Character Detection and Segmentation of Historical Uchen Tibetan Documents in Complex Situations

Zhang, Ce; Wang, Weilan; Liu, Huaming; Zhang, Guowei; Lin, Qiang

doi:10.1109/access.2022.3151886

Cited by 11 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Tibetan character ding datasets used in this paper are TCDB and HUTD [39] provided by Northwest Minzu University, in which the TCDB dataset contains the standard and variant data of Tibetan Uchen, and HUTD is the data of Tibetan antiquarian character ding, as shown in Table 1. This dataset is divided into three parts in total, which are Tibetan Uchen standard dataset, Tibetan Uchen variants dataset and Tibetan Uchen antiquarian character ding dataset.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Incremental Recognition of Multi-Style Tibetan Character Based on Transfer Learning

Zhao,

Wang,

Wang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Tibetan script possesses a distinctive artistic form of writing, intricate glyph structures, and diverse stylistic variations. In the task of text recognition, effectively handling the recognition of Tibetan script with significantly different stylistic fonts remains a challenge. Existing research has made considerable progress in recognizing Tibetan script within a single style using techniques such as convolutional neural networks and convolutional recurrent neural networks. However, when dealing with multi-style Tibetan script recognition, the standard approach involves training models using a multi-label joint training method. This approach annotates the style and class of different font style samples and merges them into a single dataset for model training. Nevertheless, as the amount of data and performance requirements increase, this approach gradually faces issues such as decreasing accuracy, insufficient generalization capability, and poor adaptability to new style samples. In this paper, we propose a transfer learning-based method for incremental recognition of multi-style Tibetan script, referred to as "multi-style Tibetan script incremental recognition." This method learns and completes the recognition of new style Tibetan script gradually from models that already possess recognition capabilities for a specific style. The proposed method consists of the following stages: 1) A multi-style classifier based on the VGG-16 network is designed to extract features that enable precise differentiation between different font styles of Tibetan script; 2) A pre-training phase is conducted using a residual network on the Tibetan script's standard Uchen style, resulting in an efficient feature extractor and a classifier capable of effectively recognizing the standard style, serving as a baseline model; 3) Through transfer learning, the feature extraction part of the baseline model is frozen, forming a shared feature extractor used for feature extraction of Tibetan script in the Uchen variant and antiquarian character styles. Corresponding classifiers are trained based on different styles; 4) By combining the multistyle classifier, shared feature extractor, and category classifier, recognition of Tibetan script characters is achieved. This method incrementally recognizes new styles based on the existing recognition model for Tibetan script in the Uchen standard style. Experimental results demonstrate that this method enhances the recognition accuracy of Tibetan script in Uchen standard, variant, and antiquarian character styles to 99.04%, 98.05%, and 97.66% respectively, using the TCDB and HUTD datasets. Compared to the traditional multitask recognition approach, the overall recognition accuracy improved from 90.14% to 98.40%. This method exhibits high accuracy, strong generalization capability, and good adaptability to new style samples in multistyle Tibetan script character recognition. Furthermore, it can be applied to other tasks involving multi-style, multi-font, and multi-script recognition.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Incremental Recognition of Multi-Style Tibetan Character Based on Transfer Learning

Zhao,

Wang,

Wang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The research on document images of Historical Tibetan document in recent years has also achieved corresponding results: binarization processing, layout analysis, line segmentation, word segmentation, and character recognition. Zhao Penghai et al proposed a solution to the problem of pseudo-adhesion in the binarization method of Historical Tibetan document by fusing the attention mechanism with U-network, which has made an outstanding contribution to the construction of the basic dataset of Historical Tibetan document, and the obtained binarized dataset is very good for both background and line adhesion [22] . Zhang Ce et al proposed a structural attribute-based method for segmentation Tibetan characters in Ujjain script, which chunks syllables according to the position of tshegs and the position of the baseline in the syllable, and at the same time uses template matching for the differentiation and segmentation of the adhering strokes, and the method effectively solves the problem of segmentation the character dings in the Historical Tibetan document [23] .…”

