We received advice from instructors that we need to test how well the Image Recognition API performs on recognizing our ingredients. We agree that it is important to consider this because this part is very important for the entire pipeline to work. We are currently working on the testing part, and if the performance is not ideal, we will consider train the pre-trained model with our dataset or implement a CNN model that focuses on the dataset we are using to manage the risks of this part.
Another suggestion we got is that we should also consider sending the text version of the recipe to the user through email so that the users can easily check the recipe if they want to. We bought wifi adapters and received them yesterday, and we are working on the email functionality now. We are still trying to figure out how to get the wifi adapter to work on Jetson nano.
The next step of our project is to connect every part together. We will research the pipeline and start implementing the connections between sub-systems in the coming week and also continue explorations on our own parts individually. There are no changes to our planned schedule.