English
Related papers

Related papers: PreP-OCR: A Complete Pipeline for Document Image R…

200 papers

Multimodal Large Language Models (MLLMs) enhance the potential of natural language processing. However, their actual impact on document information extraction remains unclear. In particular, it is unclear whether an MLLM-only…

Computation and Language · Computer Science 2026-03-04 Jiyuan Shen , Peiyue Yuan , Atin Ghosh , Yifan Mai , Daniel Dahlmeier

DeepSeek-OCR shows that rendered text can be reconstructed from a small number of vision tokens, sparking excitement about using vision as a compression medium for long textual contexts. But this pipeline requires rendering token embeddings…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Ivan Yee Lee , Cheng Yang , Taylor Berg-Kirkpatrick

Pre-training text representations have led to significant improvements in many areas of natural language processing. The quality of these models benefits greatly from the size of the pretraining corpora as long as its quality is preserved.…

Computation and Language · Computer Science 2019-11-18 Guillaume Wenzek , Marie-Anne Lachaux , Alexis Conneau , Vishrav Chaudhary , Francisco Guzmán , Armand Joulin , Edouard Grave

Closed-circuit video (CCTV) inspection has been the most popular technique for visually evaluating the interior status of pipelines in recent decades. Certified inspectors prepare the pipe repair document based on the CCTV inspection. The…

Information Retrieval · Computer Science 2024-09-02 Sai Nethra Betgeri , Shashank Reddy Vadyala , John C. Mattews , Hongfang Lu

Text recognition is a long-standing research problem for document digitalization. Existing approaches are usually built based on CNN for image understanding and RNN for char-level text generation. In addition, another language model is…

Computation and Language · Computer Science 2022-09-07 Minghao Li , Tengchao Lv , Jingye Chen , Lei Cui , Yijuan Lu , Dinei Florencio , Cha Zhang , Zhoujun Li , Furu Wei

Recently, the joint design of optical systems and downstream algorithms is showing significant potential. However, existing rays-described methods are limited to optimizing geometric degradation, making it difficult to fully represent the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Zheng Ren , Jingwen Zhou , Wenguan Zhang , Jiapu Yan , Bingkun Chen , Huajun Feng , Shiqi Chen

A common use case for OCR applications involves users uploading documents and progressively correcting automatic recognition to obtain the final transcript. This correction phase presents an opportunity for progressive adaptation of the OCR…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Jan Kohút , Michal Hradiš

Optical Character Recognition (OCR) for data extraction from documents is essential to intelligent informatics, such as digitizing medical records and recognizing road signs. Multi-modal Large Language Models (LLMs) can solve this task and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Hyakka Nakada , Yoshiyasu Tanaka

Image super-resolution pursuits reconstructing high-fidelity high-resolution counterpart for low-resolution image. In recent years, diffusion-based models have garnered significant attention due to their capabilities with rich prior…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Aiwen Jiang , Zhi Wei , Long Peng , Feiqiang Liu , Wenbo Li , Mingwen Wang

VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within individual pages) together with their bounding boxes and textual content. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Bangrui Xu , Ziyang Miao , Xuanhe Zhou , Yiming Lin , Zirui Tang , Xiaomeng Zhao , Fan Wu , Cheng Tan , Fan Wu , Bin Wang , Conghui He

Convolutional Neural Networks (CNNs) have significantly advanced Image Super-Resolution (SR), yet most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly under severe…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Bingwen Hu , Heng Liu , Zhedong Zheng , Ping Liu

Optical Chemical Structure Recognition (OCSR) is critical for converting 2D molecular diagrams from printed literature into machine-readable formats. While Vision-Language Models have shown promise in end-to-end OCR tasks, their direct…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Haocheng Tang , Xingyu Dang , Junmei Wang

The ubiquity of smartphone cameras has led to more and more documents being captured by cameras rather than scanned. Unlike flatbed scanners, photographed documents are often folded and crumpled, resulting in large local variance in text…

Computer Vision and Pattern Recognition · Computer Science 2020-08-06 Amir Markovitz , Inbal Lavi , Or Perel , Shai Mazor , Roee Litman

Detecting manipulations in digital documents is becoming increasingly important for information verification purposes. Due to the proliferation of image editing software, altering key information in documents has become widely accessible.…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Hailey Joren , Otkrist Gupta , Dan Raviv

Despite the growing adoption of electronic health records, many processes still rely on paper documents, reflecting the heterogeneous real-world conditions in which healthcare is delivered. The manual transcription process is time-consuming…

In this paper we evaluate Optical Character Recognition (OCR) of 19th century Fraktur scripts without book-specific training using mixed models, i.e. models trained to recognize a variety of fonts and typesets from previously unseen…

Computer Vision and Pattern Recognition · Computer Science 2018-10-09 Christian Reul , Uwe Springmann , Christoph Wick , Frank Puppe

Despite the existence of numerous Optical Character Recognition (OCR) tools, the lack of comprehensive open-source systems hampers the progress of document digitization in various low-resource languages, including Bengali. Low-resource…

We propose a novel learning method to rectify document images with various distortion types from a single input image. As opposed to previous learning-based methods, our approach seeks to first learn the distortion flow on input image…

Computer Vision and Pattern Recognition · Computer Science 2019-09-23 Xiaoyu Li , Bo Zhang , Jing Liao , Pedro V. Sander

The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive.…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Liangliang Cao , Bowen Zhang , Chen Chen , Yinfei Yang , Xianzhi Du , Wencong Zhang , Zhiyun Lu , Yantao Zheng

Document denoising is considered one of the most challenging tasks in computer vision. There exist millions of documents that are still to be digitized, but problems like document degradation due to natural and man-made factors make this…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Yashowardhan Shinde , Kishore Kulkarni , Sachin Kuberkar