Skip to content
Detection of restorations and treatments on dental x-rays in Tensorflow, using Faster-RCNN
Branch: master
Clone or download
Latest commit c9248fa Sep 28, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
models +finetuning 101 Aug 27, 2019
public/images +fixing inference Apr 23, 2019
scripts +better merging May 20, 2019
tooth_number_classification updating readme Apr 23, 2019
.gitignore +better merging May 20, 2019
LICENSE +scripts May 2, 2019 +fixing inference Apr 23, 2019 +inference script update Jun 11, 2019 +refacto Jun 30, 2019 +saving inference images Sep 27, 2019
requirements.txt +refactoring inference script Apr 23, 2019

Teeth detector

Image 1 Image 2 Image 3

Dataset is private for the moment, but was made with a stomatologist surgeon, using VoTT for labeling. The export was made under the Tensorflow Pascal VOC format

The project is divided into two tasks:

  1. Detect tooth restoration, endodotic treatment and implants (models/transfer)
  2. Detect teeth and identify their ISO Dental Notation (models/index)


pip install -r requirements.txt

# Tensorflow Object Detection API
git clone

git clone
cd cocoapi/PythonAPI
cp -r pycocotools <path_to_tensorflow>/models/research/

# From tensorflow/models/research/
export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim


python <path_to_tensorflow>/models/research/object_detection/ \
    --pipeline_config_path=<path_to_tooth-detection>/tooth-detection/models/transfer/faster_rcnn_resnet50_coco.config \
    --model_dir=<path_to_tooth-detection>/tooth-detection/models/transfer/new_version \
    --num_train_steps=100000 \


python \
    --PATH_TO_FROZEN_GRAPH=<path_to_tooth-detection>/<path_to_frozen_graph>/frozen_inference_graph.pb \
    --PATH_TO_TEST_IMAGES_DIR=<path_to_tooth-detection>/data/iran_index/JPEGImages \
You can’t perform that action at this time.