Sciweavers

Share
ICDAR
2007
IEEE

A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images

10 years 4 months ago
A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images
We describe an unsupervised learning algorithm for extracting sparse and locally shift-invariant features. We also devise a principled procedure for learning hierarchies of invariant features. Each feature detector is composed of a set of trainable convolutional filters followed by a max-pooling layer over non-overlapping windows, and a point-wise sigmoid non-linearity. A second stage of more invariant features is fed with patches provided by the first stage feature extractor, and is trained in the same way. The method is used to pre-train the first four layers of a deep convolutional network which achieves state-of-the-art performance on the MNIST dataset of handwritten digits. The final testing error rate is equal to 0.42%. Preliminary experiments on compression of bitonal document images show very promising results in terms of compression ratio and reconstruction error.
Marc'Aurelio Ranzato, Yann LeCun
Added 03 Jun 2010
Updated 03 Jun 2010
Type Conference
Year 2007
Where ICDAR
Authors Marc'Aurelio Ranzato, Yann LeCun
Comments (0)
books