implemented text recognition (ocr)

README.md

@@ -51,6 +51,7 @@ This program can be used to automatically start, split, and reset your preferred
   - Wayland is not currently supported
   - WSL2/WSLg requires an additional Desktop Environment, external X11 server, and/or systemd
 - Python 3.10+ (Not required for normal use. Refer to the [build instructions](/docs/build%20instructions.md) if you'd like run the application directly in Python).
+- Tesseract-OCR (optional; requierd for text recognition as an alternative comparison method). See https://github.com/UB-Mannheim/tesseract/wiki for installation instructions.
 
 ## OPTIONS
 
@@ -226,6 +227,49 @@ You can have one (and only one) image with the keyword `reset` in its name. Auto
 
 The Start Image is similar to the Reset Image. You can only have one Start Image with the keyword `start_auto_splitter`.You can reload the image using the "`Reload Start Image`" button. The pause time is the amount of seconds AutoSplit will wait before starting comparisons of the first split image. Delay times will be used to delay starting your timer after the threshold is met.
 
+### Text Recognition (OCR)
+
+You can use text recognition as an alternative comparison method.
+First you need to install tesseract and include it in your PATH variable. See [Compatibility](#Compatibility) above.
+
+To include tesseract in your PATH variable you can use this powershell snippet.
+
+Note: change the `$tesseract_path` variable to the location where tesseract is installed.
+
+```
+$path = [System.Environment]::GetEnvironmentVariable("Path", "User")
+$tesseract_path = "C:\Program Files\Tesseract-OCR"
+[System.Environment]::SetEnvironmentVariable("Path", "$path;$tesseract_path", "User")
+```
+
+To use this feature you need to place a text file (.txt) in your splits folder instead of an image file.
+
+An example file name and content could look like this:
+
+Filename: `001_start_auto_splitter.txt`
+
+Content:
+
+```
+texts = ["complete any 2 encounters"]
+top_left = 275
+top_right = 540
+bottom_left = 70
+bottom_right = 95
+fps_limit = 1
+```
+
+The `texts` field is an array and can take more than one text to look for:
+
+```
+texts = ["look for me", "or this text"]
+```
+
+The `top`, `bottom`, `left` and `right` options define a rectangle where the text you are looking for is expected to appear in the image.
+
+Note: This method can cause high CPU usage at the standard comparison FPS. You should therefor limit the comparison FPS when you use this method to 1 or 2 FPS using the `fps_limit` option.
+The size of the selected rectangle can also impact the CPU load (bigger = more CPU load).
+
 ### Profiles
 
 <!-- TODO: Profiles are saved under `%appdata%\AutoSplit\profiles` and -->

scripts/requirements.txt

@@ -4,6 +4,7 @@
 #
 # Dependencies:
 git+https://github.com/boppreh/keyboard.git#egg=keyboard  # Fix install on macos and linux-ci https://github.com/boppreh/keyboard/pull/568
+Levenshtein
 numpy>=1.26  # Python 3.12 support
 opencv-python-headless>=4.9.0.80  # Typing fixes
 packaging

src/AutoSplit.py

@@ -307,7 +307,8 @@ def __reload_start_image(self, started_by_button: bool = False, wait_for_delay:
         self.highest_similarity = 0.0
         self.reset_highest_similarity = 0.0
         self.split_below_threshold = False
-        self.timer_start_image.start(int(ONE_SECOND / self.settings_dict["fps_limit"]))
+
+        self.timer_start_image.start(int(ONE_SECOND / self.start_image.get_fps_limit(self)))
 
         QApplication.processEvents()
 
@@ -683,7 +684,7 @@ def __similarity_threshold_loop(self, number_of_split_images: int, dummy_splits_
             QApplication.processEvents()
 
             # Limit the number of time the comparison runs to reduce cpu usage
-            frame_interval = 1 / self.settings_dict["fps_limit"]
+            frame_interval = 1 / self.split_image.get_fps_limit(self)
             # Use a time delta to have a consistant check interval
             wait_delta_ms = int((frame_interval - (time() - start) % frame_interval) * ONE_SECOND)
 
@@ -867,7 +868,11 @@ def __update_split_image(self, specific_image: AutoSplitImage | None = None):
 
