Separating text extractor and text classifier.

Exactly what the title says.

Signed-off-by: Ethan Wellenreiter <ewellenreiter@gmail.com>

code/textdataretriever/textextractor/temp.ipynb

@@ -0,0 +1,104 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import cv2\n",
+    "import numpy as np\n",
+    "\n",
+    "import myfunctions as mf\n",
+    "\n",
+    "\n",
+    "import scipy.stats as st\n",
+    "import math\n",
+    "\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "img = cv2.imread('./test_images/IMG_7594.jpg')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "out = mf.houghlineprocessing(img)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cv2.imshow(\"result2\", mf.ResizeWithAspectRatio(out, height=1000))\n",
+    "cv2.waitKey(0)\n",
+    "cv2.destroyAllWindows()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://medium.com/@vatvenger/extracting-lines-from-ocr-a8f410448fc\n",
+    "# https://www.width.ai/post/the-best-ways-to-extract-text-from-images-without-tesseract-python"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Potential Next Steps. Isolate a line of text and then feed that into the OCR Model to extract the text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# #IDEA:\n",
+    "# 1. Isolate lines into rectangles\n",
+    "# 2. feed that rectangle portion of the image into an OCR model\n",
+    "# 3. append that to the final output string with the end character for nextline\n",
+    "# 4. give the whole final string to a model which gives the outputs"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}