Mmocr

Kuang, Zhen‐Bang; Sun, Hongbin; Li, Zhizhong; Yue, Xiaoyu; Lin, Tsui Hin; Chen, Jianyong; Wei, Huaqiang; Zhu, Yiqin; Gao, Tong; Zhang, Wenwei; Chen, Kai; Zhang, Wayne; Lin, Dahua

doi:10.1145/3474085.3478328

Cited by 49 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Text Line Segmentation. We employ PSENet (Wang et al 2019b) and FCENet (Zhu et al 2021) as comparison methods, which are implemented by the mmocr codebase (Kuang et al 2021). By incorporating a progressive scale expansion mechanism and multi-scale kernels, PSENet is able to gradually expand the predicted text-line region, which enables the model to effectively distinguish densely packed text lines.…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Knowledge-Enhanced Historical Document Segmentation and Recognition

Gao,

Huang,

et al. 2024

AAAI

View full text Add to dashboard Cite

Optical Character Recognition (OCR) of historical document images remains a challenging task because of the distorted input images, extensive number of uncommon characters, and the scarcity of labeled data, which impedes modern deep learning-based OCR techniques from achieving good recognition accuracy. Meanwhile, there exists a substantial amount of expert knowledge that can be utilized in this task. However, such knowledge is usually complicated and could only be accurately expressed with formal languages such as first-order logic (FOL), which is difficult to be directly integrated into deep learning models. This paper proposes KESAR, a novel Knowledge-Enhanced Document Segmentation And Recognition method for historical document images based on the Abductive Learning (ABL) framework. The segmentation and recognition models are enhanced by incorporating background knowledge for character extraction and prediction, followed by an efficient joint optimization of both models. We validate the effectiveness of KESAR on historical document datasets. The experimental results demonstrate that our method can simultaneously utilize knowledge-driven reasoning and data-driven learning, which outperforms the current state-of-the-art methods.

show abstract

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Knowledge-Enhanced Historical Document Segmentation and Recognition

Gao,

Huang,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…The raw images captured by the camera are of size 1280 × 720. All other hyperparameters and the optimizer, not mentioned below, are set to their default values as specified in MMOCR [47].…”

Section: Datasets and Implementation Detailsmentioning

confidence: 99%

The Industrial Application of Artificial Intelligence-Based Optical Character Recognition in Modern Manufacturing Innovations

Tang,

Lee,

Jung

2024

Sustainability

View full text Add to dashboard Cite

This paper presents the development of a comprehensive, on-site industrial Optical Character Recognition (OCR) system tailored for reading text on iron plates. Initially, the system utilizes a text region detection network to identify the text area, enabling camera adjustments along the x and y axes and zoom enhancements for clearer text imagery. Subsequently, the detected text region undergoes line-by-line division through a text segmentation network. Each line is then transformed into rectangular patches for character recognition by the text recognition network, comprising a vision-based text recognition model and a language network. The vision network performs preliminary recognition, followed by refinement through the language model. The OCR results are then converted into digital characters and recorded in the iron plate registration system. This paper’s contributions are threefold: (1) the design of a comprehensive, on-site industrial OCR system for autonomous registration of iron plates; (2) the development of a realistic synthetic image generation strategy and a robust data augmentation strategy to address data scarcity; and (3) demonstrated impressive experimental results, indicating potential for on-site industrial applications. The designed autonomous system enhances iron plate registration efficiency and significantly reduces factory time and labor costs.

show abstract

“…In our experiments, the Openmmlab-MMOCR [11] is selected as our toolbox, which is flexible for STD tasks. The hyperparameters of all experiments are set according to the official documentation of Openmmlab-MMOCR.…”

Section: Implementation Detailsmentioning

confidence: 99%