         # Get split image
         self.split_image = specific_image or self.split_images_and_loop_number[0 + self.split_image_number][0]
-        if is_valid_image(self.split_image.byte_array):
+        if self.split_image.is_ocr:
+            # TODO: test if setText clears a set image
+            text = "\nor\n".join(self.split_image.texts)
+            self.current_split_image.setText(f"Looking for OCR text:\n{text}")
+        elif is_valid_image(self.split_image.byte_array):
             set_preview_image(self.current_split_image, self.split_image.byte_array)
 
         self.current_image_file_label.setText(self.split_image.filename)

src/AutoSplitImage.py

@@ -5,10 +5,11 @@
 
 import cv2
 import numpy as np
+import toml
 from cv2.typing import MatLike
 
 import error_messages
-from compare import check_if_image_has_transparency, get_comparison_method_by_index
+from compare import check_if_image_has_transparency, extract_and_compare_text, get_comparison_method_by_index
 from utils import BGR_CHANNEL_COUNT, MAXBYTE, ColorChannel, ImageShape, is_valid_image
 
 if TYPE_CHECKING:
@@ -40,13 +41,27 @@
     image_type: ImageType
     byte_array: MatLike | None = None
     mask: MatLike | None = None
+    texts: list[str]
     # This value is internal, check for mask instead
     _has_transparency = False
     # These values should be overriden by some Defaults if None. Use getters instead
     __delay_time: float | None = None
     __comparison_method: int | None = None
     __pause_time: float | None = None
     __similarity_threshold: float | None = None
+    __x: int
+    __xx: int
+    __y: int
+    __yy: int
+    __fps_limit: int
+
+    @property
+    def is_ocr(self):
+        """
+        Whether a "split image" is actually for Optical Text Recognition
+        based on whether there's any text strings to search for.
+        """
+        return bool(self.texts)
 
     def get_delay_time(self, default: "AutoSplit | int"):
         """Get image's delay time or fallback to the default value from spinbox."""
@@ -80,16 +95,31 @@
             return default
         return default.settings_dict["default_similarity_threshold"]
 
+    def get_fps_limit(self, default: "AutoSplit"):
+        """Get image's fps limit or fallback to the default value from spinbox."""
+        if self.__fps_limit != 0:
+            return self.__fps_limit
+        return default.settings_dict["fps_limit"]
+
     def __init__(self, path: str):
         self.path = path
         self.filename = os.path.split(path)[-1].lower()
         self.flags = flags_from_filename(self.filename)
         self.loops = loop_from_filename(self.filename)
+        self.texts = list[str]()
         self.__delay_time = delay_time_from_filename(self.filename)
         self.__comparison_method = comparison_method_from_filename(self.filename)
         self.__pause_time = pause_from_filename(self.filename)
         self.__similarity_threshold = threshold_from_filename(self.filename)
-        self.__read_image_bytes(path)
+        self.__x = 0
+        self.__xx = 0
+        self.__y = 0
+        self.__yy = 0
+        self.__fps_limit = 0
+        if path.endswith("txt"):
+            self.__parse_text_file(path)
+        else:
+            self.__read_image_bytes(path)
 
         if START_KEYWORD in self.filename:
             self.image_type = ImageType.START
@@ -98,6 +128,18 @@
         else:
             self.image_type = ImageType.SPLIT
 
+    def __parse_text_file(self, path: str):
+        with open(path, encoding="utf-8") as f:
+            data = toml.load(f)
+            self.texts = data["texts"]
+            self.__x = data["top_left"]
+            self.__xx = data["top_right"]
+            self.__y = data["bottom_left"]
+            self.__yy = data["bottom_right"]
+            self.__fps_limit = 1
+            if "fps_limit" in data:
+                self.fps_limit = data["fps_limit"]
+
     def __read_image_bytes(self, path: str):
         image = cv2.imread(path, cv2.IMREAD_UNCHANGED)
         if not is_valid_image(image):
@@ -140,8 +182,17 @@
         default: "AutoSplit | int",
         capture: MatLike | None,
     ):
-        """Compare image with capture using image's comparison method. Falls back to combobox."""
-        if not is_valid_image(self.byte_array) or not is_valid_image(capture):
+        """
+        Compare image with capture using image's comparison method. Falls back to combobox.
+        For OCR text files: extract image text from rectangle position and compare it with the expected string.
+        """
+        if not is_valid_image(capture):
+            return 0.0
+
+        if self.is_ocr:
+            return extract_and_compare_text(capture[self.__y:self.__yy, self.__x:self.__xx], self.texts)
+
+        if not is_valid_image(self.byte_array):
             return 0.0
         resized_capture = cv2.resize(capture, self.byte_array.shape[1::-1])
 

src/compare.py

@@ -1,11 +1,12 @@
 from math import sqrt
 
 import cv2
+import Levenshtein
 import numpy as np
 from cv2.typing import MatLike
 from scipy import fft
 
-from utils import BGRA_CHANNEL_COUNT, MAXBYTE, ColorChannel, ImageShape, is_valid_image
+from utils import BGRA_CHANNEL_COUNT, MAXBYTE, ColorChannel, ImageShape, is_valid_image, run_tesseract
 
