Performance Analysis of Zone Based Features for Online Handwritten Gurmukhi Script Recognition using Support Vector Machine

Verma, Karun; Sharma, Rajendra K.

doi:10.1007/978-3-319-08422-0_107

Cited by 7 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sharma et al [20] 40 Elastic matching 90.1 Sharma et al [22] 40 HMM 91.9 Kumar and Sharma [10] 114 SVM, Rule based 95.6 Kumar et al [11] 114 SVM, Rule based 93.3 Verma and Sharma [24] 102 SVM 92.2 Verma and Sharma [12] 74 SVM, HMM 96.7 Current work 93 SVM, FSA based 97.3 Figure 14. Standard and observed rendering order of consonant and vowel(s).…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, in classification phase, rule-based methods and statistical classification methods like TDNN, HMM and SVM were also discussed. In a recent study [24] [10] for character formation from the recognized strokes. In experimentation, they have considered a test data set of 35 Gurmukhi consonants, which was written by 10 different writers, five times each.…”

Section: Related Workmentioning

confidence: 99%

“…In the literature, many researchers have used the rulebased approach to combine the recognized strokes [10,16,24,26,27]. In the present study, Gurmukhi characters are formed by combining the recognized strokes using FSA-based scheme.…”

Section: Challenges In Online Handwritten Characters Formationmentioning

confidence: 99%

See 2 more Smart Citations

Recognition of online unconstrained handwritten Gurmukhi characters based on Finite State Automata

2018

View full text Add to dashboard Cite

This paper presents a language-based efficient post-processing algorithm for the recognition of online unconstrained handwritten Gurmukhi characters. A total of 93 stroke classes have been identified to recognize the Gurmukhi character set in this work. Support Vector Machine (SVM) classifier has been employed for stroke classification. The main objective of this paper is to improve the character level recognition accuracy using an efficient Finite State Automata (FSA)-based formation of Gurmukhi characters algorithm. A database of 21,945 online handwritten Gurmukhi words is primarily collected in this experiment. After analysing the collected database, we have observed that a character can be written using one or more strokes. Therefore, a total of 65,946 strokes have been annotated using the 93 identified stroke classes. Among these strokes, 15,069 stroke samples are considered for training the classifier. The proposed system achieved promising recognition accuracy of 97.3% for Gurmukhi characters, when tested with a new database of 8,200 characters, written by 20 different writers.

show abstract