Matches in SemOpenAlex for { <https://semopenalex.org/work/W2278731850> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2278731850 endingPage "53" @default.
- W2278731850 startingPage "34" @default.
- W2278731850 abstract "This paper describes a technique using Support Vector (SVM) and Extreme Learning Machines (ELM) for automatic recognition of off-line handwritten Arabic (Indian) numerals. The features of angle, distance, horizontal, and vertical span are extracted from these numerals. The database has 44 writers with 48 samples of each digit totaling 21120 samples. A two-stage exhaustive parameter estimation technique is used to estimate the best values for the SVM parameters for this application. For SVM parameter estimation, the database is split into 4 subsets: three were used in training and validation in turn, and the fourth for testing. The SVM and ELM classifiers were trained with 75% of the data (i.e. the first 33 writers) and tested with the remaining data (i.e. writers 34 to 44) by using the estimated parameters. The recognition rates of SVM and ELM classifiers at the digit and writers’ levels are compared. The training and testing times of SVM and ELM indicate that ELM is much faster to train and test than SVM. The classification errors are analyzed and categorized. The recognition rates of SVM and ELM classifiers are compared with Hidden Markov Model (HMM) and the Nearest Mean (NM) classifiers. Using the SVM, ELM, HMM and NM classifiers the achieved average recognition rates are 99.39%, 99.45%, 97.99% and 94.35%, respectively. ELM and SVM recognition rates are better for all the digits than HMM and NM. The presented technique, using simple features and SVM and ELM classifiers, are effective in the recognition of handwritten Arabic (Indian) numerals, and it is shown to be superior to HMM and NM classifiers for all digits." @default.
- W2278731850 created "2016-06-24" @default.
- W2278731850 creator A5009096022 @default.
- W2278731850 creator A5068460528 @default.
- W2278731850 date "2009-06-15" @default.
- W2278731850 modified "2023-09-23" @default.
- W2278731850 title "Automatic Recognition of Off-line Handwritten Arabic (Indian) Numerals Using Support Vector and Extreme Learning Machines" @default.
- W2278731850 cites W1548139318 @default.
- W2278731850 cites W1994716798 @default.
- W2278731850 cites W1997332145 @default.
- W2278731850 cites W2000262867 @default.
- W2278731850 cites W2014710809 @default.
- W2278731850 cites W2015421919 @default.
- W2278731850 cites W2015489952 @default.
- W2278731850 cites W2024986448 @default.
- W2278731850 cites W2029049225 @default.
- W2278731850 cites W2039905248 @default.
- W2278731850 cites W2087136607 @default.
- W2278731850 cites W2101347091 @default.
- W2278731850 cites W2101381964 @default.
- W2278731850 cites W2107208682 @default.
- W2278731850 cites W2111072639 @default.
- W2278731850 cites W2114744730 @default.
- W2278731850 cites W2118598121 @default.
- W2278731850 cites W2131718092 @default.
- W2278731850 cites W2134603844 @default.
- W2278731850 cites W2148603752 @default.
- W2278731850 cites W2156909104 @default.
- W2278731850 cites W2157337007 @default.
- W2278731850 cites W2533349359 @default.
- W2278731850 cites W65385703 @default.
- W2278731850 hasPublicationYear "2009" @default.
- W2278731850 type Work @default.
- W2278731850 sameAs 2278731850 @default.
- W2278731850 citedByCount "11" @default.
- W2278731850 countsByYear W22787318502012 @default.
- W2278731850 countsByYear W22787318502013 @default.
- W2278731850 countsByYear W22787318502014 @default.
- W2278731850 countsByYear W22787318502016 @default.
- W2278731850 countsByYear W22787318502017 @default.
- W2278731850 crossrefType "journal-article" @default.
- W2278731850 hasAuthorship W2278731850A5009096022 @default.
- W2278731850 hasAuthorship W2278731850A5068460528 @default.
- W2278731850 hasConcept C119857082 @default.
- W2278731850 hasConcept C12267149 @default.
- W2278731850 hasConcept C153180895 @default.
- W2278731850 hasConcept C154945302 @default.
- W2278731850 hasConcept C204160518 @default.
- W2278731850 hasConcept C23224414 @default.
- W2278731850 hasConcept C2780150128 @default.
- W2278731850 hasConcept C28490314 @default.
- W2278731850 hasConcept C41008148 @default.
- W2278731850 hasConcept C50644808 @default.
- W2278731850 hasConceptScore W2278731850C119857082 @default.
- W2278731850 hasConceptScore W2278731850C12267149 @default.
- W2278731850 hasConceptScore W2278731850C153180895 @default.
- W2278731850 hasConceptScore W2278731850C154945302 @default.
- W2278731850 hasConceptScore W2278731850C204160518 @default.
- W2278731850 hasConceptScore W2278731850C23224414 @default.
- W2278731850 hasConceptScore W2278731850C2780150128 @default.
- W2278731850 hasConceptScore W2278731850C28490314 @default.
- W2278731850 hasConceptScore W2278731850C41008148 @default.
- W2278731850 hasConceptScore W2278731850C50644808 @default.
- W2278731850 hasLocation W22787318501 @default.
- W2278731850 hasOpenAccess W2278731850 @default.
- W2278731850 hasPrimaryLocation W22787318501 @default.
- W2278731850 hasRelatedWork W1501914674 @default.
- W2278731850 hasRelatedWork W1775135849 @default.
- W2278731850 hasRelatedWork W2090893314 @default.
- W2278731850 hasRelatedWork W2097394871 @default.
- W2278731850 hasRelatedWork W2101435584 @default.
- W2278731850 hasRelatedWork W2111072639 @default.
- W2278731850 hasRelatedWork W2119417805 @default.
- W2278731850 hasRelatedWork W2125654608 @default.
- W2278731850 hasRelatedWork W2132162366 @default.
- W2278731850 hasRelatedWork W2134603844 @default.
- W2278731850 hasRelatedWork W2153650732 @default.
- W2278731850 hasRelatedWork W2167982865 @default.
- W2278731850 hasRelatedWork W2373566042 @default.
- W2278731850 hasRelatedWork W2388060203 @default.
- W2278731850 hasRelatedWork W2394135218 @default.
- W2278731850 hasRelatedWork W2464155145 @default.
- W2278731850 hasRelatedWork W2502864683 @default.
- W2278731850 hasRelatedWork W2624876401 @default.
- W2278731850 hasRelatedWork W2737444041 @default.
- W2278731850 hasRelatedWork W3208828651 @default.
- W2278731850 hasVolume "2" @default.
- W2278731850 isParatext "false" @default.
- W2278731850 isRetracted "false" @default.
- W2278731850 magId "2278731850" @default.
- W2278731850 workType "article" @default.