EADST

Data Augmentation for Handwritten Recognition

I read some data augmentation papers this week.

Data augmentation has three main areas.

  • Space transform
  • Color change
  • Information delect

Here are four papers where three papers using space transform and one paper taking information delect.

  1. Bhunia, Ayan & Das, Abhirup & Bhunia, Ankan & Perla, Sai & Roy, Partha. (2019). Handwriting Recognition in Low-Resource Scripts Using Adversarial Learning. 10.1109/CVPR.2019.00490.

    • They propose the algorithm, Adversarial Feature Deformation Module (AFDM) inspired by Spatial Transformation Networks (STN).

      • Localisation Network: using Generative Adversarial Networks (GANs) to generate the transform matrix.
      • Grid Generator: transforming feature maps with matrix.
      • Sampler: based on the neighbor relative position to update weights.

      image

  2. Luo, Canjie & Zhu, Yuanzhi & Jin, Lianwen & Wang, Yongpan. (2020). Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition.

    • They combine moving least squares with a learnable agent to augment data.

      Code

      image

  3. C. Wigington, S. Stewart, B. Davis, B. Barrett, B. Price and S. Cohen, "Data Augmentation for Recognition of Handwritten Words and Lines Using a CNN-LSTM Network," 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, 2017, pp. 639-645, doi: 10.1109/ICDAR.2017.110.

    • They reshape the characters with the normal distribution where the parameters from the normalization step.

      image

  4. Pengguang Chen. GridMask data augmentation. arXiv preprint arXiv:2001.04086, 2020. 3.

    • They use grid mask strategy to shadow some blocks with the grid for image.
    • A handwritten recognition is used in this paper: GridMask Based Data Augmentation for Bengali Handwritten Grapheme Classification

      Code

      image

相关标签
About Me
XD
Goals determine what you are going to be.
Category
标签云
Bipartite 报税 ONNX Jev logger Claude Google Qwen 关于博主 Jupyter Paddle v2ray git-lfs 顶会 Freesound CTC TensorRT Clash WebCrawler QWEN TTS Docker Cloudreve Password GIT 算法题 Safetensors UNIX Pickle API Miniforge 多线程 uwsgi PDF Github Plotly Food Pandas Anaconda VPN Shortcut Gemma Website Random tqdm Sklearn SAM Django Markdown EXCEL 长期记忆 OCR Harness Template 搞笑 DeepStream Qwen2.5 printf hf 多进程 Tracking GGML SVR Numpy Pytorch mmap diffusers Git uWSGI LaTeX ModelScope Algorithm Card 强化学习 Attention RAR Domain HaggingFace Tensor PyTorch Excel Llama TSV VSCode LLAMA Diagram CV 飞书 阿里云 GoogLeNet CC XML llama.cpp C++ Firewall Review WAN 论文 Qwen2 Input Use FP32 Rebuttal Tiktoken Distillation InvalidArgumentError COCO Heatmap 净利润 Datetime 继承 FlashAttention LoRA 域名 Logo Crawler 音频 OpenCV torchinfo UI GPT4 财报 GPTQ BeautifulSoup RL 自我改进 腾讯云 Base64 SQL Jetson NLP Quantize transformers MD5 Magnet 云服务器 Image2Text Plate Dataset AI 图标 Transformers RGB Python Linux Proxy TensorFlow Vmess 证件照 Color CLAP XGBoost 个人博客 Video Web 签证 Search Michelin CUDA YOLO Hungarian NLTK Paper Permission scipy API网关 PIP Statistics Animate Quantization ChatGPT Hotel Data FP16 Translation Ubuntu IndexTTS2 News VGG-16 Hilton OpenAI Land Baidu Bert Interview Windows Conda ResNet-50 LLM git v0.dev 图形思考法 DeepSeek PDB icon SPIE Vim 递归学习法 Bin Knowledge Mixtral ms-swift Augmentation Pillow FP64 CSV Nginx Breakpoint BF16 版权 JSON NameSilo Zip FastAPI PyCharm SQLite 论文速读 Bitcoin FP8 HuggingFace Disk Agent BTC Ptyhon CEIR Math 第一性原理 Streamlit 公式 CAM tar LeetCode
站点统计

本站现有博文340篇,共被浏览1017842次

本站已经建立2718天!

热门文章
文章归档
回到顶部