![]() Fortunately, the letters we need to detect are consistent. Getting enough screenshots for good training was going to take some time and there was a challenge in getting enough of the rare letters, like Q or Z, to effectively train the model. The first step was to collect enough images to be able to train a model to detect letters. This approach allowed me to capture images from the show to use for training and grab images to send for inference to detect letters. ![]() This project uses a USB HDMI capture device connected to a Roku express to capture images from the show while it is being aired. Computer vision to the rescue! After a few weeks of training and coding, I am excited to share a project that does exactly that. ![]() The correct ones are visible of course, but there is no way to see the guesses that were incorrect. This post was contributed to the Roboflow blog by Warren Wiens, a marketing strategist with 20+ years experience in technology who is learning about AI in their spare time.Īs a regular fan of Wheel of Fortune, I often find myself wishing that I could see all the letters that have been guessed for a puzzle. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |