Automated Paper Cup Design Defect Detection via Neural Network Masking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The paper cup industry faces significant challenges in detecting design defects before printing, leading to quality control issues and increased costs due to manual inspection and repeated proofing, which hinders flexible and customized production models.
Innovation Solution
A method and device utilizing an image segmentation model based on neural network technology to automatically detect design defects in paper cup designs by obtaining a design drawing set, generating a precise mask, and mapping it to specification data for defect detection, enabling identification of defects before printing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual inspection is used to detect design defects, then detection capability is provided, but production efficiency decreases and costs increase
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated computer-based detection system that uses image processing and neural network algorithms to automatically identify design defects in paper cup templates, eliminating the need for human operators to manually review each design
Solution Approach 2:
The detection system performs self-validation by automatically comparing design elements against predefined rules and standards, enabling the system to detect its own potential errors without requiring external manual verification
2Reliability
If repeated proofing is conducted to avoid defects, then product quality improves, but time consumption and costs increase
Solution Approach 1:
The patent implements preliminary defect detection at the template design stage by automatically analyzing design drawings before production begins, identifying potential quality issues early in the process flow and preventing the need for repeated proofing and rework later
3Productivity
If automated detection system is implemented, then productivity improves, but system complexity increases
Solution Approach 1:
The patent divides the defect detection task into multiple independent modules including template image acquisition, image preprocessing, feature extraction, neural network analysis, and result output, allowing each module to be developed, tested, and maintained separately while working together as an integrated system
Data Source
AI summary
Disclosed are method and device for automatically pre-detecting paper cup design defects. The method includes: receiving an imported design drawing to be detected, and obtaining a corresponding fan-shaped image mask through the trained image segmentation model; converting the fan-shaped image mask into a real fan-shaped frame; calculating and obtaining a corresponding target model design drawing according to the real fan-shaped frame, and mapping to the specification data of a corresponding model; and partitioning the real fan-shaped frame according to the mapped specification data, detecting corresponding defects in each partition through a preset detection module, and outputting defect detection results. The present disclosure enables identification of design defects solely through graphic design drafts, thereby reducing costs, enhancing flexible production capabilities, and filling a gap in the paper cup industry. Defect detection functions are pluggable, that is, ineffective detection modules can be replaced, and new detection items can be added.