Sub-word based Persian OCR Using Auto-Encoder Features and Cascade Classifier

Pourreza, Masoud; Derakhshan, R.; Fayyazi, Hossein; Sabokrou, Mohammad

doi:10.1109/istel.2018.8661146

Cited by 6 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a recent increase in the number of research on recognition of both handwritten and machine printed text recognition in such languages [24,40,53,62,65,68]. In [45], an SVM classifer is used to recognize sub-words represented with features extracted by an Auto Encoder. The system is trained and tested on a proprietary, single-font, multi-size synthetic data and obtained 0.076 CER on B Nazanin font type.…”

Section: Arabic Text Recognitionmentioning

confidence: 99%

Printed Ottoman text recognition using synthetic data and data augmentation

Tasdemir

2023

IJDAR

View full text Add to dashboard Cite

Ottoman script is an Arabic alphabet-based script as well. It was a writing system of the Turkish language for several centuries until it was replaced with the modern Turkish script, which is based on the Latin alphabet, in 1928. With the ever increasing digitization campaigns, millions of Ottoman documents are coming to light. But, their contents are not directly accessible, nor they are digitally editable and searchable. OCR and text recognition technologies can be a solution to this problem in the form of auto-mated and semi-automated conversion systems. This study presents a DL-based character recognition system for the printed Ottoman script. We first generate a synthetic text image dataset from a text corpus, and then augment it using some image processing methods. We develop a hybrid Convolutional Neural Network-Bidirectional Long Short Term Memory recognizer and train it with the original and the augmented datasets. Finally we apply a Transfer Learning procedure for adapting the system to real image data. The proposed system obtains 0.16 CER on a test set containing line images from a historical printed Ottoman book.

show abstract

Section: Arabic Text Recognitionmentioning

confidence: 99%

Printed Ottoman text recognition using synthetic data and data augmentation

Tasdemir

2023

IJDAR

View full text Add to dashboard Cite

show abstract

“…Through a neural network classifier and new features, the recognition rate was 99.02% by using the improved gradient method, and 98.8% by using the gradient histogram method on the HODA dataset. In 2018, researchers created a Sub-Word Image Dictionary (SWID) that was applied to sub-word based on Persian OCR methods [31]. To recognize the sub-words, Support Vector Machine (SVM) classifiers were trained by SWID.…”

Section: Persian Languagementioning

confidence: 99%

“…Language Architecture Accuracy [23] On-line English Handwriting BLSTM 74.00 [23] On-line English Handwriting HMM 65.40 [22] Off-line English BLSTM 74.10 [22] On-line English BLSTM 79.70 [19] French LSTM 99.00 [20] Urdu MLSTM 94.97 [21] Pashto MLSTM 98.90 [29] Urdu LSTM-RNN 99.00 [30] Persian Improved Gradient & Gradient Histogram 98.80 [31] Persian SVM 61.14 [33] Persian CNN 97.00 […”

Section: Refmentioning

confidence: 99%

Persian Optical Character Recognition Using Deep Bidirectional Long Short-Term Memory

et al. 2022

View full text Add to dashboard Cite

Optical Character Recognition (OCR) is a system of converting images, including text,into editable text and is applied to various languages such as English, Arabic, and Persian. While these languages have similarities, their fundamental differences can create unique challenges. In Persian, continuity between Characters, the existence of semicircles, dots, oblique, and left-to-right characters such as English words in the context are some of the most important challenges in designing Persian OCR systems. Our proposed framework, Bina, is designed in a special way to address the issue of continuity by utilizing Convolution Neural Network (CNN) and deep bidirectional Long-Short Term Memory (BLSTM), a type of LSTM networks that has access to both past and future context. A huge and diverse dataset, including about 2M samples of both Persian and English contexts,consisting of various fonts and sizes, is also generated to train and test the performance of the proposed model. Various configurations are tested to find the optimal structure of CNN and BLSTM. The results show that Bina successfully outperformed state of the art baseline algorithm by achieving about 96% accuracy in the Persian and 88% accuracy in the Persian and English contexts.

show abstract

“…Similar synthetic printed text datasets are used for recognition of other Arabic alphabet based scripts as well. In [43], a character error rate of 7.6% was achieved on a synthetic Persian printed text dataset by using Support Vector Machines. Likewise, a character error rate of 0.8% was achieved by using a CNN-LSTM model for synthetic word images created with a font similar to the Naskh font for Persian in [46].…”

Section: Related Workmentioning

confidence: 99%

Transcription of Ottoman Machine-Print Documents

Tasdemir

Kizilirmak

Akcan

et al. 2022

Preprint

View full text Add to dashboard Cite

With the ever increasing speed of the digitization process, a large collection of Ottoman documents is accessible to researchers and the general public. But, the majority of the users interested in these documents can not read these documents unless they are transcripted to the modern Turkish script which use an extended version of the Latin alphabet. Manual transcription of such a massive amount of documents is beyond the capacity of human experts. As a solution, we propose an automatic recognition system for printed Ottoman documents which transcribes Ottoman texts directly to the modern Turkish script. We evaluated three decoding strategies including the Word Beam Search decoder that allows to use a recognition lexicon and n-gram statistics during the decoding phase. The system achieves 2.25% character error rate and 6.42% word error rate on a test set of 1.4K samples, using the test set transcriptions as the recognition lexicon. Using a general purpose, large lexicon of the Ottoman era (260K words and 77% test coverage), the performance is measured as 3.68% character error rate and 16.61% word error rate.

show abstract

Sub-word based Persian OCR Using Auto-Encoder Features and Cascade Classifier

Cited by 6 publications

References 13 publications

Printed Ottoman text recognition using synthetic data and data augmentation

Printed Ottoman text recognition using synthetic data and data augmentation

Persian Optical Character Recognition Using Deep Bidirectional Long Short-Term Memory

Transcription of Ottoman Machine-Print Documents

Contact Info

Product

Resources

About