├── requirements.txt ├── .gitattributes ├── LICENSE ├── readme.md ├── main.py └── .gitignore /requirements.txt: -------------------------------------------------------------------------------- 1 | opencv-python 2 | pytesseract 3 | openai -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- 1 | # Auto detect text files and perform LF normalization 2 | * text=auto 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2024 Tom Shaw 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /readme.md: -------------------------------------------------------------------------------- 1 | # Receipt Parser 2 | 3 | This project extracts text from an image of a store receipt and converts it into a structured JSON object using OCR and AI. 4 | 5 | ## Requirements 6 | 7 | - Python 3.x 8 | - OpenCV 9 | - Pytesseract 10 | - OpenAI Python client 11 | 12 | ## Installation 13 | 14 | 1. Clone the repository: 15 | ```sh 16 | git clone 17 | cd 18 | ``` 19 | 20 | 2. Install the required packages: 21 | ```sh 22 | pip install -r requirements.txt 23 | ``` 24 | 25 | 3. Add your OpenAI API key in [main.py]: 26 | ```python 27 | ai_client = OpenAI( 28 | api_key="YOUR_OPEN_AI_API_KEY" 29 | ) 30 | ``` 31 | 32 | ## Usage 33 | 34 | 1. Add an image of a receipt named `receipt.jpg` to the project directory. 35 | 36 | 2. Run the script: 37 | ```sh 38 | python main.py 39 | ``` 40 | 41 | 3. The extracted JSON data will be saved in `receipt.json`. 42 | 43 | ## Project Structure 44 | 45 | - main.py: The main script that processes the image, extracts text, and converts it to JSON. 46 | - requirements.txt: The list of required Python packages. 47 | - readme.md: Project documentation. 48 | 49 | ## License 50 | 51 | This project is licensed under the MIT License. 52 | 53 | ## Credit 54 | 55 | This project was created by [Tom Shaw](https://tomshaw.dev) 56 | -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | import cv2 2 | import pytesseract 3 | from openai import OpenAI 4 | 5 | ai_client = OpenAI( 6 | api_key="YOUR_OPEN_AI_API_KEY" 7 | ) 8 | 9 | def preprocess_image(image): 10 | image = cv2.imread(image) 11 | # Convert the image to grayscale 12 | gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) 13 | 14 | # Save the grayscale image 15 | 16 | cv2.imwrite('gray_image.jpg', gray) 17 | 18 | # Apply thresholding 19 | _, threshold = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) 20 | 21 | # Save the thresholded image 22 | 23 | cv2.imwrite('thresholded_image.jpg', threshold) 24 | 25 | return threshold 26 | 27 | def extract_text(image): 28 | return pytesseract.image_to_string(image) 29 | 30 | def ai_extract(text_content): 31 | prompt = """You are a receipt parser AI. I am going to provide you with text extracted from an image of a store receipt. 32 | I need you to return a JSON object with this structure: 33 | {“total”, “business”, “items”: [{“title”, “quantity”, “price”}], “transaction_timestamp”}. 34 | Return the prices as integers that represent the number of pennies (£1 = 100) Only return the JSON object. 35 | Do not return anything else. Here is the text extracted from the receipt: """ + text_content 36 | 37 | response = ai_client.chat.completions.create( 38 | model="gpt-4o", 39 | messages=[ 40 | { 41 | "role": "user", 42 | "content": prompt 43 | } 44 | ] 45 | ) 46 | 47 | return response.choices[0].message.content[response.choices[0].message.content.find('{'):response.choices[0].message.content.rfind('}')+1] 48 | 49 | if __name__ == '__main__': 50 | 51 | image_path = "receipt.jpg" 52 | 53 | preprocessed_image = preprocess_image(image_path) 54 | 55 | text_content = extract_text(preprocessed_image) 56 | 57 | json_data = ai_extract(text_content) 58 | 59 | with open('receipt.json', 'w') as f: 60 | f.write(json_data) -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | --------------------------------------------------------------------------------