{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n for filename in filenames:\n print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-03-28T17:46:42.280832Z","iopub.execute_input":"2023-03-28T17:46:42.281252Z","iopub.status.idle":"2023-03-28T17:47:25.29328Z","shell.execute_reply.started":"2023-03-28T17:46:42.281214Z","shell.execute_reply":"2023-03-28T17:47:25.291858Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"
\n\n#
Benetech | Simple OCR Network
\n\n\n### Table of Contents\n\nThe notebook will be divided into separate sections to provide an organized walk-through. The sections are:\n\n
\n
    \n
  1. Import Libraries
    2. \n
  2. Load Image
    3. \n
  3. Load Annotation
    4. \n
  4. Plot all annotation information from image
    5. \n
  5. Object Character Recognition
    6. \n
  6. Predict Bounding Boxes
    7. \n
\n
","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:56:25.501591Z","iopub.execute_input":"2023-03-28T17:56:25.502026Z","iopub.status.idle":"2023-03-28T17:56:25.512526Z","shell.execute_reply.started":"2023-03-28T17:56:25.501984Z","shell.execute_reply":"2023-03-28T17:56:25.510822Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 1 | Import Libraries [↑](#top) \n***","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:48:09.608947Z","iopub.execute_input":"2023-03-28T17:48:09.609617Z","iopub.status.idle":"2023-03-28T17:48:09.616236Z","shell.execute_reply.started":"2023-03-28T17:48:09.609576Z","shell.execute_reply":"2023-03-28T17:48:09.614791Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%config Completer.use_jedi = False","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:10:05.457814Z","iopub.execute_input":"2023-03-28T17:10:05.45825Z","iopub.status.idle":"2023-03-28T17:10:05.467007Z","shell.execute_reply.started":"2023-03-28T17:10:05.45821Z","shell.execute_reply":"2023-03-28T17:10:05.465855Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install -Uqqq pycocotools","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:10:58.002247Z","iopub.execute_input":"2023-03-28T17:10:58.003697Z","iopub.status.idle":"2023-03-28T17:11:09.183874Z","shell.execute_reply.started":"2023-03-28T17:10:58.003634Z","shell.execute_reply":"2023-03-28T17:11:09.182313Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from IPython.display import Image\nImage(filename='/kaggle/input/benetech-making-graphs-accessible/train/images/0000ae6cbdb1.jpg') ","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:12:26.508083Z","iopub.execute_input":"2023-03-28T17:12:26.509511Z","iopub.status.idle":"2023-03-28T17:12:26.523891Z","shell.execute_reply.started":"2023-03-28T17:12:26.509429Z","shell.execute_reply":"2023-03-28T17:12:26.522945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from IPython.display import Image\nImage(filename='/kaggle/input/benetech-making-graphs-accessible/train/images/183bc1684dc1.jpg') ","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:58:38.257864Z","iopub.execute_input":"2023-03-28T17:58:38.258697Z","iopub.status.idle":"2023-03-28T17:58:38.270606Z","shell.execute_reply.started":"2023-03-28T17:58:38.258644Z","shell.execute_reply":"2023-03-28T17:58:38.269215Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Image(filename='/kaggle/input/benetech-making-graphs-accessible/train/images/000631f33080.jpg') ","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:13:22.149241Z","iopub.execute_input":"2023-03-28T17:13:22.149924Z","iopub.status.idle":"2023-03-28T17:13:22.162946Z","shell.execute_reply.started":"2023-03-28T17:13:22.149882Z","shell.execute_reply":"2023-03-28T17:13:22.161504Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from IPython.display import Image\nImage(filename='/kaggle/input/benetech-making-graphs-accessible/train/images/8b119ce2ddc7.jpg') ","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:16:42.377915Z","iopub.execute_input":"2023-03-28T18:16:42.37876Z","iopub.status.idle":"2023-03-28T18:16:42.389359Z","shell.execute_reply.started":"2023-03-28T18:16:42.37871Z","shell.execute_reply":"2023-03-28T18:16:42.388308Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"graph_dir = '/kaggle/input/benetech-making-graphs-accessible/train/annotations'\nfilenames = os.listdir(graph_dir)\nprint(\"Number of articles retrieved from biorxiv:\", len(filenames))","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:14:36.272796Z","iopub.execute_input":"2023-03-28T17:14:36.273219Z","iopub.status.idle":"2023-03-28T17:14:36.305739Z","shell.execute_reply.started":"2023-03-28T17:14:36.27318Z","shell.execute_reply":"2023-03-28T17:14:36.304663Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"annotation = '/kaggle/input/benetech-making-graphs-accessible/train/annotations'\nannot_df = pd.DataFrame()\nfor root, dirs, files in os.walk(annotation):\n for name in files: \n f = os.path.join(root, name)\n with open(f) as f:\n d = json.load(f)\n tt = json_normalize(d, max_level = 1)\n tt['file']= name.split('.')