Ocr accuracy regression harnes

.venv-1/bin/python

@@ -0,0 +1 @@
+python3

.venv-1/bin/python3

@@ -0,0 +1 @@
+/usr/bin/python3

.venv-1/bin/python3.12

@@ -0,0 +1 @@
+python3

.venv-1/lib64

@@ -0,0 +1 @@
+lib

.venv-1/pyvenv.cfg

@@ -0,0 +1,5 @@
+home = /usr/bin
+include-system-site-packages = false
+version = 3.12.3
+executable = /usr/bin/python3.12
+command = /usr/bin/python3 -m venv /workspaces/Soter/.venv-1

.venv/bin/python

@@ -0,0 +1 @@
+python3

.venv/bin/python3

@@ -0,0 +1 @@
+/usr/bin/python3

.venv/bin/python3.12

@@ -0,0 +1 @@
+python3

.venv/lib64

@@ -0,0 +1 @@
+lib

.venv/pyvenv.cfg

@@ -0,0 +1,5 @@
+home = /usr/bin
+include-system-site-packages = false
+version = 3.12.3
+executable = /usr/bin/python3.12
+command = /usr/bin/python3 -m venv /workspaces/Soter/.venv

tmp_ocr_inspect.ipynb

@@ -0,0 +1,61 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "04410dbd",
+   "metadata": {},
+   "source": [
+    "# OCR Golden Input Inspection\n",
+    "\n",
+    "Use this notebook to inspect the existing `app/ai-service/test_id_card.png` image and extract tesseract text plus bounding boxes for expected OCR golden inputs.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9b89948f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e00de119",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3746ce6d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "from PIL import Image\n",
+    "import pytesseract\n",
+    "from pytesseract import Output\n",
+    "\n",
+    "image_path = Path('app/ai-service/test_id_card.png')\n",
+    "img = Image.open(image_path)\n",
+    "data = pytesseract.image_to_data(img, output_type=Output.DICT)\n",
+    "\n",
+    "for i, text in enumerate(data['text']):\n",
+    "    if text.strip():\n",
+    "        print(i, repr(text), data['conf'][i], data['left'][i], data['top'][i], data['width'][i], data['height'][i])\n",
+    "\n",
+    "print('\\n--- summary ---')\n",
+    "print('\\n'.join([text for text in data['text'] if text.strip()]))\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}