.png){kind=icon}
返回
Evaluating synthetic pre-Training for handwriting processing tasks
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2023.06.003.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this work, we explore massive pre-training on synthetic word images for enhancing the performance on four benchmark downstream handwriting analysis tasks. To this end, we build a large synthetic dataset of word images rendered in several handwriting fonts, which offers a complete supervision sig-nal. We use it to train a simple convolutional neural network (ConvNet) with a fully supervised objective. The vector representations of the images obtained from the pre-trained ConvNet can then be consid-ered as encodings of the handwriting style. We exploit such representations for Writer Retrieval, Writer Identification, Writer Verification, and Writer Classification and demonstrate that our pre-training strat-egy allows extracting rich representations of the writers' style that enable the aforementioned tasks with competitive results with respect to task-specific State-of-the-Art approaches.& COPY; 2023 Elsevier B.V. All rights reserved.
Keyword:
Handwritten text
Synthetic data
Writer retrieval
Writer identification
Writer verification
Writer classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
Learning features for offline handwritten signature verification using deep convolutional neural networks基于深度卷积神经网络的离线手写签名验证特征学习.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Deep adaptive learning for writer identification based on single handwritten word imagesPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Offline signature verification using a region based deep metric learning networkPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏GR-RNN: Global-context residual recurrent neural networks for writer identificationPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容