[0]\n annot_df = pd.concat([annot_df, tt], axis=0) ","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:15:54.630927Z","iopub.execute_input":"2023-03-28T17:15:54.631348Z","iopub.status.idle":"2023-03-28T17:32:57.20111Z","shell.execute_reply.started":"2023-03-28T17:15:54.631309Z","shell.execute_reply":"2023-03-28T17:32:57.199975Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pd.set_option('display.max_columns', None) ","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:33:29.385525Z","iopub.execute_input":"2023-03-28T17:33:29.385936Z","iopub.status.idle":"2023-03-28T17:33:29.391294Z","shell.execute_reply.started":"2023-03-28T17:33:29.385901Z","shell.execute_reply":"2023-03-28T17:33:29.390112Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"annot_df.head(5)","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:33:42.958837Z","iopub.execute_input":"2023-03-28T17:33:42.959268Z","iopub.status.idle":"2023-03-28T17:33:43.125614Z","shell.execute_reply.started":"2023-03-28T17:33:42.959232Z","shell.execute_reply":"2023-03-28T17:33:43.124248Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"JSON_COLUMNS = ['data-series']\nfor column in JSON_COLUMNS:\n column_as_df = json_normalize(annot_df[column])\n column_as_df.columns = [f\"{column}.{subcolumn}\" for subcolumn in column_as_df.columns]\n df = annot_df.drop(column, axis=1).merge(column_as_df, right_index=True, left_index=True)","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:35:33.77187Z","iopub.execute_input":"2023-03-28T17:35:33.772278Z","iopub.status.idle":"2023-03-28T17:35:38.191082Z","shell.execute_reply.started":"2023-03-28T17:35:33.772243Z","shell.execute_reply":"2023-03-28T17:35:38.189959Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:36:04.547542Z","iopub.execute_input":"2023-03-28T17:36:04.548638Z","iopub.status.idle":"2023-03-28T17:36:04.792327Z","shell.execute_reply.started":"2023-03-28T17:36:04.548591Z","shell.execute_reply":"2023-03-28T17:36:04.791429Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv('../input/benetech-making-graphs-accessible/sample_submission.csv')\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:49:42.591464Z","iopub.execute_input":"2023-03-28T17:49:42.591878Z","iopub.status.idle":"2023-03-28T17:49:42.610334Z","shell.execute_reply.started":"2023-03-28T17:49:42.591841Z","shell.execute_reply":"2023-03-28T17:49:42.609034Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## Based on: https://www.kaggle.com/eigrad/convert-rle-to-bounding-box-x0-y0-x1-y1\ndef rle2mask(rle, img_w, img_h):\n \n ## transforming the string into an array of shape (2, N)\n array = np.fromiter(rle.split(), dtype = np.uint)\n array = array.reshape((-1,2)).T\n array[0] = array[0] - 1\n \n ## decompressing the rle encoding (ie, turning [3, 1, 10, 2] into [3, 4, 10, 11, 12])\n # for faster mask construction\n starts, lenghts = array\n mask_decompressed = np.concatenate([np.arange(s, s + l, dtype = np.uint) for s, l in zip(starts, lenghts)])\n\n ## Building the binary mask\n msk_img = np.zeros(img_w * img_h, dtype = np.uint8)\n msk_img[mask_decompressed] = 1\n msk_img = msk_img.reshape((img_h, img_w))\n msk_img = np.asfortranarray(msk_img) ## This is important so pycocotools can handle this object\n \n return msk_img","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:51:52.79121Z","iopub.execute_input":"2023-03-28T17:51:52.792196Z","iopub.status.idle":"2023-03-28T17:51:52.805024Z","shell.execute_reply.started":"2023-03-28T17:51:52.792149Z","shell.execute_reply":"2023-03-28T17:51:52.803722Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Code by Jensen https://www.kaggle.com/code/a03102030/simple-cnn-for-top-10000-data\n#https://www.kaggle.com/code/mpwolke/iwildcam-2022-cnn\n\nimg=[]\nfilename=df.name[:10000]#original