{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Image Preprocessing - Crop\n\n안녕하세요. 캐코 3회 대회는 자동차 이미지 분류 문제인데요.\n\n제공되는 데이터를 보면 이미지에 자동차 외에 배경도 포함되어 있는 것을 볼 수 있습니다.\n\n이미지에서 이런 배경 부분을 없애고 자동차 부분만 모델 트레이닝 하는데 사용한다면 더 좋은 성능을 얻을 수 있을거라 생각되는데요.\n\n대회 운영진인 김태진님이 공유한 아래의 베이스라인 커널은 제공되는 이미지를 그대로 사용하고 있지만, 바운딩 박스 처리에 대한 언급을 하셨습니다.\n\nhttps://www.kaggle.com/fulrose/3rd-ml-month-car-model-classification-baseline\n\n그래서 본 커널에서는 데이터에서 제공되는 바운딩 박스를 기준으로 이미지를 잘라 저장해서, 이 데이터를 모델에 사용할 수 있도록 하겠습니다.\n\n대부분의 코드는 김태진님이 공유한 커널을 바탕으로 했습니다."},{"metadata":{},"cell_type":"markdown","source":"# Cropped Image Dataset\n\n본 커널에서 생성한 Crop 이미지 데이터는 아래 링크의 Kaggle Dataset으로 만들었으니 자유롭게 사용하시면 됩니다.\n\nhttps://www.kaggle.com/tmheo74/3rd-ml-month-car-image-cropping-dataset"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import gc\nimport os\nimport glob\nimport zipfile\nimport warnings\nimport numpy as np \nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom tqdm import tqdm\n\nimport cv2\nimport PIL\nfrom PIL import ImageOps, ImageFilter, ImageDraw","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"DATA_PATH = '../input/'\nos.listdir(DATA_PATH)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# 이미지 폴더 경로\nTRAIN_IMG_PATH = os.path.join(DATA_PATH, 'train')\nTEST_IMG_PATH = os.path.join(DATA_PATH, 'test')\n\n# CSV 파일 경로\ndf_train = pd.read_csv(os.path.join(DATA_PATH, 'train.csv'))\ndf_test = pd.read_csv(os.path.join(DATA_PATH, 'test.csv'))\ndf_class = pd.read_csv(os.path.join(DATA_PATH, 'class.csv'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def crop_boxing_img(img_name, margin=16) :\n    if img_name.split('_')[0] == \"train\" :\n        PATH = TRAIN_IMG_PATH\n        data = df_train\n    elif img_name.split('_')[0] == \"test\" :\n        PATH = TEST_IMG_PATH\n        data = df_test\n        \n    img = PIL.Image.open(os.path.join(PATH, img_name))\n    pos = data.loc[data[\"img_file\"] == img_name, \\\n                   ['bbox_x1','bbox_y1', 'bbox_x2', 'bbox_y2']].values.reshape(-1)\n\n    width, height = img.size\n    x1 = max(0, pos[0] - margin)\n    y1 = max(0, pos[1] - margin)\n    x2 = min(pos[2] + margin, width)\n    y2 = min(pos[3] + margin, height)\n    \n    if abs(pos[2] - pos[0]) > width or abs(pos[3] - pos[1]) > height:\n        print(f'{img_name} is wrong bounding box, img size: {img.size},  bbox_x1: {pos[0]}, bbox_x2: {pos[2]}, bbox_y1: {pos[1]}, bbox_y2: {pos[3]}')\n        return img\n\n    return img.crop((x1,y1,x2,y2))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Process Train Image Data Crop"},{"metadata":{"trusted":true},"cell_type":"code","source":"for i, row in df_train.iterrows():\n    cropped = crop_boxing_img(row['img_file'])\n    cropped.save(row['img_file'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Process Test Image Data Crop"},{"metadata":{"trusted":true},"cell_type":"code","source":"for i, row in df_test.iterrows():\n    cropped = crop_boxing_img(row['img_file'])\n    cropped.save(row['img_file'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Cropped Image Eye Checking"},{"metadata":{},"cell_type":"markdown","source":"## Train Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"tmp_imgs = df_train['img_file'][100:105]\nplt.figure(figsize=(12,20))\n\nfor num, f_name in enumerate(tmp_imgs):\n    img = PIL.Image.open(os.path.join(TRAIN_IMG_PATH, f_name))\n    plt.subplot(5, 2, 2*num + 1)\n    plt.title(f_name)\n    plt.imshow(img)\n    plt.axis('off')\n    \n    img_crop = PIL.Image.open(f_name)\n    plt.subplot(5, 2, 2*num + 2)\n    plt.title(f_name + ' cropped')\n    plt.imshow(img_crop)\n    plt.axis('off')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Test Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"tmp_imgs = df_test['img_file'][100:105]\nplt.figure(figsize=(12,20))\n\nfor num, f_name in enumerate(tmp_imgs):\n    img = PIL.Image.open(os.path.join(TEST_IMG_PATH, f_name))\n    plt.subplot(5, 2, 2*num + 1)\n    plt.title(f_name)\n    plt.imshow(img)\n    plt.axis('off')\n    \n    img_crop = PIL.Image.open(f_name)\n    plt.subplot(5, 2, 2*num + 2)\n    plt.title(f_name + ' cropped')\n    plt.imshow(img_crop)\n    plt.axis('off')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Zip Train, Test Image"},{"metadata":{"trusted":true},"cell_type":"code","source":"with zipfile.ZipFile('train_crop.zip','w') as zip: \n        # writing each file one by one \n        for file in glob.glob('train*.jpg'): \n            zip.write(file)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with zipfile.ZipFile('test_crop.zip','w') as zip: \n        # writing each file one by one \n        for file in glob.glob('test*.jpg'): \n            zip.write(file)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Delete Image After Zipping"},{"metadata":{"trusted":true},"cell_type":"code","source":"!rm -rf *.jpg","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}