Writer identification using oriented Basic Image Features and the Delta encoding

• We present a full description of the oBIF Column method as applied to writer identification.
• We evaluate the oBIF Column encoding scheme using the IAM dataset, producing a performance of 99% for 301 writers.
• We present the Delta encoding, an addition to the oBIF Column scheme.
• We evaluate the Delta encoding using two leading international competitions, gaining first place in both.
• We show how our method uses different sources of information.

We describe how oriented Basic Image Feature Columns (oBIF Columns) can be used for writer identification and how this texture-based scheme can be enhanced by encoding a writer's style as the deviation from the mean encoding for a population of writers. We hypothesise that this deviation, the Delta encoding, provides a more informative encoding than the texture-based encoding alone. The methods have been evaluated using the IAM dataset and by making entries to two top international competitions for assessing the state-of-the-art in writer identification. We demonstrate that the oBIF Column scheme on its own is sufficient to gain a performance level of 99% when tested using 300 writers from the IAM dataset. However, on the more challenging competition datasets, significantly improved performance was obtained using the Delta encoding scheme, which achieved first place in both competitions. In our characterisation of the Delta encoding, we demonstrate that the method is making use of information contained in the correlation between the written style of different textual elements, which may not be used by other methods.