Cooking State Recognition from Images Using Inception Architecture

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.

arXiv comment6 pages, 8 figures, 4 tables

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Identifying Object States in Cooking-Related Images
• Functional Object-Oriented Network for Manipulation Learning

Cited by in corpus (4)

• Rethinking Cooking State Recognition with Vision Transformers
• Tuned Inception V3 for Recognizing States of Cooking Ingredients
• VGG Fine-tuning for Cooking State Recognition
• Classifying States of Cooking Objects Using Convolutional Neural Network