Section: Related Workmentioning

confidence: 99%

Based on K-Net adhesive syllable segmentation for historical Tibetan document images

zhou,

Hao,

wang

et al. 2024

Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023)

View full text Add to dashboard Cite

Historical Tibetan document hold a significant place within surviving ancient literature in China for their representation of Tibetan culture and history. All of these documents were handwritten and thus possess various problems such as adhesion, blurred handwriting, and background stains. Segmentation of syllables from the text is a crucial step in analyzing images of Historical Tibetan document that must be completed prior to syllable recognition. Syllable segmentation is challenged by pre-syllable and post-syllable stroke sticking, tsheg sticking, and syllable stroke sticking. In this paper, we enhance the K-Net model to improve its efficacy in segmenting syllables in Historical Tibetan document texts. The main work includes: (1) to better classify the sticking syllables, we modify the backbone network to ResNeXt; (2) before entering into the kernel learning, we convert the feature mask and the segmentation mask into a convolution to increase the correct rate of mask prediction; (3) information proofreading in each step of kernel updating, and the mask prediction obtained from kernel learning is convolved with the feature mask to obtain a new mask prediction with higher correct rate; and (4) streamlining part of the instance segmentation code to lighten the network model. The experimental results demonstrate that the suggested technique can solve the syllable segmentation issue of syllable-to-syllable stroke sticking and tsheg-to-syllable stroke sticking proficiently. Consequently, syllable segmentation of mAcc attains 95.66%, and mIoU attains 76.59% for the Historical Tibetan document.

show abstract

“…However, some research has been dedicated to detecting and recognizing other ethnic characters. In the detection and recognition of the Tibetan character, Zhang et al [18] proposed an innovative Tibetan character segmentation approach grounded in critical feature information. The method effectively tackled challenges such as text lines with varying degrees of tilt and distortion, overlapping and intersecting character strokes, and the diversity in stroke styles.…”

Section: Tibetan Character Detection and Recognitionmentioning

confidence: 99%

A Method for Detecting and Recognizing Yi Character Based on Deep Learning

Sun,

Ding,

Sun

et al. 2024

CMC

View full text Add to dashboard Cite

Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition, we present a deep learning-based approach for Yi character detection and recognition. In the detection stage, an improved Differentiable Binarization Network (DBNet) framework is introduced to detect Yi characters, in which the Omni-dimensional Dynamic Convolution (ODConv) is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features, thereby improving the accuracy of Yi character detection. Then, the feature pyramid network fusion module is used to further extract Yi character image features, improving target recognition at different scales. Further, the previously generated feature map is passed through a head network to produce two maps: a probability map and an adaptive threshold map of the same size as the original map. These maps are then subjected to a differentiable binarization process, resulting in an approximate binarization map. This map helps to identify the boundaries of the text boxes. Finally, the text detection box is generated after the post-processing stage. In the recognition stage, an improved lightweight MobileNetV3 framework is used to recognize the detect character regions, where the original Squeezeand-Excitation (SE) block is replaced by the efficient Shuffle Attention (SA) that integrates spatial and channel attention, improving the accuracy of Yi characters recognition. Meanwhile, the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model, so that the model can better understand the contextual information and improve the accuracy of text recognition. The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters, with detection and recognition accuracy rates of 97.5% and 96.8%, respectively. And also, we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms. In these comparisons, the proposed model achieves better detection and recognition results with a certain reliability.

show abstract

Character Detection and Segmentation of Historical Uchen Tibetan Documents in Complex Situations

Cited by 11 publications

References 31 publications

Incremental Recognition of Multi-Style Tibetan Character Based on Transfer Learning

Incremental Recognition of Multi-Style Tibetan Character Based on Transfer Learning

Based on K-Net adhesive syllable segmentation for historical Tibetan document images

A Method for Detecting and Recognizing Yi Character Based on Deep Learning

Contact Info

Product

Resources

About