Using Mask-RCNN to solve Where's Waldo. Refer this for detailed description of the problem and the solution.
Some results
Training and validation data sets used for this project are put in data folder. For custom datasets, use via-via tool to annotate.
You can either set your configurations in the waldo_config.py file or use the default. Then use the following commands for training and predicting.
This will download the Mask-RCNN model trained on coco dataset to the MODEL_DIR folder and trains a model with the data in the DATA_DIR folder.
python train.py
Shows a popup with the waldo detected in the image.
python predict.py [MODEL PATH] [PATH TO IMAGE]
# for example
python predict.py models/logs/waldo20180612T1628/mask_rcnn_waldo_0030.h5 data/val/5.jpg