Unlock instant, AI-driven research and patent intelligence for your innovation.

A Fast Vein Image Retrieval Method Based on Image Feature Signature

A technology of image features and vein images, applied in still image data retrieval, biometric identification, subcutaneous biometrics, etc., can solve problems such as large storage space occupied by hash tables, inability to meet industrial applications, loss of precision, etc.

Active Publication Date: 2022-03-11
MELUX TECH CO LTD
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when faced with large-scale, high-dimensional data, the precision loss caused by hashing and the large storage space occupied by hash tables make it unable to meet the needs of most industrial applications.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Fast Vein Image Retrieval Method Based on Image Feature Signature
  • A Fast Vein Image Retrieval Method Based on Image Feature Signature
  • A Fast Vein Image Retrieval Method Based on Image Feature Signature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] In order to make the purpose and technical solution of the present invention clearer, the technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0023] The invention discloses a fast vein image retrieval method based on image feature signatures. By decomposing an image into a local feature set, signature encoding is performed on the local features, and a full-text search engine is used to convert image retrieval into text retrieval, thereby realizing vein image retrieval. Quick search.

[0024] refer to figure 1 As shown, taking the fast retrieval of palm vein images as an example, the specific implementation steps are as follows:

[0025] Step (1): Use the connected domain detection method to extract local features of the palm vein image to be processed, and obtain the key point area image set of the palm vein image, which is defined as P.

[0026] Specifically, the palm vein imag...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a fast vein image retrieval method based on image feature signature. The method decomposes the image into a local feature set, performs signature encoding on the local features, and uses a full-text search engine to convert image retrieval into text retrieval, thereby realizing vein image retrieval. Fast retrieval of images. The method of the invention achieves the purpose of narrowing the retrieval range and reducing the storage space of the feature by reducing the dimension of the feature vector and signing the image. At the same time, image retrieval is carried out by referring to the method of text retrieval, which effectively improves the retrieval efficiency. While maintaining high precision for hundreds of millions of images, it can achieve millisecond-level response speed, reaching the level of industrial availability.

Description

technical field [0001] The invention relates to the technical field of vein feature recognition, in particular to a fast vein image retrieval method based on image feature signatures. Background technique [0002] As a biometric identification technology, vein recognition is more accurate than fingerprint, face and other biometric identification technologies. It uses the distribution lines of palm veins and finger veins for identification. Its main feature is non-contact image collection, which is safe and hygienic. , can not be obtained under visible light, and only the living body can detect the veins, which cannot be forged, and has strong concealment and anti-counterfeiting capabilities. Compared with face and fingerprint and other characteristic information, the vein structure of the palm is richer and more complex, and the security level is high. At present, vein recognition technology has been gradually applied to security systems, banking systems, building access con...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/53G06V40/14
Inventor 余孟春谢清禄梁锦峰
Owner MELUX TECH CO LTD