Capturing children food exposure using wearable cameras and deep learning

HIGHLIGHTS

SUMMARY

Since the amount of footage captured is typically large, and only a small percentage corresponds to images with content related to food, the authors employ machine_learning to identify images (i.e., video frames) related to food and discard any other footage. The authors also employed machine_learning to classify food exposure images into images that contain food items being consumed by the child wearing the camera or others, images that contain food advertisements, and images that contain food outlets. 5- A MobileNet V2 machine_learning model to classify the food exposure images into subsequent classes, namely . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or E-mail:

If you don't have an account, you can create one here.