 MAXRANGE = MAXBYTE + 1
 CHANNELS = [ColorChannel.Red.value, ColorChannel.Green.value, ColorChannel.Blue.value]
@@ -126,6 +127,37 @@
     return 1 - (hash_diff / 64.0)
 
 
+def extract_and_compare_text(capture: MatLike, texts: list[str]):
+    """
+    Compares the extracted text of the given image and returns the similarity between the two texts.
+    The best match of all texts is returned.
+
+    @param capture: Image of any given shape as a numpy array
+    @param texts: a list of strings to match for
+    @return: The similarity between the text in the image and the text supplied as a number 0 to 1.
+    """
+    png = np.array(cv2.imencode(".png", capture)[1]).tobytes()
+    # If the string is found 1:1 in the string extracted from the image a 1 is returned.
+    # Otherwise the levenshtein ratio is calculated between the two strings and gets returned.
+    # Especially with stylised characters, OCR could conceivably get the right
+    # letter, but mix up the casing (m/M, o/O, t/T, etc.)
+    image_string = run_tesseract(png).lower().strip()
+
+    ratio = 0.0
+    for text in texts:
+        # TODO: this 1:1 matching could lead to false positives
+        # maybe remove it and only rely on fuzzy matching?
+        # discussion: https://github.com/Toufool/AutoSplit/pull/272#discussion_r1477120477
+        if text in image_string:
+            ratio = 1.0
+            break
+        ratio = max(ratio, Levenshtein.ratio(text, image_string))
+    # TODO: debug: remove me
+    if ratio > 0.9:  # noqa: PLR2004
+        print(f"text from image ({ratio:,.2f}): {image_string}")
+    return ratio
+
+
 def __compare_dummy(*_: object):
     return 0.0
 

src/split_parser.py

@@ -209,7 +209,7 @@ def parse_and_validate_images(autosplit: "AutoSplit"):
     else:
         for image in split_images:
             # Test for image without transparency
-            if not is_valid_image(image.byte_array):
+            if not image.is_ocr and not is_valid_image(image.byte_array):
                 error_message = partial(error_messages.image_validity, image.filename)
                 break
 

src/utils.py

@@ -1,10 +1,12 @@
 import asyncio
 import os
+import subprocess  # noqa: S404
 import sys
 from collections.abc import Callable, Iterable
 from enum import IntEnum
 from functools import partial
 from itertools import chain
+from os import environ
 from platform import version
 from threading import Thread
 from typing import TYPE_CHECKING, Any, TypeGuard, TypeVar
@@ -37,6 +39,9 @@
 
 T = TypeVar("T")
 
+TESSERACT_CMD = ["tesseract", "-", "-", "--oem", "1", "--psm", "6"]
+DEFAULT_ENCODING = "utf-8"
+
 DWMWA_EXTENDED_FRAME_BOUNDS = 9
 MAXBYTE = 255
 ONE_SECOND = 1000
@@ -126,8 +131,6 @@
     if sys.platform == "win32":
         os.startfile(file_path)  # noqa: S606
     else:
-        import subprocess  # noqa: PLC0415, S404
-
         opener = "xdg-open" if sys.platform == "linux" else "open"
         subprocess.call([opener, file_path])  # noqa: S603
 
@@ -209,6 +212,41 @@
     return chain.from_iterable(nested_iterable)
 
 
+def subprocess_args():
+    """
+    See https://github.com/pyinstaller/pyinstaller/wiki/Recipe-subprocess
+    for reference and comments.
+
+    This code snippet was copied from https://github.com/madmaze/pytesseract
+    """
+    kwargs = {
+        "stdin": subprocess.PIPE,
+        "stdout": subprocess.PIPE,
+        "stderr": subprocess.DEVNULL,
+        "startupinfo": None,
+        "env": environ,
+    }
+
+    if hasattr(subprocess, "STARTUPINFO"):
+        kwargs["startupinfo"] = subprocess.STARTUPINFO()
+        kwargs["startupinfo"].dwFlags |= subprocess.STARTF_USESHOWWINDOW
+        kwargs["startupinfo"].wShowWindow = subprocess.SW_HIDE
+
+    return kwargs
+
+
+def run_tesseract(png: bytes):
+    """
+    Executes the tesseract CLI and pipes a PNG encoded image to it.
+
+    @param png: PNG encoded image as byte array
+    @return: The recognized output string from tesseract
+    """
+    p = subprocess.Popen(TESSERACT_CMD, **subprocess_args())  # noqa: S603
+    output = p.communicate(input=png)[0]
+    return output.decode(DEFAULT_ENCODING)
+
+
 # Environment specifics
 WINDOWS_BUILD_NUMBER = int(version().split(".")[-1]) if sys.platform == "win32" else -1
 FIRST_WIN_11_BUILD = 22000