add app

.gitignore

@@ -0,0 +1,188 @@
+
+# Created by https://www.toptal.com/developers/gitignore/api/macos,python,jupyternotebooks
+# Edit at https://www.toptal.com/developers/gitignore?templates=macos,python,jupyternotebooks
+
+### JupyterNotebooks ###
+# gitignore template for Jupyter Notebooks
+# website: http://jupyter.org/
+
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Remove previous ipynb_checkpoints
+#   git rm -r .ipynb_checkpoints/
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+
+# IPython
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# End of https://www.toptal.com/developers/gitignore/api/macos,python,jupyternotebooks
+
+# image
+*.JPG

app.py

@@ -0,0 +1,105 @@
+import cv2
+import re
+import pytesseract
+import numpy as np
+import gradio as gr
+import pandas as pd
+from pytesseract import Output
+from matplotlib import pyplot as plt
+
+
+# get grayscale image
+def get_grayscale(image):
+    return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+# noise removal
+def remove_noise(image):
+    return cv2.medianBlur(image,5)
+
+#thresholding
+def thresholding(image, thresh_hold=0, which='ostu'):
+    if which == 'ostu':
+        return cv2.threshold(image, thresh_hold, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
+    elif which == 'simple':
+        _, img = cv2.threshold(image,thresh_hold,255,cv2.THRESH_BINARY)
+        return img
+    elif which == 'adaptive':
+        return cv2.adaptiveThreshold(image, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2)
+
+#dilation
+def dilate(image):
+    kernel = np.ones((5,5),np.uint8)
+    return cv2.dilate(image, kernel, iterations = 1)
+
+#erosion
+def erode(image):
+    kernel = np.ones((5,5),np.uint8)
+    return cv2.erode(image, kernel, iterations = 1)
+
+#opening - erosion followed by dilation
+def opening(image):
+    kernel = np.ones((5,5),np.uint8)
+    return cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel)
+
+#canny edge detection
+def canny(image):
+    return cv2.Canny(image, 100, 200)
+
+#skew correction
+def deskew(image):
+    coords = np.column_stack(np.where(image > 0))
+    angle = cv2.minAreaRect(coords)[-1]
+    if angle < -45:
+        angle = -(90 + angle)
+    else:
+        angle = -angle
+    (h, w) = image.shape[:2]
+    center = (w // 2, h // 2)
+    M = cv2.getRotationMatrix2D(center, angle, 1.0)
+    rotated = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
+    return rotated
+
+#template matching
+def match_template(image, template):
+    return cv2.matchTemplate(image, template, cv2.TM_CCOEFF_NORMED)
+
+def show_cvimg(img, figsize=(15, 15)):
+    fig, ax = plt.subplots(dpi=80, figsize=figsize)
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    ax.imshow(img)
+
+
+def extract_purchased_items(txt):
+    pat = '.*\s*(FB|FA|NB)'
+    p = re.compile("(.*) (\d+[,\.\/\:\']*\d+) (FB|FA|NB)")
+
+    txts = txt.split('\n')
+    items = []
+    not_parsed = []
+    for t in txts:
+        if re.match(pat, t):
+            result = p.search(t)
+            if result is not None:
+                items.append({'item': result.group(1),
+                              'price': re.sub('[,\.\/\:\']', '.', result.group(2)),
+                              'type': result.group(3)
+                             })
+            else:
+                not_parsed.append({'not parsed': t})
+    return pd.DataFrame(items), pd.DataFrame(not_parsed)
+
+
+def parse_receipt(img, **kwargs):
+    # preprocessing
+    gray = get_grayscale(img)
+    thresh = thresholding(gray, **kwargs)
+
+    # ocr
+    custom_config = r'--oem 3 --psm 6'
+    txt = pytesseract.image_to_string(thresh, config=custom_config)
+
+    return extract_purchased_items(txt)
+
+
+iface = gr.Interface(fn=parse_receipt, inputs="image", outputs=["dataframe", "dataframe"])
+iface.launch()

requirements.txt

@@ -0,0 +1,6 @@
+opencv-python
+pytesseract
+numpy
+pandas
+gradio
+matplotlib