VGG Fine-tuning for Cooking State Recognition
This addresses a specific task for domestic robots but is incremental, applying an existing method to a new dataset.
The paper tackled the problem of recognizing cooking states of food ingredients for domestic robots by fine-tuning the VGG architecture, achieving an accuracy of 76.6% on the test set.
An important task that domestic robots need to achieve is the recognition of states of food ingredients so they can continue their cooking actions. This project focuses on a fine-tuning algorithm for the VGG (Visual Geometry Group) architecture of deep convolutional neural networks (CNN) for object recognition. The algorithm aims to identify eleven different ingredient cooking states for an image dataset. The original VGG model was adjusted and trained to properly classify the food states. The model was initialized with Imagenet weights. Different experiments were carried out in order to find the model parameters that provided the best performance. The accuracy achieved for the validation set was 76.7% and for the test set 76.6% after changing several parameters of the VGG model.