AI Contact Lens Center Deviation Detection for Off-Center Defects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining contact lens defects, particularly off-center deviations, are inadequate for precise measurement, leading to increased production costs and quality issues due to discarding all defects, and consume excessive computing resources with limited accuracy.
Innovation Solution
An apparatus and method using a data augmentation unit with a denoising diffusion probabilistic model (DDPM) and an asymmetric convolution-you only look once (AC-YOLO) model to accurately detect and measure center deviation by augmenting contact lens image data and enhancing computing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional defect inspection methods are used to determine contact lens defects, then all defective products are discarded, but this leads to increased production costs and reduced productivity
Solution Approach 1:
The patent replaces traditional mechanical/optical inspection systems with an AI-based deep learning system. The neural network automatically analyzes contact lens images to detect defects such as off-center deviations, replacing manual or rule-based inspection methods. This substitution enables more precise defect identification while reducing waste, as the AI can distinguish between critical and non-critical defects, allowing selective rejection rather than discarding all potentially defective items.
2Measurement precision
If conventional center deviation measurement methods are used, then measurement accuracy is limited, but computing resources are consumed excessively
Solution Approach 1:
The patent transforms the measurement approach by changing the parameters processed by the AI system. Instead of measuring multiple physical dimensions and calculating deviations, the system directly predicts center deviation as a single parameter output from the neural network. This parameter transformation simplifies computation while maintaining or improving accuracy, as the AI learns optimal measurement strategies during training.
Solution Approach 2:
The patent uses image copying and data augmentation techniques to create synthetic training data. By generating multiple copies and variations of contact lens images with simulated defects, the system trains the AI model efficiently without requiring extensive physical samples or complex measurement equipment. This copying approach reduces the computational burden during actual inspection while maintaining measurement precision.
3Reliability
If existing defect determination systems are implemented, then quality control is maintained, but real-time inspection and decision-making are hindered
Solution Approach 1:
The patent implements preliminary action by pre-training the AI model with extensive contact lens images and defect patterns before deployment. The system learns to recognize various defect types, including off-center deviations, during an offline training phase. This preliminary learning enables the system to perform rapid, accurate inspections in real-time production environments without requiring complex calculations or reference comparisons during actual quality control checks.
Data Source
AI summary
An apparatus for measuring a center deviation of a contact lens includes a data augmentation unit configured to augment original contact lens image data photographed during a contact lens manufacturing process, an artificial intelligence learning unit configured to use a dataset augmented by the data augmentation unit as an input to conduct learning through an artificial intelligence learning model, and detect a center point of a colored area and a center point of a frame area of the contact lens through learning, and a measuring unit configured to measure the center deviation using the center point of the colored area and the center point of the frame area detected through the artificial intelligence learning model in the artificial intelligence learning unit. There is an effect of quickly and accurately detecting an off-center defect of a contact lens, thereby reducing a defect rate and increasing production efficiency.