{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# How To: Crop and Pad Images for Batch Consistency\n",
    "\n",
    "Use `ImageCropper` to remove scanner borders and `ImagePadder` to make\n",
    "images a uniform size for batch processing."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-04-21T02:47:55.491664Z",
     "start_time": "2026-04-21T02:47:53.080606Z"
    }
   },
   "outputs": [],
   "source": [
    "from phenotypic.data import load_yeast_plate_full\n",
    "from phenotypic.correction import ImageCropper, ImagePadder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-04-21T02:47:56.888576Z",
     "start_time": "2026-04-21T02:47:55.492351Z"
    }
   },
   "outputs": [],
   "source": [
    "plate = load_yeast_plate_full()\n",
    "print(f\"Original size: {plate.shape}\")\n",
    "plate.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Crop Scanner Borders\n",
    "\n",
    "Remove unwanted borders by specifying pixels to trim from each edge."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-04-21T02:47:57.711587Z",
     "start_time": "2026-04-21T02:47:56.907121Z"
    }
   },
   "outputs": [],
   "source": [
    "cropper = ImageCropper(top=450, bottom=450, left=450, right=450)\n",
    "cropped = cropper.apply(plate)\n",
    "print(f\"Cropped size: {cropped.shape}\")\n",
    "cropped.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Pad to Uniform Size\n",
    "\n",
    "When batch-processing plates of different sizes, pad them to a consistent\n",
    "dimension."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2026-04-21T02:47:58.302812Z",
     "start_time": "2026-04-21T02:47:57.726570Z"
    }
   },
   "outputs": [],
   "source": [
    "padder = ImagePadder(top=20, bottom=20, left=20, right=20, mode=\"constant\",\n",
    "                     constant_value=0)\n",
    "padded = padder.apply(cropped)\n",
    "print(f\"Padded size: {padded.shape}\")\n",
    "padded.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Both operations can be included in an `ImagePipeline` for batch\n",
    "processing. Place `ImageCropper` first, then `ImagePadder`, before\n",
    "any detection steps."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}