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

SigNet is a state of the art model for feature representation used forhandwritten signature verification (HSV). This representation is based on aDeep Convolutional Neural Network (DCNN) and contains 2048 dimensions. Whentransposed to a dissimilarity space generated by the dichotomy transformation(DT), related to the writer-independent (WI) approach, these features mayinclude redundant information. This paper investigates the presence ofoverfitting when using Binary Particle Swarm Optimization (BPSO) to perform thefeature selection in a wrapper mode. We proposed a method based on a globalvalidation strategy with an external archive to control overfitting during thesearch for the most discriminant representation. Moreover, an investigation isalso carried out to evaluate the use of the selected features in a transferlearning context. The analysis is carried out on a writer-independent approachon the CEDAR, MCYT and GPDS datasets. The experimental results showed thepresence of overfitting when no validation is used during the optimizationprocess and the improvement when the global validation strategy with anexternal archive is used. Also, the space generated after feature selection canbe used in a transfer learning context.

An Investigation of Feature Selection and Transfer Learning for Writer-Independent Offline Handwritten Signature Verification