A Retrieval Method of Face Image

A face image and face image information technology, applied in digital data information retrieval, instruments, digital data authentication, etc., can solve problems such as inaccurate retrieval results and inaccurate retrieval results

Active Publication Date: 2021-07-13
成都旺小宝科技有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Because there will be a gap between the ID photo image and the facial features of the current face image, the retrieval results will be inaccurate, and because the customer will visit many times and the visit time is too long, the capture device will have multiple times for the same customer. Different capture images from different angles, when searching by swiping the face image, even if the threshold is used for screening, the retrieval results will not be accurate enough, so it is necessary to perform multiple retrievals in different ways and types to obtain accurate and sufficient data to confirm the judgment Customer's visit record

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 Retrieval Method of Face Image
  • A Retrieval Method of Face Image
  • A Retrieval Method of Face Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Embodiment 1 of the present invention discloses a kind of retrieval method of face image, as figure 1 As shown, the specific steps are as follows:

[0038] S1: Collect the customer's ID photo data and the current face image data of the customer when swiping the card;

[0039] In this embodiment, the client's ID photo data is the ID photo on the resident ID card, and the ways to obtain the image data of the ID photo include:

[0040] A. Obtain the ID photo data through the ID card scanning device;

[0041] B. Directly import the ID photo data through the external data transmission interface on the terminal;

[0042] C. The image data of the ID card is transmitted to the terminal through the network or the data transmission interface, and the ID photo data of the ID card is extracted by online identification by calling a third-party algorithm using OCR recognition technology.

[0043] The current face image data of the customer is collected by the camera equipment on t...

Embodiment 2

[0053] Embodiment 2 of the present invention discloses a kind of face image retrieval method based on above-mentioned embodiment 1, as figure 2 and image 3 as shown, figure 2 and image 3 The whole constitutes a schematic flow diagram of the search method in this embodiment, and the specific steps are as follows:

[0054] S1: Collect the client's certificate photo data and the client's current facial image data when swiping the certificate. The specific process is as described in step S1 of the above-mentioned embodiment 1;

[0055] S2: Search for the first time, and mark the results for the second search, the specific process is as described in step S2 of the above-mentioned embodiment 1;

[0056] S3: Perform image processing on the face image data collected when swiping the card, and use the image processed face image as a reference image to search in the database.

[0057] The image processing is to call a third-party interface to perform P-image processing on the fa...

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 present invention provides a method for retrieving human face images, including the first retrieval and the second retrieval. The first retrieval is based on the threshold T1 as a condition, Obtain the retrieval results r1 and r2 respectively, mark the retrieval result r2 obtained based on the face image data collected when swiping the card as the reference image, and perform secondary retrieval based on the threshold T2 with the marked result image as the reference image, and set The retrieved similar image is bound to the client described in the current certificate and output. The present invention makes the result of capturing the human face image finally more accurate through secondary retrieval, and avoids the omission of retrieval data at the same time.

Description

technical field [0001] The invention relates to the technical field of face image retrieval, in particular to a face image retrieval method. Background technique [0002] After the sale of the real estate, there are a lot of visitors in the sales office. In order to achieve accurate positioning and tracking of visiting customers, better serve customers, and at the same time solve the problem of reducing the work intensity of staff when a large number of people visit, and facilitate the distinction between visits What channels do people visit, distinguish new and old customers, and automatic identification of second visits from peer customers? The risk control and passenger flow management system is used. The system is equipped with a face collection device at the entrance of the sales office to collect face image data of visitors And store it to form a face image database. When the real estate is sold, the customer searches through the real-time face image collected by swipi...

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): G06F16/583G06K9/00G06K9/62G06F21/32
CPCG06F16/583G06F21/32G06V40/172G06F18/22
Inventor 孙月徐桂贞袁培蓉汪琳建罗开琼谋程立涛翁达瑞张钧蓉杨森
Owner 成都旺小宝科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products