Identifying Object States in Cooking-Related Images
This work addresses a new problem in computer vision for robotics, specifically in cooking scenarios, but it is incremental as it builds on existing deep learning methods.
The paper tackles the problem of identifying object states in cooking-related images, a novel task for robotic task planning, by creating a dataset of eleven object states and proposing a ResNet-based model that achieves significant improvement through object-specific fine-tuning.
Understanding object states is as important as object recognition for robotic task planning and manipulation. To our knowledge, this paper explicitly introduces and addresses the state identification problem in cooking related images for the first time. In this paper, objects and ingredients in cooking videos are explored and the most frequent objects are analyzed. Eleven states from the most frequent cooking objects are examined and a dataset of images containing those objects and their states is created. As a solution to the state identification problem, a Resnet based deep model is proposed. The model is initialized with Imagenet weights and trained on the dataset of eleven classes. The trained state identification model is evaluated on a subset of the Imagenet dataset and state labels are provided using a combination of the model with manual checking. Moreover, an individual model is fine-tuned for each object in the dataset using the weights from the initially trained model and object-specific images, where significant improvement is demonstrated.