EADST

Code for SPIE paper - CEIR

CEIR

This project is for the SPIE paper - Novel Receipt Recognition with Deep Learning Algorithms. In this paper, we propose an end-to-end novel receipt recognition system for capturing effective information from receipts (CEIR).

CEIR code and results have been made available at: CEIR code

CEIR system demo is available at: CEIR Demo

The CEIR has three parts: preprocess, detection, recognition.

Introduction

In the preprocessing method, by converting the image to gray scale and obtaining the gradient with the Sobel operator, the outline of the receipt area is decided by morphological transformations with the elliptic kernel.

In text detection, the modified connectionist text proposal network to execute text detection. The pytorch implementation of detection is based on CTPN.

In text recognition, the convolutional recurrent neural network with the connectionist temporal classification with maximum entropy regularization as a loss function to update the weights in networks and extract the characters from receipt. The pytorch implementation of recognition is based on CRNN and ENESCTC.

We validate our system with the scanned receipts optical character recognition and information extraction (SROIE) database.

Dependency

Python 3.6.3 1. torch==1.4 2. torchvision 3. opencv-python 4. lmdb

Prediction

  1. Download pre-trained model from Google Drive and put the file under ./detection/output/ folder.

  2. Change the image name to demo.jpg in the CEIR folder.

  3. Run python ceir_crop.py for stage 1.
  4. Run python ceir_detect.py for stage 2.
  5. Run python ceir_recognize.py for stage 3.

  6. The result will be saved in ./result/.

Training

  1. Put dataset in ./dataset/train/image and ./dataset/train/label.

  2. Preprocess parameters can be changed in ./preprocess/crop.py.

  3. In the detection part, the ./detection/config.py is used for configuring. After that, run python train.py in the detection folder.

  4. In recognition, you need to change trainroot and other parameters in train.sh, then run sh train.sh to train.

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

本站现有博文340篇,共被浏览1019217次

本站已经建立2719天!

热门文章
文章归档
回到顶部