Scene Text Detection and Recognition -- HRRegionNet: Chinese Character Segmentation in Historical Documents with Regional Awareness -- Fast Text v. Non-text Classification of Images -- Mask Scene Text Recognizer -- Rotated Box Is Back: An Accurate Box Proposal Network for Scene Text Detection -- Heterogeneous Network Based Semi-supervised Learning For Scene Text Recognition -- Scene Text Detection with Scribble Line -- EEM: An End-to-end Evaluation Metric for Scene Text Detection and Recognition -- SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models -- Fast Recognition for Multidirectional and Multi-Type License Plates with 2D Spatial Attention -- A Multi-level Progressive Rectification Mechanism for Irregular Scene Text Recognition -- Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition -- FEDS - Filtered Edit Distance Surrogate -- Bidirectional Regression for Arbitrary-Shaped Text Detection -- Document Classification -- VML-HP: Hebrew paleography dataset -- Open Set Authorship Attribution toward Demystifying Victorian Periodicals -- A More Effective Sentence-Wise Text Segmentation Approach using BERT -- Data Augmentation for Writer Identification Using a Cognitive Inspired Model -- Key-guided Identity Document Classification Method by Graph Attention Network -- Document Image Quality Assessment via Explicit Blur and Text Size Estimation -- Analyzing the potential of Zero-Shot Recognition for Document Image Classification -- Gender Detection Based on Spatial Pyramid Matching -- EDNets: Deep Feature Learning for Document Image Classification based on Multi-view Encoder-Decoder Neural Networks -- Fast End-to-end Deep Learning Identity Document Detection, Classification and Cropping -- Gold-Standard Benchmarks and Data Sets -- Image Collation: Matching illustrations in manuscripts -- Revisiting the Coco Panoptic Metric to Enable Visual and Qualitative Analysis of Historical Map Instance Segmentation.-A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes -- GNHK: A Dataset for English Handwriting in the Wild -- Personalizing Handwriting Recognition Systems with Limited User-Specific Samples -- An Efficient Local Word Augment Approach for Mongolian Handwritten Script Recognition -- IIIT-INDIC-HW-WORDS: A Dataset for Indic Handwritten Text Recognition -- Historical Document Analysis -- AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptions -- TS-Net: OCR Trained to Switch Between Text Transcription Styles -- Handwriting Recognition with Novelty -- Vectorization of Historical Maps Using Deep Edge Filtering and Closed Shape Extraction -- Data Augmentation Based on CycleGAN for Improving Woodblock-printing Mongolian Words Recognition -- SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization -- Handwriting Recognition -- Recognizing Handwritten Chinese Texts with Insertion and Swapping Using A Structural AttentionNetwork -- Strikethrough Removal From Handwritten Words Using CycleGANs -- Iterative Weighted Transductive Learning for Handwriting Recognition -- Competition Reports -- ICDAR 2021 Competition on Scientific Literature Parsing -- ICDAR 2021 Competition on Historical Document Classification -- ICDAR 2021 Competition on Document Visual Question Answering -- ICDAR 2021 Competition on Scene Video Text Spotting -- ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment -- ICDAR 2021 Competition on Components Segmentation Task of Document Photos -- ICDAR 2021 Competition on Historical Map Segmentation -- ICDAR 2021 Competition on Time-Quality Document Image Binarization -- ICDAR 2021 Competition on On-Line Signature Verification -- ICDAR 2021 Competition on Script Identification in the Wild -- ICDAR 2021 Competition on Scientific Table Image Recognition to LaTeX -- ICDAR 2021 Competition on Multimodal Emotion Recognition on Comics Scenes -- ICDAR 2021 Competition on Mathematical Formula Detection.

This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. The 182 full papers were carefully reviewed and selected from 340 submissions, and are presented with 13 competition reports. The papers are organized into the following topical sections: scene text detection and recognition, document classification, gold-standard benchmarks and data sets, historical document analysis, and handwriting recognition. In addition, the volume contains results of 13 scientific competitions held during ICDAR 2021.