Napredna pretraga

Pregled bibliografske jedinice broj: 607022

Improving Offline Handwritten Digit Recognition Using Concavity-based Features


Karić, Miran; Martinović, Goran
Improving Offline Handwritten Digit Recognition Using Concavity-based Features // International Journal of Computers Communications & Control, 8 (2013), 2; 206-219 (međunarodna recenzija, članak, znanstveni)


Naslov
Improving Offline Handwritten Digit Recognition Using Concavity-based Features

Autori
Karić, Miran ; Martinović, Goran

Izvornik
International Journal of Computers Communications & Control (1841-9836) 8 (2013), 2; 206-219

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Complementary features; concavity features; digit recognition; feature extraction; handwritten character recognition; off-line recognition

Sažetak
This paper examines benefits of using concavity-based structural features in recognition of handwritten digits. An overview of existing concavity features is presented and a new method is introduced. These features are used as complementary features to gradient and chaincode features, both among the best performing features in handwritten digit recognition. Two support vector classifiers (SVCs) are chosen for classification task as the top performers in previous works ; SVC with radial basis function (RBF) kernel and the SVC with polynomial kernel. For reference, we also used the k-nearest neighbor (k-NN) classifier. Results are obtained on MNIST, USPS and DIGITS datasets. We also tested dataset independency of various feature vectors by combining different datasets. The introduced feature extraction method gives the best results in majority of tests.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekt / tema
165-0361621-2000 - Distribuirano računalno upravljanje u transportu i industrijskim pogonima (Željko Hocenski, )
165-0362980-2002 - Postupci raspoređivanja u samoodrživim raspodijeljenim računalnim sustavima (Goran Martinović, )

Ustanove
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek

Časopis indeksira:


  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Uključenost u ostale bibliografske baze podataka:


  • INSPEC
  • Scopus