Writer Identification for Handwritten Words
19 Dec 2016-pp 265-276
TL;DR: This work makes use of allographic features at sub-word level to exploit the discriminative properties of features that belong to the same cluster, in a supervised approach, to achieve writer identification rates close to 63% on the handwritten words drawn from a dataset by 10 writers.
Abstract: In this work we present a framework for recognizing writer for a handwritten word. We make use of allographic features at sub-word level. Our work is motivated by previous techniques which make use of a codebook. However, instead of encoding the features using the codewords, we exploit the discriminative properties of features that belong to the same cluster, in a supervised approach. We are able to achieve writer identification rates close to 63% on the handwritten words drawn from a dataset by 10 writers. Our work has application in scenarios where multiple writers write/annotate on the same page.
References
More filters
Book•
03 Jan 19892,878 citations
TL;DR: This paper attempts to eliminate the assumption that the written text is fixed by presenting a novel algorithm for automatic text-independent writer identification by taking a global approach based on texture analysis, where each writer's handwriting is regarded as a different texture.
341 citations
TL;DR: The proposed automatic approach bridges the gap between image-statistics approaches on one end and manually measured allograph features of individual characters on the other end, and revealed a high-sensitivity of the CO/sup 3/ PDF for identifying individual writers on the basis of a single sentence of uppercase characters.
Abstract: In this paper, a new technique for offline writer identification is presented, using connected-component contours (COCOCOs or CO/sup 3/s) in uppercase handwritten samples. In our model, the writer is considered to be characterized by a stochastic pattern generator, producing a family of connected components for the uppercase character set. Using a codebook of CO/sup 3/s from an independent training set of 100 writers, the probability-density function (PDF) of CC's was computed for an independent test set containing 150 unseen writers. Results revealed a high-sensitivity of the CO/sup 3/ PDF for identifying individual writers on the basis of a single sentence of uppercase characters. The proposed automatic approach bridges the gap between image-statistics approaches on one end and manually measured allograph features of individual characters on the other end. Combining the CO/sup 3/ PDF with an independent edge-based orientation and curvature PDF yielded very high correct identification rates.
265 citations
03 Aug 2003
TL;DR: The joint probability distribution of theangle combination of two "hinged" edge fragments outperforms all other individual features and may improve the performance of edge-based directional probability distributions in writer identification procedures.
Abstract: This paper evaluates the performance of edge-based directionalprobability distributions as features in writer identificationin comparison to a number of non-angular features.It is noted that the joint probability distribution of theangle combination of two "hinged" edge fragments outperformsall other individual features. Combining features mayimprove the performance. Limitations of the method pertainto the amount of handwritten material needed in orderto obtain reliable distribution estimates. The global featurestreated in this study are sensitive to major style variation(upper- vs lower case), slant, and forged styles, whichnecessitates the use of other features in realistic forensicwriter identification procedures.
180 citations
25 Aug 2013
TL;DR: A public database for writer retrieval, writer identification and word spotting is presented and an evaluation of the best algorithms of the ICDAR and ICHFR writer identification contest has been performed on the CVL-database.
Abstract: In this paper a public database for writer retrieval, writer identification and word spotting is presented. The CVL-Database consists of 7 different handwritten texts (1 German and 6 English Texts) and 311 different writers. For each text an RGB color image (300 dpi) comprising the handwritten text and the printed text sample are available as well as a cropped version (only handwritten). A unique ID identifies the writer, whereas the bounding boxes for each single word are stored in an XML file. An evaluation of the best algorithms of the ICDAR and ICHFR writer identification contest has been performed on the CVL-database.
164 citations