Fish Tail Cross-Section Imaging for Accurate Quality Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining the quality of tuna requires significant expertise and is challenging due to the irregularities in the cross-section of non-frozen fish, making it difficult for non-experts to assess quality accurately.
Innovation Solution
A fish quality determination system utilizing machine learning to analyze image data of a fish's cross-section, estimate the fish's body region, generate trimming image data by removing non-body regions, and determine quality based on fat ratio and freshness using machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If quality determination is performed by visual inspection of cross section, then expert judgment can be applied, but it requires many years of experience and is difficult for non-experts
Solution Approach 1:
The patent replaces the mechanical/visual inspection system with an image processing and machine learning system. The quality determination is automated through computer-based image analysis that processes cross-section images to identify fat regions and determine quality metrics, eliminating the need for expert visual inspection while maintaining or improving accuracy
Solution Approach 2:
The patent introduces an intermediary image processing system between the fish cross-section and the quality determination. The system captures images of the cross-section, processes them through algorithms that identify fat regions and calculate quality metrics, and outputs automated quality assessments, serving as a mediator that translates physical characteristics into quantifiable quality data
2Reliability
If cross section is taken from non-frozen fish, then freshness is preserved, but the cross section has many irregularities and rough surfaces making determination more difficult
Solution Approach 1:
The patent changes the parameter of fish state from frozen to non-frozen while compensating for the resulting irregularities through image processing. By processing images to identify and measure fat regions despite the rough surfaces and irregularities, the system maintains accurate quality determination while preserving freshness through non-frozen handling
3Area of stationary object
If image data includes vertebra and background regions, then complete fish cross section is captured, but these regions become noise that interferes with quality determination
Solution Approach 1:
The patent extracts and isolates the relevant fat regions from the complete cross-section image data. The image processing system identifies and separates fat regions from other elements such as vertebrae and background, extracting only the necessary information for quality determination while eliminating interfering noise from unrelated regions
Data Source
AI summary
A fish quality determination system includes a first machine learning unit that analyzes, by machine learning, a relationship between image data obtained by imaging a cross section of a fish tail and a region of a fish body in the image data, a data acquisition unit that acquires image data of a cross section of a tail of a determination target fish from a user device, a first estimation unit that estimates a region of a body of the determination target fish and outputs an estimation result, using the image data of the cross section of the tail of the determination target fish acquired by the data acquisition unit as an input, based on the relationship analyzed by the first machine learning unit, a generation unit that generates trimming image data in which a region other than the body of the fish is trimmed from the image data of the cross section of the tail of the determination target fish based on the estimation result by the first estimation unit, and a quality determination unit that determines quality of the determination target fish using the trimming image data.