An end-to-end network for irregular printed Mongolian recognition

Cui, Shaodong; Su, Yila; Ji, Ren; Ji, Yatu

doi:10.1007/s10032-021-00388-y

Cited by 9 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset consists of 800,000 samples collected from the dictionary and covers 20,250 words. In 2021, Cui et al 7 proposed a triplet attention Mogrifier network (TAMN) for irregular printed Mongolian text recognition. The TAMN network uses a special spatial transformation method to correct the distorted Mongolian image.The recognition accuracy reached 90.30% on their own dataset, which includes 98,085 Mongolian pictures from the China Mongolian News Network and covers 6538 words.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A new dataset for mongolian online handwritten recognition

Pan

Fan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

This paper introduces a new traditional Mongolian word-level online handwriting dataset, MOLHW. The dataset consists of handwritten Mongolian words, including 164,631 samples written by 200 writers and covering 40,605 Mongolian common words. These words were selected from a large Mongolian corpus. The coordinate points of words were collected by volunteers, who wrote the corresponding words on the dedicated application for their mobile phones. Latin transliteration of Mongolian was used to annotate the coordinates of each word. At the same time, the writer’s identification number and mobile phone screen information were recorded in the dataset. Using this dataset, we propose an encoder–decoder Mongolian online handwriting recognition model with a deep bidirectional gated recurrent unit and attention mechanism as the baseline evaluation model. Under this model, the optimal performance of the word error rate (WER) on the test set was 24.281%. Furthermore, we present the experimental results of different Mongolian online handwriting recognition models. The experimental results show that compared with other models, the model based on Transformer could learn the corresponding character sequences from the coordinate data of the dataset more effectively, with a 16.969% WER on the test set. The dataset is now freely available to researchers worldwide. The dataset can be applied to handwritten text recognition as well as handwritten text generation, handwriting identification, and signature recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Therefore, the segmentation of characters will greatly affect the accuracy of recognition. Due to the above special nature of Mongolian, in recent years, many scholars have adopted the non-segmentation strategy [5][6][7] . Datasets for studying Mongolian OCR are relatively easy to obtain.…”

Section: Related Workmentioning

confidence: 99%

A new dataset for mongolian online handwritten recognition

Pan

Fan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Cui et al [2] presented an end-to-end neural network model tailored to irregularly printed Mongolian text recognition. Their comprehensive approach spans from image input to text output, enabling direct detection and extraction of Mongolian text from images.…”

Section: Related Workmentioning

confidence: 99%

“…This results in the model having a relatively high recognition accuracy for in-vocabulary words but a significantly lower recognition capability for OOV words. To address this issue, the common approach is to incorporate a post-processing module based on a dictionary or language model after the recognition model [2,3]. However, in this scheme, the recognition model and the postprocessing model are independent of each other, cannot be jointly optimized, and do not support end-to-end recognition.…”

Section: Introductionmentioning

confidence: 99%

Online Mongolian Handwriting Recognition Based on Encoder–Decoder Structure with Language Model

Fan,

Sun,

Wang

et al. 2023

Electronics

View full text Add to dashboard Cite

Mongolian online handwriting recognition is a complex task due to the script’s intricate characters and extensive vocabulary. This study proposes a novel approach by integrating a pre-trained language model into the sequence-to-sequence(Seq2Seq) + attention mechanisms(AM) model to enhance recognition accuracy. Three fusion models, including former, latter, and complete fusion, are introduced, showing substantial improvements over the baseline model. The complete fusion model, combined with synchronized language model parameters, achieved the best results, significantly reducing character and word error rates. This research presents a promising solution for accurate Mongolian online handwriting recognition, offering practical applications in preserving and utilizing the Mongolian script.

show abstract