2019/05/13 by Juan Wilches, Wilches, Juan
Computer Science · Engineering · Medicine · #Advanced Chemical Sensor Technologies #Algorithm #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolutional neural network #Currency Recognition and Detection #Engineering #FOS: Computer and information sciences #Image (mathematics) #Machine learning #Nutritional Studies and Diet #Pattern recognition (psychology) #Set (abstract data type) #State (computer science) #Task (project management) #Test set #cs.CV
paper · pdf · doi:10.48550/arxiv.1905.08606
arxiv created 2019/05/13 · openalex publication_date 2019/05/13 · arxiv updated 2019/05/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.