Semi-supervised Feature Learning For Improving Writer Identification
release_6asi7sqgqfcrbeuz3rltoxc2oi
by
Shiming Chen, Yisong Wang, Chin-Teng Lin, Weiping Ding, Zehong Cao
2018
Abstract
Data augmentation is usually used by supervised learning approaches for
offline writer identification, but such approaches require extra training data
and potentially lead to overfitting errors. In this study, a semi-supervised
feature learning pipeline was proposed to improve the performance of writer
identification by training with extra unlabeled data and the original labeled
data simultaneously. Specifically, we proposed a weighted label smoothing
regularization (WLSR) method for data augmentation, which assigned the weighted
uniform label distribution to the extra unlabeled data. The WLSR method could
regularize the convolutional neural network (CNN) baseline to allow more
discriminative features to be learned to represent the properties of different
writing styles. The experimental results on well-known benchmark datasets
(ICDAR2013 and CVL) showed that our proposed semi-supervised feature learning
approach could significantly improve the baseline measurement and perform
competitively with existing writer identification approaches. Our findings
provide new insights into offline write identification.
In text/plain
format
Archived Content
There are no accessible files associated with this release. You could check other releases for this work for an accessible version.
Know of a fulltext copy of on the public web? Submit a URL and we will archive it
1807.05490v2
access all versions, variants, and formats of this works (eg, pre-prints)