Cook Program Determination for Personalized Food Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated appliances struggle to recognize personalized and custom food items using generic computer-vision models, limiting their ability to determine appropriate cook programs for unique meals.
Innovation Solution
A system and method that includes a food identification module capable of determining new food classes through image recognition, using a combination of base and auxiliary neural network sub-modules for personalized cook program generation, allowing for the automatic recognition and cooking of custom foods by clustering image features and updating the food identification module with user-provided cooking instructions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a generic computer-vision model is used for food recognition, then the system can recognize common food items, but it cannot recognize personalized and custom food items
Solution Approach 1:
The food identification module is segmented into multiple specialized sub-modules, each trained to recognize specific food categories or personalized food items. This segmentation allows the system to handle both common and personalized foods with dedicated recognition expertise.
Solution Approach 2:
The food identification module is designed as a universal system that can recognize both generic food items and personalized custom foods. The module adapts its recognition capabilities based on the input, functioning as both a general-purpose and specialized recognizer.
2Adaptability or versatility
If the food identification module is updated with user-provided cooking instructions, then personalized cook programs can be generated, but the system complexity increases
Solution Approach 1:
User cooking instructions are collected and stored in advance during setup or initial use. This preliminary action allows the system to have personalized cooking data ready before actual cooking operations, reducing real-time processing complexity.
Solution Approach 2:
The system automatically updates its food identification capabilities using user-provided instructions without requiring manual reconfiguration. The module self-adapts by learning from user inputs, reducing the operational complexity for users.
3Adaptability or versatility
If image features are clustered to determine new food classes, then new foods can be automatically recognized, but the processing time increases
Solution Approach 1:
The system performs partial clustering operations by focusing on key distinguishing features of food images rather than analyzing all possible attributes. This selective approach enables new food class recognition while reducing overall processing time.
Solution Approach 2:
Image features are pre-processed and organized into clusters during offline training or setup phases. This preliminary clustering prepares the data structure in advance, allowing faster recognition during actual cooking operations.
Data Source
AI summary
In variants, the method can include: sampling cavity measurements of the cook cavity; determining an image representation using the cavity measurements; determining a food class based on the image representation; optionally comparing the image representation to prior image representations; optionally determining a new food class based on the image representation; optionally updating a food identification module with the new food class; and optionally determining a cook program associated with the new food class.