Identifying Object States in Cooking-Related Images

TL;DR

This paper introduces a novel approach to identify object states in cooking images, creating a dataset and employing deep learning models to improve state recognition for robotic applications.

Contribution

It is the first to explicitly address object state identification in cooking images, proposing a ResNet-based model and fine-tuning strategies for improved accuracy.

Findings

The model achieves high accuracy on the dataset.

Fine-tuning significantly improves object-specific state recognition.

The dataset and methodology support future research in robotic manipulation.

Abstract

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.