Boe technology group co., ltd. (20240233313). MODEL TRAINING METHOD, IMAGE PROCESSING METHOD, COMPUTING AND PROCESSING DEVICE AND NON-TRANSIENT COMPUTER-READABLE MEDIUM simplified abstract
MODEL TRAINING METHOD, IMAGE PROCESSING METHOD, COMPUTING AND PROCESSING DEVICE AND NON-TRANSIENT COMPUTER-READABLE MEDIUM
Organization Name
boe technology group co., ltd.
Inventor(s)
MODEL TRAINING METHOD, IMAGE PROCESSING METHOD, COMPUTING AND PROCESSING DEVICE AND NON-TRANSIENT COMPUTER-READABLE MEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240233313 titled 'MODEL TRAINING METHOD, IMAGE PROCESSING METHOD, COMPUTING AND PROCESSING DEVICE AND NON-TRANSIENT COMPUTER-READABLE MEDIUM
Simplified Explanation: The patent application describes a model training method that uses a convolutional neural network to enhance the quality of fingerprint images.
Key Features and Innovation:
- Acquiring a sample set with blurred and sharp fingerprint images.
- Using an encoding network for down-sampling and feature extraction.
- Employing a decoding network for up-sampling and feature extraction.
- Calculating loss value to adjust network parameters for image enhancement.
- Determining the adjusted network as an image processing model.
Potential Applications: This technology can be used in forensic analysis, biometric security systems, and image enhancement software.
Problems Solved: This technology addresses the challenge of enhancing the quality of blurred fingerprint images for better identification and analysis.
Benefits:
- Improved accuracy in fingerprint identification.
- Enhanced security in biometric systems.
- Better image quality for forensic analysis.
Commercial Applications: Enhancing fingerprint images for law enforcement agencies, biometric security companies, and image processing software developers.
Prior Art: Researchers can explore prior studies on image enhancement using convolutional neural networks and fingerprint recognition technologies.
Frequently Updated Research: Stay updated on advancements in image processing, biometric security, and neural network training for fingerprint enhancement.
Questions about Fingerprint Image Enhancement: 1. How does this technology improve the accuracy of fingerprint identification? 2. What are the potential challenges in implementing this technology in real-world applications?
Original Abstract Submitted
a model training method includes: acquiring a sample set, wherein samples in the sample set include a blurred image and a sharp image of a same fingerprint; inputting the blurred image into a convolutional neural network, performing, by an encoding network in the convolutional neural network, down-sampling and feature extraction to the blurred image, to output a plurality of feature maps, and performing, by a decoding network in the convolutional neural network, up-sampling and feature extraction to the feature maps, to output a predicted image corresponding to the blurred image; according to the predicted image, the sharp image and a predetermined loss function, calculating a loss value of the convolutional neural network, and, with minimizing the loss value as a target, adjusting parameters of the convolutional neural network; and determining the convolutional neural network of which the parameters are adjusted to be an image processing model.