Optical Food Recognition for Automatic Cooking Cycle Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing cooking devices often rely on external identification methods like RFID tags or barcodes, which can lead to erroneous food identification, especially with mislabeled items, and do not utilize real-time visual recognition of food appearance.

Innovation Solution

A commercial cooking device equipped with digital optical identification means, including a camera and controller, that captures images of food and compares them to stored data to accurately identify food based on physical features, allowing for automatic cooking cycle selection and adjustment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If external identification methods like RFID tags or barcodes are used, then the cooking device can automatically identify food, but erroneous identification occurs especially with mislabeled items

Engineering Contradiction:

Improveautomatic food identificationVSAvoidaccuracy of food identification

Core Design Contradiction:

Extent of automationVSReliability

Solution Approach 1:

The patent replaces external identification systems (RFID tags, barcodes) with an optical recognition system using cameras and image processing algorithms. This substitution eliminates dependency on potentially mislabeled external identifiers and directly analyzes the physical appearance of food items for accurate identification.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates visual copies (images) of the food item and compares them against stored reference images in a database. This copying approach allows for pattern recognition and matching based on actual food appearance rather than relying on external labels that may be incorrect.

Inventive Principle:

Principle #26Copying

2Reliability

If digital optical identification means are added to the cooking device, then food identification accuracy improves, but device complexity increases

Engineering Contradiction:

Improveaccuracy of food identificationVSAvoidcomplexity of identification system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The optical recognition system serves multiple functions: identifying food type, determining food quantity, verifying food placement, and potentially assessing food quality. This multi-functionality justifies the added complexity by providing comprehensive food analysis through a single integrated system.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system performs automatic image capture, processing, and identification without requiring manual intervention. The camera automatically captures food images, the processor analyzes them, and the system independently identifies the food item, reducing the need for complex user interactions.

Inventive Principle:

Principle #25Self-service

3Reliability

If real-time visual recognition is implemented, then misidentification errors are eliminated, but processing time and energy consumption increase

Engineering Contradiction:

Improveaccuracy of food identificationVSAvoidenergy consumption of recognition system

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system captures images at specific moments (when food is placed in the device) rather than continuous monitoring. It processes only the necessary visual features for identification rather than analyzing every pixel in detail, reducing energy consumption while maintaining accuracy.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

Reference images and identification criteria are pre-loaded into the system's database before operation. This preliminary preparation allows for rapid comparison and identification during actual use, minimizing real-time processing requirements and energy consumption.

Inventive Principle:

Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This solution reduces errors in food identification by using real-time visual recognition, ensuring accurate cooking parameters and eliminating misidentification issues associated with external tags or codes, providing a more reliable and user-friendly cooking experience.

Implementation Method 1

picture taking means for taking a picture of the food product to be cooked

Methodology Applied

Scientific EffectLight reflection: Reflection

Data Source

PatentUS10154749B2Cooking device and procedure for cooking food

Publication Date: 2018.12.18 WELBILT DEUTSCHLAND GMBH

AI summary

Disclosed is a cooking device with optical identification means for identifying food to be cooked. A motion detector is provided to activate the optical identification means. The motion detector may also activate a light source for lighting the field of vision of the optical means. Optical identification is controlled by the outer appearance of the food. A controller accesses a physical feature database and compares previously stored picture data to the physical features of the food to be cooked. The controller calculates a matching probability rank between the stored picture data and the food to be cooked. The controller is also programmed to have a learning ability for recognizing a previously unknown food product. Based upon the identification of the food product to be cooked, the cooking device starts the recipe for cooking the food product.