EUVIMEDEUVIMED entdecken
Crossref

CHARACTER RECOGNITION

S Narmatha, R Pooja Shree, R. S. Prajashni, S. Ranjith Kumar

BSSS Journal of Computer · 2022

DOI: 10.51767/jc1305 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BSSS Journal of Computer, 2022. Verfasst von S Narmatha und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Character recognition has numerous applications namely postal addresses, bank check amounts, documents, number plates, etc. Development of a recognition system is an emerging need for digitizing handwritten documents that use Tamil characters. Therefore, we created a prediction model to recognize Tamil characters, the model works based on the Deep convolutional neural network (CNN). In this project, model is sequential. It is like a derivation of LeNet-4 architecture, including a dropout layer.A dataset for few Tamil characters is created, along with the recognition model. It helps people in identifying the exact script written in document, where some may find it difficult to recognize the characters written in paper due to colloquial writing and different handwriting styles. CNN have given excellent results to old fashioned shallow networks in acknowledgement tasks. To avoid overfitting in the recognition model, accuracy is increased by using dropout layer and dataset increment method. With the help of these methods in the CNN model, test accuracy rate was increased. The modifiedCNN architecture achieved a highest test accuracy of 97.75%.

Zitieren

APA

Narmatha, S., Shree, R. P., Prajashni, R. S., & Kumar, S. R. (2022). CHARACTER RECOGNITION. BSSS Journal of Computer. https://doi.org/10.51767/jc1305

Vancouver

Narmatha S, Shree RP, Prajashni RS, Kumar SR. CHARACTER RECOGNITION. BSSS Journal of Computer. 2022. doi:10.51767/jc1305

BibTeX
@article{Narmatha2022,
  author = {Narmatha, S and Shree, R Pooja and Prajashni, R. S. and Kumar, S. Ranjith},
  title = {CHARACTER RECOGNITION},
  journal = {BSSS Journal of Computer},
  year = {2022},
  doi = {10.51767/jc1305}
}
Kostenlos starten →