Related papers: PreP-OCR: A Complete Pipeline for Document Image R…
Automating the annotation of scanned documents is challenging, requiring a balance between computational efficiency and accuracy. DocParseNet addresses this by combining deep learning and multi-modal learning to process both text and visual…
Digitization of newspapers is of interest for many reasons including preservation of history, accessibility and search ability, etc. While digitization of documents such as scientific articles and magazines is prevalent in literature, one…
Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that…
Recent image restoration methods have produced significant advancements using deep learning. However, existing methods tend to treat the whole image as a single entity, failing to account for the distinct objects in the image that exhibit…
Previous methods for audio-image matching generally fall into one of two categories: pipeline models or End-to-End models. Pipeline models first transcribe speech and then encode the resulting text; End-to-End models encode speech directly.…
Document centric RAG pipelines usually begin with OCR, followed by brittle heuristics for chunking, table parsing, and layout reconstruction. These text first workflows are costly to maintain, sensitive to small layout shifts, and often…
Most existing super-resolution methods do not perform well in real scenarios due to lack of realistic training data and information loss of the model input. To solve the first problem, we propose a new pipeline to generate realistic…
We present DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. Specifically,…
Optical Character Recognition (OCR) is an established task with the objective of identifying the text present in an image. While many off-the-shelf OCR models exist, they are often trained for either scientific (e.g., formulae) or generic…
Document parsing has garnered widespread attention as vision-language models (VLMs) advance OCR capabilities. However, the field remains fragmented across dozens of specialized models with varying strengths, forcing users to navigate…
Extracting the relevant information out of a large number of documents is a challenging and tedious task. The quality of results generated by the traditionally available full-text search engine and text-based image retrieval systems is not…
Effects of Optical Character Recognition (OCR) quality on historical information retrieval have so far been studied in data-oriented scenarios regarding the effectiveness of retrieval results. Such studies have either focused on the effects…
Efficient text retrieval is critical for applications such as legal document analysis, particularly in specialized contexts like Japanese legal systems. Existing retrieval methods often underperform in such domain-specific scenarios,…
There is a need for information retrieval from large collections of low-resolution (LR) binary document images, which can be found in digital libraries across the world, where the high-resolution (HR) counterpart is not available. This…
The performance of optical character recognition (OCR) heavily relies on document image quality, which is crucial for automatic document processing and document intelligence. However, most existing document enhancement methods require…
This paper presents a complete Optical Character Recognition (OCR) system for camera captured image/graphics embedded textual documents for handheld devices. At first, text regions are extracted and skew corrected. Then, these regions are…
Most existing image restoration methods use neural networks to learn strong image-level priors from huge data to estimate the lost information. However, these works still struggle in cases when images have severe information deficits.…
Information extraction (IE) from unstructured documents remains a critical challenge in data processing pipelines. Traditional optical character recognition (OCR) methods and conventional parsing engines demonstrate limited effectiveness…
Computed Tomography (CT) using synchrotron radiation is a powerful technique that, compared to lab-CT techniques, boosts high spatial and temporal resolution while also providing access to a range of contrast-formation mechanisms. The…
Document tamper detection has always been an important aspect of tamper detection. Before the advent of deep learning, document tamper detection was difficult. We have made some explorations in the field of text tamper detection based on…