first

LICENSE

@@ -0,0 +1,17 @@
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

README.md

@@ -0,0 +1,42 @@
+WoW Screenshot OCR
+==============
+
+Deep learning OCR models to read text from WoW screenshots. Based on a detector that spots text frames from screenshots, and a recognizer that reads text from detected frames.
+
+- Chat
+- Combat log
+- Nameplates
+- UI frames
+- Map
+
+Usage
+----
+
+Models will use pre trained weights, you don't have to train anything
+
+```
+import wow_ocr
+
+# Init pipeline, detector and recognizer models with pre trained weights
+pipeline = wow_ocr.pipeline.Pipeline()
+
+
+# Screenshots example
+images = [
+    wow_ocr.tools.read(url)
+    for url in [
+        "https://image_url.com/1.jpg",
+        "https://image_url.com/2.jpg",
+    ]
+]
+
+# Results - Image to Text
+prediction_groups = pipeline.recognize(images)
+# # Each list of predictions in prediction_groups is a list of
+# # (word, box) tuples.
+
+```
+
+![](p1.webp)
+![](p2.webp)
+

pyproject.toml

@@ -0,0 +1,36 @@
+[build-system]
+requires      = ["setuptools>=61.0.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "wow-ocr"
+version = "0.0.0"
+description = "A packaged OCR model to read texts into WoW screenshots"
+readme = "README.md"
+authors = [{ name = "Geo", email = "[email protected]" }]
+license = { file = "LICENSE" }
+classifiers = [
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+]
+keywords = ["ocr", "wow", "screenshot"]
+dependencies = [
+    "validators",
+    "essential_generators",
+    "tqdm",
+    "imgaug",
+    "fonttools",
+    "editdistance",
+    "pyclipper",
+    "shapely",
+    "efficientnet",
+    "tensorflow",
+]
+requires-python = ">=3.9"
+
+[project.optional-dependencies]
+dev = ["black", "pip-tools", "pytest", "types-requests", "types-pkg-resources"]
+
+[project.urls]
+Homepage = "https://github.com/geo-tp/wow-ocr"

setup.cfg

@@ -0,0 +1,9 @@
+
+# Config for projects that do not yet support pyproject.toml (PEP-518)
+# https://www.python.org/dev/peps/pep-0518/
+
+# mypy: https://github.com/python/mypy/issues/5205
+[mypy]
+ignore_missing_imports = True
+check_untyped_defs = True
+ha

wow_ocr/__init__.py

@@ -0,0 +1,3 @@
+from . import detector, recognizer, tools, pipeline
+
+__version__ = "0.0.0"