Document Layout Analysis

"Document Layout Analysis is performed to determine physical structure of a document, that is, to determine document components. These document components can consist of single connected components-regions [...] of pixels that are adjacent to form single regions [...] , or group of text lines. A text line is a group of characters, symbols, and words that are adjacent, “relatively close” to each other and through which a straight line can be drawn (usually with horizontal or vertical orientation)." L. O'Gorman, "The document spectrum for page layout analysis," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 11, pp. 1162-1173, Nov. 1993.

Image credit: PubLayNet: largest dataset ever for document layout analysis

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 51–60 of 99 papers

Title	Date	Tasks	Status	Hype
CTE: A Dataset for Contextualized Table Extraction	Feb 2, 2023	Document Layout AnalysisTable Detection	CodeCode Available	1
Détection d'Objets dans les documents numérisés par réseaux de neurones profonds	Jan 27, 2023	Document Layout AnalysisLine Detection	—Unverified	0
M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis	Jan 1, 2023	ArticlesDocument Layout Analysis	CodeCode Available	1
Efficient few-shot learning for pixel-precise handwritten document layout analysis	Oct 27, 2022	Document Layout AnalysisFew-Shot Learning	—Unverified	0
Transformer-based Approach for Document Understanding	Oct 16, 2022	DecoderDocument Layout Analysis	—Unverified	0
Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks	Aug 23, 2022	Document Layout Analysisdocument understanding	CodeCode Available	1
Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis	Aug 22, 2022	Component ClassificationDocument Layout Analysis	CodeCode Available	1
DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis	Jun 2, 2022	Document Layout AnalysisObject Detection	CodeCode Available	8
Unified Pretraining Framework for Document Understanding	Apr 22, 2022	Document Layout Analysisdocument understanding	—Unverified	0
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking	Apr 18, 2022	cross-modal alignmentDocument AI	CodeCode Available	0

Show:10 25 50

← PrevPage 6 of 10Next →

All datasets PubLayNet val U-DIADS-Bib D4LA Document Layout Recognition Challenge mini-dev Document Layout Recognition Challenge test RVL-CDIP

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	CDeC-Net	Table	0.98	—	Unverified
2	VGT	Overall	0.96	—	Unverified
3	TRDLU	Overall	0.96	—	Unverified
4	VSR	Overall	0.96	—	Unverified
5	DETR	Overall	0.96	—	Unverified
6	LayoutLMv3-B	Overall	0.95	—	Unverified
7	DiT-L	Overall	0.95	—	Unverified
8	DoPTA	Overall	0.95	—	Unverified
9	UDoc	Overall	0.94	—	Unverified
10	ResNext-101-32×8d	Overall	0.94	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CV-Group	Class Average IoU	83.4	—	Unverified
2	CNKI	Class Average IoU	77.8	—	Unverified
3	VAI-OCR	Class Average IoU	70.7	—	Unverified
4	DeepLabV3+	Class Average IoU	66.5	—	Unverified
5	L3i++	Class Average IoU (Few-shot setting)	61.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DoPTA	mAP	70.72	—	Unverified
2	DocLayout-YOLO	mAP	70.3	—	Unverified
3	VGT	mAP	68.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Faster_RCNN	Overall	0.96	—	Unverified
2	fglihai	Overall	0.96	—	Unverified
3	Faster-RCNN	Overall	0.95	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	fglihai	Overall	0.92	—	Unverified
2	USYD NLP_CS29-2	Overall	0.92	—	Unverified
3	Faster-RCNN	Overall	0.91	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	VisualWordGrid	FAR	28.7	—	Unverified