Enhancing Farsi Text Recognition via Iteratively Using a Language Model
A Afkari-Fahandari, F Asadi-Zeydabadi… - 2024 20th CSI …, 2024 - ieeexplore.ieee.org
In the present era, there is a growing demand for a reliable Farsi text recognition system, that
addresses the needs of both industrial and individual users. The process of text recognition …
addresses the needs of both industrial and individual users. The process of text recognition …
Sub-word based Persian OCR using auto-encoder features and cascade classifier
In Persian text, unlike English, the letters are stick together and their shapes varies
depending on where they are in the word. This makes it difficult to distinguish letters in …
depending on where they are in the word. This makes it difficult to distinguish letters in …
Merging clustering and classification results for whole book recognition
Historical printed books OCR is one of the challenging tasks in the area of document image
analysis. Low quality of print and paper and unfamiliar font faces are the most known …
analysis. Low quality of print and paper and unfamiliar font faces are the most known …
Persian OCR with Cascaded Convolutional Neural Networks Supported by Language Model
M Pourreza, R Derakhshan, S Bibak… - … on Computer and …, 2020 - ieeexplore.ieee.org
Persian 1 OCR is a difficult task because of some specific features of Persian writing style,
like different styles of letters in different places of the word and similarity of letters to each …
like different styles of letters in different places of the word and similarity of letters to each …
Training a whole-book LSTM-based recognizer with an optimal training set
Despite the recent progress in OCR technologies, whole-book recognition, is still a
challenging task, in particular in case of old and historical books, that the unknown font faces …
challenging task, in particular in case of old and historical books, that the unknown font faces …