Refrigerator Image Recognition for Automatic Food Item Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current refrigerator management systems face challenges in accurately tracking the storage and expiration of food items due to user convenience limitations, particularly when items are loaded or unloaded without proper input, leading to discrepancies between stored information and actual contents.

Innovation Solution

A method utilizing image recognition technology within a refrigerator, which includes a voice input unit, loading/unloading recognition unit, object region detection, characteristic extraction, and storage item management to automatically recognize, register, and update information on food items through video analysis, eliminating the need for manual input and enhancing accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual input methods (keypad/touch pad) are used to register food items, then user can provide storage information, but user convenience deteriorates and input errors increase when users do not properly input items

Engineering Contradiction:
Improveaccuracy of storage informationVSAvoiduser convenience
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The refrigerator system performs self-service by automatically detecting and registering food items through image recognition technology. The camera captures images of food items placed in the refrigerator, and the control unit automatically processes these images to identify and register the items without requiring manual user input through keypad or touch pad interfaces.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual input system (keypad/touch pad) with an optical recognition system. Instead of requiring users to physically type or touch inputs, the system uses a camera to capture images and an image recognition algorithm to automatically identify and register food items, substituting mechanical interaction with optical and computational processes.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Extent of automation

If RFID tags and wireless communication are used to detect food items, then automatic detection capability is improved, but device complexity increases and detection accuracy deteriorates in metallic environments

Engineering Contradiction:
Improveautomatic detection capabilityVSAvoidsystem complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

Instead of using RFID tags attached to each food item, the patent creates a visual copy or image of the food item using a camera. The control unit then processes these images to identify and register the items. This approach eliminates the need for physical RFID tags on each item while achieving automatic detection through image-based copying and recognition.

Inventive Principle:
Principle #26Copying

3Extent of automation

If image recognition technology is implemented, then automatic recognition and registration of food items is achieved, but device complexity increases due to additional components

Engineering Contradiction:
Improveautomatic recognition capabilityVSAvoidnumber of components
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The control unit serves multiple functions: it controls the camera operation, processes the captured images through image recognition algorithms, identifies food items, registers them in the database, and manages storage information. By making the control unit multi-functional, the patent avoids adding separate dedicated components for each function, thereby reducing overall device complexity while achieving automatic recognition.

Inventive Principle:
Principle #6Universality (Multi-functionality)

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 enables accurate management of food items by automatically recognizing and updating information on loading/unloading, increasing user convenience and reducing errors, allowing for efficient tracking and notification of stored goods, including expiration dates.

Implementation Method 1

an imaging unit obtaining images on goods loading/unloading

Methodology Applied
Scientific EffectOptical detection: Light

Implementation Method 2

a loading/unloading recognition unit detecting the optical flow through vision recognition on the goods loading/unloading video generated by the imaging unit

Methodology Applied
Scientific EffectOptical flow: Light

Data Source

PatentEP2985553B1Method for managing storage product in refrigerator using image recognition, and refrigerator for same
Publication Date: 2020.08.26 LG ELECTRONICS INC
  • EP2985553B1 patent drawingFigure 1~2
  • EP2985553B1 patent drawingFigure 3
  • EP2985553B1 patent drawingFigure 4

AI summary

A refrigerator is provided. The refrigerator includes an imaging unit generating a goods loading/unloading video through video recording of storage goods loaded into or unloaded from the refrigerator; a data storage unit storing the goods loading/unloading video, goods information that may be stored in the refrigerator, and storage items information; a control unit recognizing loading/unloading of goods based on an optical flow detected through vision recognition from the goods loading/unloading video, and updating the storage items information in the refrigerator based on recognition information generated through vision recognition on loading/unloading of the goods and the goods information stored in the data storage unit; and a display unit displaying a managed state of storage items for a user based on the updated storage items information.