Barcode Recognition Using Neural Networks for Selection Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing barcode recognition technologies face challenges in accurately and efficiently recognizing multiple barcodes or texts in a single image, leading to inefficiencies in logistics and management processes.
Innovation Solution
A method and device utilizing a camera module and artificial neural networks to continuously capture images, identify target images, convert them to strings, and selectively output the corresponding strings based on similarity comparisons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple barcodes or texts are recognized in a single image, then the recognition speed is improved, but the accuracy of selecting the desired barcode or text deteriorates
Solution Approach 1:
The system performs preliminary continuous capturing and identification of multiple barcodes or texts before the user makes a selection. The camera module continuously captures images and the processing module identifies multiple barcodes/texts in advance, storing them for later selection. This preliminary action allows the system to have all options ready before the user needs to select, improving both speed and accuracy.
Solution Approach 2:
The system introduces an intermediary selection mechanism (predetermined mark, confirmation signal) between the initial recognition of multiple barcodes and the final output. This intermediary step allows the user to select the desired barcode or text from the pre-identified multiple options, resolving the contradiction between fast recognition and accurate selection.
2Quantity of substance
If continuous capturing is performed to capture multiple barcodes or texts, then the quantity of recognized barcodes or texts is improved, but the time required for processing increases
Solution Approach 1:
The camera module continuously captures images during a predetermined time period, ensuring that multiple barcodes or texts are captured without interruption. This continuous capturing ensures that all relevant barcodes or texts are captured in sequence, increasing the quantity recognized while the system processes them efficiently in real-time.
Solution Approach 2:
The system performs preliminary identification and storage of multiple barcodes or texts during the continuous capturing phase. By identifying and storing the captured barcodes/texts in advance (before user selection), the system reduces the processing time required after capturing, as the heavy lifting of identification is already done.
3Measurement precision
If a single capture is taken to select a specific barcode or text, then the selection precision is improved, but the probability of capturing the desired target deteriorates
Solution Approach 1:
The system performs preliminary continuous capturing to capture multiple barcodes or texts before the user needs to select. By having multiple pre-captured images with multiple identified barcodes/texts available, the system ensures that the desired target is already captured and identified, making the subsequent single capture for selection redundant and improving both precision and reliability.
Solution Approach 2:
The system creates multiple copies (images) of the target area during continuous capturing. Instead of relying on a single capture, the system has multiple captured images with identified barcodes/texts to choose from, increasing the reliability that the desired target is captured while allowing precise selection from the available copies.
Data Source
AI summary
A barcode image recognition device includes a camera module, an input component, a processing module, a storage module, an output module, and a display. The input component is coupled to the camera module, and the processing module is coupled to the camera module. The processing module includes a first artificial neural network, a conversion module, a second artificial neural network, and a comparison module. The first artificial neural network identifies the first target image of each target object in the default images captured by the camera module. The second artificial neural network identifies the second target image in the captured image captured by the camera module. The storage module is coupled to the processing module. The output module is coupled to the comparison module and the storage module. The display is coupled to the output module.