Control method for safety box with palmprint recognition system
A control method and technology of palmprint recognition, which is applied in the field of safes, can solve problems such as no application method of palmprint recognition technology, and achieve the effects of easy mass production, low cost and high safety
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0024] The present embodiment provides a kind of control structure of palmprint safe, as Figure 4 Shown, comprise palmprint image collection module 10, palmprint image preprocessing module 11, palmprint image feature extraction module 12, image matching module 13, storage module 16 and unlocking control module 15; Described palmprint image collection module 10 uses To collect the palmprint image of the user, the palmprint image of the user is preprocessed in the palmprint image preprocessing module 11, and the feature vector of the palmprint image after the preprocessing is extracted in the palmprint image feature extraction module 12 According to the feature vector extracted and the pre-stored authorized user palmprint feature vector matching in the storage module, if the matching is consistent, an unlocking instruction is sent to the unlocking control module, and if the matching is inconsistent, the unlocking instruction is not issued, no matter whether the matching is consi...
Embodiment 2
[0041] This embodiment provides a palmprint image preprocessing method.
[0042] Preprocessing is the first step in the process of automatic palmprint recognition, and its quality directly affects the effect of palmprint recognition. Commonly used preprocessing methods mainly include binarization, positioning (rotation and translation), normalization, filtering, and thinning of palmprint images.
[0043] Palmprint image acquisition is performed with a CCD-based device. In order to reduce the errors and distortions caused by translation, rotation, and distortion during the collection process, when collecting palmprint images, each finger of the palm should be opened as far as possible, so that the edges of the fingers can be extracted and used for alignment and normalization palm print image. After processing, the size of each palmprint block is 128×128 (such as figure 2 (a)), and the offset and rotation have been basically eliminated, which facilitates the recognition of p...
Embodiment 3
[0045] This embodiment provides a palmprint image feature extraction method—wavelet feature extraction.
[0046] Palm print image is an approximate texture periodic pattern, in which the main lines are the deepest and thickest lines on the palm, and most palms have three main lines; besides the main lines, there are many crease lines on the palm, generally these The lines are thinner, shallower, and quite irregular than the main lines. The direction and spatial frequency of the ridge lines in different regions of the palmprint image represent the intrinsic characteristics of the palmprint image. According to the characteristics of the palmprint image, we experimented with various feature extraction methods and found that because the wavelet transform has multi-channel and multi-resolution functions, a method based on wavelet transform is used to extract the features of the palmprint image for recognition It not only saves the time of image preprocessing, but also has higher r...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com