Modular Tablet Vision Inspection for Defect Category and Position Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tablet quality inspection systems fail to accurately analyze defect categories and positions, leading to inaccurate quality assessment due to simple image comparison and pixel analysis, ignoring the impact of defect categories on tablet quality.
Innovation Solution
A tablet quality inspection system using modular machine vision recognition that extracts implicit features from defect images, categorizes defects based on these features, and analyzes tablet quality by considering defect positions, employing defect feature extraction models and judgment value calculations to determine defect categories and overall quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If simple image comparison and pixel analysis are used for tablet quality inspection, then the inspection process is simple and fast, but the accuracy of defect category analysis and quality assessment is poor
Solution Approach 1:
The inspection system segments the defect analysis process into multiple independent modules: defect detection module, feature extraction module, defect categorization module, and quality assessment module. Each module handles a specific aspect of the inspection, allowing complex analysis without sacrificing overall inspection speed. The segmentation enables parallel processing of different defect features simultaneously.
Solution Approach 2:
The system transforms the inspection approach by changing from simple pixel value comparison to multi-parameter feature analysis. It extracts multiple features including color parameters (RGB, HSV), texture parameters (entropy, contrast, homogeneity), and shape parameters, then uses these transformed parameters for accurate defect categorization while maintaining inspection efficiency through optimized computation.
2Measurement precision
If comprehensive feature extraction and defect categorization are performed, then the quality assessment accuracy is improved, but the inspection complexity and processing time increase
Solution Approach 1:
The complex inspection system is divided into modular functional components: image acquisition module, preprocessing module, defect detection module, feature extraction module, categorization module, and quality assessment module. This segmentation reduces overall system complexity by making each module independent and manageable, while enabling comprehensive analysis through their coordinated operation.
Solution Approach 2:
The system introduces intermediate processing steps including image preprocessing (noise filtering, contrast enhancement) and feature selection mechanisms that act as mediators between raw image data and final quality assessment. These intermediaries simplify the complexity by filtering out irrelevant information and transforming data into suitable formats for subsequent analysis stages.
3Measurement precision
If detailed defect feature extraction and categorization are implemented, then the tablet quality analysis becomes accurate, but the inspection efficiency decreases
Solution Approach 1:
The system performs preliminary defect detection and feature extraction before full categorization and quality assessment. By identifying potential defect regions first and extracting only relevant features from those regions, it avoids processing the entire image with all analysis algorithms, thus maintaining accuracy while reducing inspection time through selective detailed analysis.
Solution Approach 2:
The system applies partial action by focusing detailed feature extraction and categorization only on detected defect regions rather than the entire tablet surface. For areas without defects, it uses simplified verification, thereby achieving accurate defect analysis where needed while maintaining overall inspection efficiency through selective application of complex processing.
Data Source
AI summary
Disclosed in the present disclosure are a tablet quality inspection system and method based on modular machine vision recognition, belonging to the field of machine vision. The present disclosure analyzes defect category according to extracted defect feature, obtains the defect category of corresponding tablet, analyzes the tablet production quality according to the tablet defect category and the corresponding defect position data, so as to accurately analyze tablet image, extract the implicit feature reflecting tablet defect, accurately analyze the defect category according to the implicit feature of the defect, and then accurately analyze tablet quality according to the classified defect category and positions, thereby improving the accuracy and the efficiency of a tablet quality inspection.