Untitled.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import cv2\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "tmp_image = np.zeros((500, 500, 3), dtype=np.uint8)\n",
    "tmp_image = cv2.rectangle(tmp_image, (0, 0), (500, 500), (255, 255, 0), -1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "sub_image = np.zeros((25, 25, 3), dtype=np.uint8)\n",
    "sub_image = cv2.circle(sub_image, (12, 12), 11, (255, 0, 0), -1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x254b09f8d30>"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAD8CAYAAAC4nHJkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrd6JGq7nixwAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x254b0a8d128>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(sub_image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "tmp_image[100:125, 100:125, :] = sub_image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x254b1d64278>"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAQsAAAD8CAYAAABgtYFHAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxbCQ1GJYSGr5f3G5xN1SrqIUAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x254b098be10>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(tmp_image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "nonzero = np.nonzero(sub_image.sum(axis=2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "tmp_image[100:125,100:125,:][nonzero]=sub_image[nonzero]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x254b0ab8940>"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAQsAAAD8CAYAAABgtYFHAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxbCQ1GJYSGr5f3G5xN1SrqIUAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x254b0986ac8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(tmp_image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}