Article Identification via Image Feature Extraction and User Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In industrial production, particularly in sheet metal manufacturing, articles often cannot be automatically identified due to insufficient image capture and inadequate identification programs, leading to resource waste and potential errors, as manual identification is time-consuming and relies on experienced personnel.
Innovation Solution
A method and apparatus that associate images of articles with stored CAD data using image and article feature extraction algorithms, with user ratings optimizing the algorithms to improve identification accuracy, employing data aggregation routines and weighted variables for enhanced image processing and comparison.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification of articles is performed, then identification accuracy is improved, but time consumption increases and relies on experienced personnel
Solution Approach 1:
The patent replaces manual visual identification with an automated image processing system that captures images of articles, extracts features from these images, and compares them against stored article data to automatically identify articles, eliminating the need for experienced personnel and reducing time consumption while maintaining accuracy
Solution Approach 2:
The system creates a digital copy (image) of the physical article and processes this copy through feature extraction algorithms, allowing rapid and repeatable identification without physical handling of each article, thus saving time and resources
2Loss of time
If automatic identification of articles is performed, then time consumption is reduced, but identification accuracy deteriorates due to insufficient image capture and inadequate programs
Solution Approach 1:
The patent divides the identification process into distinct segments: image capture, image feature extraction, article feature extraction from stored data, and comparison. This segmentation allows each component to be optimized independently, improving overall accuracy while maintaining automation
Solution Approach 2:
The system extracts multiple features from images (such as geometric parameters, surface characteristics, and dimensional data) and compares them against stored article parameters, using weighted variables to adjust the importance of different features, thereby improving identification accuracy through parameter-based analysis
3Reliability
If features are extracted from both image and stored article data, then identification reliability is improved, but processing complexity increases
Solution Approach 1:
The patent introduces feature extraction algorithms as intermediary components that bridge the image capture system and the stored article data, transforming both into comparable feature representations. This intermediary layer simplifies the comparison process while maintaining high reliability through comprehensive feature analysis
Data Source
AI summary
The invention relates to a method and an apparatus (10) for recognizing an article. This involves at least one shot (14), in particular in the form of a photograph, of the article being produced. The shot (14) is used to ascertain shot features (22) by means of a shot extraction algorithm (20). Stored article data (12) are used to ascertain article features (28) and to compare them with the shot features (22) in order to output association information (36). There is in particular provision according to the invention for a user rating (42) to be provided to improve both the shot extraction algorithm (20) and the article extraction algorithm (26). Alternatively or additionally, there is in particular provision according to the invention for both the shot extraction algorithm (20) and the article extraction algorithm (26) to be produced on the basis of interconnected, preferably weighted, data aggregation routines.