is id\nlabel=df.source[:10000]\nfor file in filename:\n image=cv2.imread(\"../input/benetech-making-graphs-accessible/train/images/\"+file+'.jpg')\n res=cv2.resize(image,(32,32))\n img.append(res)\nimg=np.array(img)","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:52:02.17718Z","iopub.execute_input":"2023-03-28T17:52:02.178128Z","iopub.status.idle":"2023-03-28T17:52:02.2796Z","shell.execute_reply.started":"2023-03-28T17:52:02.178083Z","shell.execute_reply":"2023-03-28T17:52:02.277825Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Loading SeshuRajuP data","metadata":{}},{"cell_type":"code","source":"import json \nimport os\nimport pandas as pd \nfrom pandas.io.json import json_normalize #package for flattening json in pandas df","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:11:14.83129Z","iopub.execute_input":"2023-03-28T17:11:14.831735Z","iopub.status.idle":"2023-03-28T17:11:14.837207Z","shell.execute_reply.started":"2023-03-28T17:11:14.831689Z","shell.execute_reply":"2023-03-28T17:11:14.836084Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv('../input/benetech-making-graphs-accessible-csv/train.csv')\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2023-03-28T17:11:32.427078Z","iopub.execute_input":"2023-03-28T17:11:32.427525Z","iopub.status.idle":"2023-03-28T17:11:32.46124Z","shell.execute_reply.started":"2023-03-28T17:11:32.427482Z","shell.execute_reply":"2023-03-28T17:11:32.459358Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import requests\nfrom bs4 import BeautifulSoup\nimport lxml\nimport urllib\nimport sys\nfrom PIL import Image\nimport cv2\nimport csv\nimport multiprocessing\nimport matplotlib.pyplot as plt\nimport math\nimport time\nimport datetime\nimport glob","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:18:52.302468Z","iopub.execute_input":"2023-03-28T18:18:52.302895Z","iopub.status.idle":"2023-03-28T18:18:52.487143Z","shell.execute_reply.started":"2023-03-28T18:18:52.302857Z","shell.execute_reply":"2023-03-28T18:18:52.485954Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Code by Ventakumar R https://www.kaggle.com/venkatkumar001/hfp-2-eda-tensorflow/notebook\n\nimport json, codecs\n\nwith codecs.open(\"../input/benetech-making-graphs-accessible/train/annotations/002bcf154c3d.json\", 'r',\n encoding='utf-8', errors='ignore') as f:\n train_meta = json.load(f)\n \n#with codecs.open(\"../input/.json\", 'r',\n # encoding='utf-8', errors='ignore') as f:\n # test_meta = json.load(f)","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:19:07.123631Z","iopub.execute_input":"2023-03-28T18:19:07.124577Z","iopub.status.idle":"2023-03-28T18:19:07.131219Z","shell.execute_reply.started":"2023-03-28T18:19:07.124534Z","shell.execute_reply":"2023-03-28T18:19:07.129803Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import cv2 as cv\n\nimg = cv.imread('../input/benetech-making-graphs-accessible/train/images/002b6b51c9f1.jpg')\nprint( img.shape )","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:19:27.938313Z","iopub.execute_input":"2023-03-28T18:19:27.938741Z","iopub.status.idle":"2023-03-28T18:19:27.96857Z","shell.execute_reply.started":"2023-03-28T18:19:27.938704Z","shell.execute_reply":"2023-03-28T18:19:27.967273Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"DATA_PATH = \"../input/benetech-making-graphs-accessible/\"","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:19:43.905962Z","iopub.execute_input":"2023-03-28T18:19:43.907227Z","iopub.status.idle":"2023-03-28T18:19:43.912363Z","shell.execute_reply.started":"2023-03-28T18:19:43.90718Z","shell.execute_reply":"2023-03-28T18:19:43.911076Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"image_paths = sorted(glob.glob(os.path.join(DATA_PATH, 'train/images/*.jpg')))","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:19:58.567713Z","iopub.execute_input":"2023-03-28T18:19:58.568138Z","iopub.status.idle":"2023-03-28T18:19:58.788198Z","shell.execute_reply.started":"2023-03-28T18:19:58.568089Z","shell.execute_reply":"2023-03-28T18:19:58.786967Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"Number of images: {len(image_paths)}\")","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:20:10.934111Z","iopub.execute_input":"2023-03-28T18:20:10.93453Z","iopub.status.idle":"2023-03-28T18:20:10.940745Z","shell.execute_reply.started":"2023-03-28T18:20:10.934492Z","shell.execute_reply":"2023-03-28T18:20:10.939189Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"paths = sorted(glob.glob(\"../input/benetech-making-graphs-accessible/train/images/*\"))","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:20:36.133915Z","iopub.execute_input":"2023-03-28T18:20:36.13467Z","iopub.status.idle":"2023-03-28T18:20:36.352272Z","shell.execute_reply.started":"2023-03-28T18:20:36.134629Z","shell.execute_reply":"2023-03-28T18:20:36.351332Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf \nimport numpy as np\nimport os\nimport matplotlib.pyplot as plt \ntf.__version__","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:20:47.294701Z","iopub.execute_input":"2023-03-28T18:20:47.295745Z","iopub.status.idle":"2023-03-28T18:20:56.218628Z","shell.execute_reply.started":"2023-03-28T18:20:47.295697Z","shell.execute_reply":"2023-03-28T18:20:56.217124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Name0=os.listdir('../input/benetech-making-graphs-accessible')\nName=sorted(Name0)\nn=len(Name)\nN=list(range(n))\nnormal_mapping=dict(zip(Name,N)) \nreverse_mapping=dict(zip(N,Name)) ","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:21:05.416539Z","iopub.execute_input":"2023-03-28T18:21:05.417824Z","iopub.status.idle":"2023-03-28T18:21:05.424765Z","shell.execute_reply.started":"2023-03-28T18:21:05.417769Z","shell.execute_reply":"2023-03-28T18:21:05.423469Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/ImageDataGenerator\n\nimg_generator = tf.keras.preprocessing.image.ImageDataGenerator(\n #rotation_range=90,\n brightness_range=(0.5,1), \n #shear_range=0.2, \n #zoom_range=0.2,\n channel_shift_range=0.2,\n horizontal_flip=False,\n vertical_flip=False,\n rescale=1./255,\n validation_split=0.3)","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:21:23.134519Z","iopub.execute_input":"2023-03-28T18:21:23.135357Z","iopub.status.idle":"2023-03-28T18:21:23.142255Z","shell.execute_reply.started":"2023-03-28T18:21:23.135312Z","shell.execute_reply":"2023-03-28T18:21:23.140764Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Stpete Ishii https://www.kaggle.com/code/stpeteishii/transfer-learning-for-manga-facial-expressions\n\nroot_dir = '../input/benetech-making-graphs-accessible'\n\nimg_generator_flow_train = img_generator.flow_from_directory(\n directory=root_dir,\n target_size=(224, 224),\n batch_size=32,\n shuffle=True,\n subset=\"training\")\n\nimg_generator_flow_valid = img_generator.flow_from_directory(\n directory=root_dir,\n target_size=(224, 224),\n batch_size=32,\n shuffle=True,\n subset=\"validation\")","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:21:41.902559Z","iopub.execute_input":"2023-03-28T18:21:41.902962Z","iopub.status.idle":"2023-03-28T18:22:23.327443Z","shell.execute_reply.started":"2023-03-28T18:21:41.902927Z","shell.execute_reply":"2023-03-28T18:22:23.326323Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Stpete Ishii https://www.kaggle.com/code/stpeteishii/transfer-learning-for-manga-facial-expressions\n\nimgs, labels = next(iter(img_generator_flow_train))\nfor img, label in zip(imgs, labels):\n value=np.argmax(label)\n plt.imshow(img)\n plt.title(reverse_mapping[value])\n plt.show()","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:22:41.256797Z","iopub.execute_input":"2023-03-28T18:22:41.257641Z","iopub.status.idle":"2023-03-28T18:22:47.780894Z","shell.execute_reply.started":"2023-03-28T18:22:41.257593Z","shell.execute_reply":"2023-03-28T18:22:47.780029Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Ihelon https://www.kaggle.com/code/ihelon/lego-minifigure-faces-overview\n\nn_cols = 4\nn_rows = int(math.ceil(len(paths) / n_cols))\n\nfor r in range(n_rows):\n plt.figure(figsize=(16, 5))\n for c in range(n_cols):\n plt.subplot(1, n_cols, c + 1)\n current = r * n_cols + c\n if current >= len(paths):\n break\n image = cv2.imread(paths[current])\n image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n plt.imshow(image)\n plt.xticks([])\n plt.yticks([])\n plt.show()","metadata":{"execution":{"iopub.status.busy":"2023-03-28T18:23:37.948574Z","iopub.execute_input":"2023-03-28T18:23:37.949347Z"},"trusted":true},"execution_count":null,"outputs":[]}]}