlabeled image by creating a sequence of such image transformations that connect it, through other unlabeled images, to a labeled image. In order to measure the total transformation, a robust and reliable metric of the path length is proposed, which combines a local dissimilarity between consecutive images along the path with a global connectivity-based metric. For the local dissimilarity we use a symmetrized version of the zero-order image deformation model (IDM) proposed by Keysers et al. in [1]. For the global distance we use a connectivity-based metric proposed by Chapelle and Zien in [2]. Experimental results on the MNIST benchmark indicate that the proposed cla...

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Steven Van Vaerenbergh, Ignacio Santamaría, Paolo Emilio Barbano
• Keywords: ICASSP 2011, Image, Local Dissimilarity, Signal Processing, Unlabeled Images