Automatic image captioning is the process of generating a descriptive text description for an image. Image captioning is one of the few applications of deep neural networks where we work with image and text data simultaneously. This captioning model can be trained using standard backpropagation techniques such as Stochastic Gradient Descent (SGD). I trained this model on the MS-COCO dataset with real-world images of humans, animals, vehicles, etc., in various situations and surroundings.
Read more →
While eating jellybeans isn’t as hazardous in the real world as in the Harry Potter universe, it can still be unexpectedly interesting: you think you have a few raspberry flavored beans, but how do you know one of them isn’t actually cinnamon? In an effort to combat this anxiety-inducing problem, we collected several sets of image data. I’ll talk about how we applied computer vision techniques to isolate the beans and extract useful features from the images (as well as the associated challenges).
Read more →
