English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent deep learning based methods have achieved the state-of-the-artperformance for handwritten Chinese character recognition (HCCR) by learningdiscriminative representations directly from raw data. Nevertheless, we believethat the long-and-well investigated domain-specific knowledge should still helpto boost the performance of HCCR. By integrating the traditionalnormalization-cooperated direction-decomposed feature map (directMap) with thedeep convolutional neural network (convNet), we are able to obtain new highestaccuracies for both online and offline HCCR on the ICDAR-2013 competitiondatabase. With this new framework, we can eliminate the needs for dataaugmentation and model ensemble, which are widely used in other systems toachieve their best results. This makes our framework to be efficient andeffective for both training and testing. Furthermore, althoughdirectMap+convNet can achieve the best results and surpass human-levelperformance, we show that writer adaptation in this case is still effective. Anew adaptation layer is proposed to reduce the mismatch between training andtest data on a particular source layer. The adaptation process can beefficiently and effectively implemented in an unsupervised manner. By addingthe adaptation layer into the pre-trained convNet, it can adapt to the newhandwriting styles of particular writers, and the recognition accuracy can befurther improved consistently and significantly. This paper gives an overviewand comparison of recent deep learning based approaches for HCCR, and also setsnew benchmarks for both online and offline HCCR.

Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark