Problem Description

• People are becoming more health conscious and interested in tracking their calorie intake.
• An image classifier that can provide nutritional information based on the picture of the food taken could be a unique selling point for calorie-tracking apps.
• We plan to scrape data using the FlickrAPI package to create an image classifier for food items and use it to output nutritional values of the respective food item.

Analytics Plan

Data Scraping

• Use getPhotoSearch method from the FlickrAPI package to find the most “interesting” pics under a certain tag and retrieve all metadata about the photos.
• Use download.file method to download the photos scraped URLs.

Data Processing

• Resize the images to a fixed size to ensure that images are all the same size, which is required by many neural network architectures.
• Normalize the pixel values of the images to have zero mean and unit variance to help ensure that the data is centered around zero, which is often required by many neural network architectures.
• Convert images to grayscale or another color space to help reduce the computational cost of the model and improve its robustness to lighting conditions.

Model Building

• Use Keras and Tensorflow to build the convoluted neural network (CNN).
• Define the model architecture which would involve specifying the layers of the neural network, including the input layer, convolution layers, pooling layers, and dense layers. The exact architecture is yet to be decided.
• Compile the model by specifying the optimizer, loss function, and metrics to be used during training. The level of metrics to be decided.
• Use the fit function to train the model.

Evaluation Plan

• Initial split data into 80% for training & 20% for test.
• Use 20% to evaluate the performance of the model using metrics such as accuracy, loss, precision, recall for each class of classification.
• Identify the classes that are not performing optimally and either perform Hyper parameter tuning by adjusting factors such as learning rate, batch size, number of epochs, etc. or increasing the training set for the particular class that are not performing well.

Deploying the model

• Build a simple user interface that identifies the food item in the picture and displays nutritional info.
• Food item to calorific content mappings to be scraped from US Dept of Agriculture Website.