paper-with-me

Papers

Omnifont Persian OCR System Using Primitives

2022-02-13 · Azarakhsh Keipour, Mohammad Eshghi, Sina Mohammadzadeh Ghadikolaei, Negin Mohammadi, Shahab Ensafi

In this paper, we introduce a model-based omnifont Persian OCR system. The system uses a set of 8 primitive elements as structural features for recognition. First, the scanned document is preprocessed. After normalizing the preprocessed image, text rows and sub-words are separated and then thinned. After recognition of dots in sub-words, strokes are extracted and primitive elements of each sub-word are recognized using the strokes. Finally, the primitives are compared with a predefined set of character identification vectors in order to identify sub-word characters. The separation and recognition steps of the system are concurrent, eliminating unavoidable errors of independent separation of letters. The system has been tested on documents with 14 standard Persian fonts in 6 sizes. The achieved precision is 97.06%.

📄 PDF Abstract BibTeX arXiv:2202.06371

Code (0)

등록된 구현이 없습니다.

Tasks

Optical Character Recognition (OCR)

Similar Papers 제목 키워드 기반

PersianRAG: A Retrieval-Augmented Generation System for Persian Language

2024-11-05 · Hossein Hosseini, Mohammad Sobhan Zare, Amir Hossein Mohammadi, Arefeh Kazemi 외

Retrieval augmented generation (RAG) models, which integrate large-scale pre-trained generative models with external retrieval mechanisms, have shown significant success in various natural language processing (NLP) tasks…

Language ModelingLanguage ModellingQuestion AnsweringRAG+2

Tajik-Farsi Persian Transliteration Using Statistical Machine Translation

2012-05-01 · LREC 2012 5 · Chris Irwin Davis

Tajik Persian is a dialect of Persian spoken primarily in Tajikistan and written with a modified Cyrillic alphabet. Iranian Persian, or Farsi, as it is natively called, is the lingua franca of Iran and is written with th…

Machine TranslationTranslationTransliteration

Persian SemCor: A Bag of Word Sense Annotated Corpus for the Persian Language

2021-01-01 · EACL (GWC) 2021 1 · Hossein Rouhizadeh, Mehrnoush Shamsfard, Mahdi Dehghan, Masoud Rouhizadeh

Supervised approaches usually achieve the best performance in the Word Sense Disambiguation problem. However, the unavailability of large sense annotated corpora for many low-resource languages make these approaches inap…

Word Sense Disambiguation

Persian Wordnet Construction using Supervised Learning

2017-04-11 · Zahra Mousavi, Heshaam Faili

This paper presents an automated supervised method for Persian wordnet construction. Using a Persian corpus and a bi-lingual dictionary, the initial links between Persian words and Princeton WordNet synsets have been gen…

ClassificationGeneral Classification

PQuAD: A Persian Question Answering Dataset

2022-02-13 · Kasra Darvishi, Newsha Shahbodagh, Zahra Abbasiantaeb, Saeedeh Momtazi

We present Persian Question Answering Dataset (PQuAD), a crowdsourced reading comprehension dataset on Persian Wikipedia articles. It includes 80,000 questions along with their answers, with 25% of the questions being ad…

ArticlesDiversityQuestion AnsweringReading Comprehension