Tagged articles
layout analysis
17 articles · Page 1 of 1
This article demonstrates how the Raggae Python SDK enables layout analysis, reading order resolution, and region association for complex documents (PDF, Word, PowerPoint, Excel, HTML, scanned) to preserve spatial relationships in RAG pipelines, using specialized analyzers and geometric resolvers to avoid flattening content into plain text.
DOCXHTMLPDF
0 likes · 36 min read

MinerU, an open-source document parser from Shanghai AI Lab, converts PDFs and scans to Markdown and structured JSON with layout preservation, offering four quality tiers, CLI and Python APIs, three deployment modes, and intermediate JSON outputs that enable custom chunking for RAG pipelines.
MinerUPDFPython
0 likes · 13 min read

This article explains why MinerU, an open-source document parser with 80k+ GitHub stars, outperforms traditional text-extraction tools by understanding document structure — handling multi-column layouts, tables, and formulas — and introduces its four-tier parsing modes, stable locators for Agent workflows, and practical integration code for Python and Java.
MinerUPDF parsingRAG
0 likes · 16 min read

This article provides an in‑depth technical analysis of Multimodal GraphRAG, covering document parsing pipelines, layout analysis, model comparisons, knowledge‑graph enrichment, multimodal indexing and retrieval, and a systematic comparison of RAG, GraphRAG, and KG‑QA approaches.
GraphRAGMultimodal RetrievalOCR pipeline
0 likes · 23 min read

This article provides a comprehensive technical overview of multimodal GraphRAG, detailing document‑intelligence parsing pipelines, layout analysis, OCR‑pipeline vs OCR‑free approaches, knowledge‑graph integration for chunk relationships, multimodal indexing, retrieval‑generation workflows, and a comparative analysis of RAG, GraphRAG, and KG‑QA solutions.
GraphRAGMultimodal RetrievalOCR
0 likes · 23 min read

This article presents a detailed technical walkthrough of multimodal GraphRAG, covering document‑intelligence parsing pipelines, layout‑analysis models, knowledge‑graph augmentation, multimodal indexing and retrieval, and a comparative analysis of RAG, GraphRAG, and KG‑QA approaches, with concrete examples, model sizes, benchmark scores, and research citations.
GraphRAGMultimodal RetrievalRAG
0 likes · 25 min read

This article examines MinerU's strengths and nine critical shortcomings—such as layout order errors, cross‑page table splits, merged‑cell failures, OCR misrecognition, and licensing issues—and provides concrete improvement strategies, interview‑ready resume bullets, and practical response frameworks for engineers.
LLMMinerUOCR
0 likes · 13 min read

The 360LayoutAnalysis project from 360 AI Lab releases lightweight, yolov8‑based layout analysis models covering Chinese and English papers, Chinese research reports, and a general document scenario, providing fast inference, paragraph‑level detection, and open‑source code and weights for flexible document‑understanding pipelines.
AI ModelDocument UnderstandingYOLOv8
0 likes · 9 min read

This article examines the challenges of extracting data from complex financial reports and presents an AI‑driven solution that combines advanced layout analysis, table recognition, OCR, and large‑language‑model integration using Baidu’s PaddlePaddle low‑code platform, detailing model selection, training, performance tuning, and deployment.
AIDocument ExtractionLow‑code AI
0 likes · 11 min read


AntTechNov 15, 2023 · Artificial Intelligence
The paper identifies reading‑order disorder as a critical obstacle in visually‑rich document information extraction, proposes a Token Path Prediction model with grid‑label formulation, introduces re‑annotated FUNSD‑r and CORD‑r datasets, and demonstrates SOTA performance on NER, entity linking, and reading‑order prediction tasks.
Document AINERlayout analysis
0 likes · 17 min read

This article reviews three representative document intelligence models—StrucText, LayoutLMv3, and GraphDoc—detailing their input features, feature fusion strategies, self‑supervised tasks, and underlying architectures, and explains how they learn embeddings for segments, words, or regions to enable classification and key‑value extraction.
Document AIGraph Neural Networkslayout analysis
0 likes · 15 min read


58 TechMar 17, 2021 · Artificial Intelligence
This article presents the practical deployment of OCR technology within 58’s information‑security workflows, focusing on layout‑analysis techniques for document and credential recognition, detailing rule‑based, template‑matching, object‑detection, and image‑segmentation methods, their implementation steps, experimental results, advantages, limitations, and future directions.
Document RecognitionOCRlayout analysis
0 likes · 18 min read

WeChat’s 8.0 update introduced an OCR pipeline that first quickly detects text in images, classifies the image type, applies a lightweight multi‑language detection network and a MobileNetV3‑based DBNet recognizer with a multi‑task CTC/Attention model, then merges results via a rule‑based layout analyzer to deliver accurate, well‑formatted extracted text across diverse languages and document types.
Computer VisionDBNetOCR
0 likes · 13 min read

This article explains how Alibaba's Front‑End Intelligent project automatically converts UI design images into production‑ready code, covering layout analysis, background and foreground processing, a fusion of traditional image algorithms with deep‑learning detection, GAN‑based complex‑background extraction, experimental results and real‑world deployment.
GANautomationcode generation
0 likes · 21 min read

This article explains Alibaba's front‑end intelligent project that automatically generated 79.34% of the Double‑11 UI code, detailing why images are used as input, the layered image‑processing pipeline, background and foreground analysis, traditional versus deep‑learning methods, fusion techniques, evaluation results, and real‑world deployments.
code generationfrontendimage processing
0 likes · 20 min read

The paper presents a structured layout‑information framework combined with a guided‑line “leader‑follower” algorithm that represents UI controls as Connection objects and matches them via attribute and vector similarity, enabling fast identification of recurring business components and duplicate GridView items without extensive retraining, thereby enhancing code reuse in UI2CODE projects.
component detectionguided line methodlayout analysis
0 likes · 9 min read

The UI2CODE system tackles UI layout analysis by first extracting backgrounds with Sobel, Laplacian and Canny edge detection plus a flood‑fill algorithm, then isolating foreground components through connected‑component analysis and a Faster R‑CNN classifier, and finally fusing both pipelines to achieve superior precision, recall and IoU on Xianyu app screenshots.
Computer VisionFaster R-CNNUI2Code
0 likes · 16 min read
