![]() ![]() Detection the card’s edition (if it has one) + detection and reading name to reduce matches.Detect the card in the frame to have a tight region of interest (front side of the card and not rotated). ![]() The cards are labeled with their name (ex: '2s' for '2 of spades', 'Kh' for King for hearts) and with the bounding boxes delimiting their printed. The notebook creatingplayingcardsdataset.ipynb is a guide through the creation of a dataset of playing cards. Here’s what I though to do in the first place: Generating a dataset of playing cards to train a neural net. So I’d like to know where to start with ? My input will be from a camera with poor to high quality, and the common case should be 1 card at a time (so I could automate the card sorting with a raspberry). Also its quite slow (OpenCV + Project in release mode recognizes the card in 30~50ms), given that MTG has more than 30k cards (some are identical but with different editions), it may take too much time to process all the database. Plans: Adding NPP 4.1 functions and GPU video decoding. ![]() Next we need to add the classifiers in generatetfrecord.py. From the \objectdetection folder, issue the following command in the Anaconda command prompt: This will create trainlabels.csv and testlabels.csv files. I watched many videos that does object recognition, I followed a tutorial that sets up an object detection with ORB/SIFT, its decently working but I don’t know how to make some match score. Started learning code and papers for future people detection GTC demo. xml files to csvs containing all the data for the train and test images. I’m a new commer in OpenCV’s world and my project would be to detect some Magic the Gathering (MTG) cards in order to sort and count them. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |