Smart Oven Computer Vision System for Real-Time Doneness Control

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Predefined cooking modes in cooking appliances often fail to provide optimal results due to variations in food size, shape, and initial temperature, limiting user customization and flexibility.

Innovation Solution

A smart oven system utilizing computer vision and deep learning, with a cavity-mounted camera and sensors, analyzes food images and sensor data to determine a doneness score, adjusting cooking cycles based on user inputs and desired doneness levels, allowing for real-time automated cooking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If predefined cooking modes are used, then ease of operation is improved, but adaptability deteriorates

Engineering Contradiction:

Improveease of operationVSAvoidadaptability

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The cooking cycle transitions from static predefined parameters to dynamic real-time adjustment based on computer vision monitoring. The system continuously observes food appearance changes and adjusts cooking parameters dynamically to achieve optimal doneness while maintaining ease of operation.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements feedback control by using a camera to monitor food appearance during cooking and adjusting the cooking cycle based on observed doneness. This closed-loop feedback enables the system to adapt to variations in food items while keeping the user interface simple.

Inventive Principle:

Principle #23Feedback

2Device complexity

If predefined cooking cycles are used, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:

Improvedevice complexityVSAvoidmeasurement precision

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system replaces traditional mechanical timers and temperature sensors with computer vision-based doneness detection. The camera captures visual information about food appearance changes, providing more precise measurement of cooking progress without significantly increasing device complexity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If real-time monitoring is implemented, then adaptability is improved, but device complexity increases

Engineering Contradiction:

ImproveadaptabilityVSAvoiddevice complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system uses a camera as an intermediary device to monitor food appearance changes during cooking. This non-intrusive sensor provides real-time feedback on doneness without requiring complex internal sensors or direct contact with the food, thereby improving adaptability while limiting complexity increase.

Inventive Principle:

Principle #24Intermediary (Mediator)

4Adaptability or versatility

If user customization options are increased, then adaptability is improved, but ease of operation deteriorates

Engineering Contradiction:

ImproveadaptabilityVSAvoidease of operation

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system performs self-monitoring of food doneness using computer vision, eliminating the need for users to manually track cooking progress or make continuous adjustments. The appliance autonomously adapts the cooking cycle based on observed appearance changes, providing adaptability without increasing operational complexity for the user.

Inventive Principle:

Principle #25Self-service

Data Source

PatentEP4119851A1Real-time automated cooking cycles using computer vision and deep learning

Publication Date: 2023.01.18 BEKO EUROPE MANAGEMENT SRL

Figure 1
Figure 2
Figure 3

AI summary

A food class (304) of a food item is recognized. A target doneness score (310) is defined for the food item based on the food class (304) and a desired doneness level (306). A recurrent model (302) is utilized to determine a current doneness score (314) of the food item according to sensor data captured of the food item. The current doneness score (314) and the target doneness score (310) are utilized to control a heating system (122) to cook the food item.