This project performs image recognition using OpenCV and Google Cloud Vision API with input from webcam. OpenCV tracks faces and monitors for smiles, when a smile is detected a picture is saved locally on the computer, sent the image to Google Cloud Storage bucket, then Google Cloud Vision API is invoked to analyze that picture, and the results are sent back to console. We need a webcam to provide video input to the program.
With OpenCV only minimal features can be extracted from live video feed, like faces, eyes, smiles. An image is captured when a smile is detected and stored on Google Cloud Storage Bucket. The stored image is then analyzed to get meaningful information about what is there in the image. We call them labels and is performed by Google Cloud Vision API.
This project has been implemented on Intel NUC running Corei5 processor, Ubuntu 16.04, OpenCV2 and Python2.