Cooking State Recognition from Images Using Inception Architecture

TL;DR

This paper presents a deep learning method using a modified Inception architecture to accurately recognize cooking states from images, aiding kitchen robots in understanding their environment.

Contribution

It introduces a novel modified Inception-based model specifically designed for cooking state recognition from images.

Findings

The proposed model effectively classifies various cooking states.

The modified architecture outperforms baseline models in accuracy.

Robust analysis shows the model's adaptability to different layers and optimizers.

Abstract

A kitchen robot properly needs to understand the cooking environment to continue any cooking activities. But object's state detection has not been researched well so far as like object detection. In this paper, we propose a deep learning approach to identify different cooking states from images for a kitchen robot. In our research, we investigate particularly the performance of Inception architecture and propose a modified architecture based on Inception model to classify different cooking states. The model is analyzed robustly in terms of different layers, and optimizers. Experimental results on a cooking datasets demonstrate that proposed model can be a potential solution to the cooking state recognition problem.