awrd2019 / Playing-Cards-Computer-Vision

I train a model using TensorFlow to detect the suit and number of a playing card. I created my own dataset by taking pictures of each card, then performing data augmentation using rotate, zoom, brighten, and shear functions.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Playing-Cards-Computer-Vision

I trained a model using TensorFlow to detect the suit and number of playing cards given their image. I created my own dataset by taking pictures of each card, then performed pre-processing and data augmentation using rotate, zoom, brighten, and shear functions. My final dataset consisted of 39000, 180x180 grayscale images. I then trained a convolutional neural network to classify the card images.

Please check out my medium article on this project- https://medium.com/@awrd2019/image-classification-for-playing-cards-26d660f3149e.

About

I train a model using TensorFlow to detect the suit and number of a playing card. I created my own dataset by taking pictures of each card, then performing data augmentation using rotate, zoom, brighten, and shear functions.


Languages

Language:Jupyter Notebook 100.0%