Interactive face image attribute marking device based on MFC

An interactive human and face image technology, applied in the field of face recognition, can solve the problems of slow speed, complex operation, low efficiency, etc., and achieve the effect of reducing development cycle, reducing difficulty, and strong practicability

Inactive Publication Date: 2017-07-28
ENC DATA SERVICE CO LTD
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Face attribute recognition, including gender, age, whether to wear glasses, whether it is blurry, etc., is increasingly used in face multi-task recognition, and the annotation of these attributes comes from manual annotation. The development of face technology is becoming more and more mature. The demand for attribute resources and description text is massive. At present, face attribute labeling is basically manual labeling, which is complex, slow, and inefficient.

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
  • Interactive face image attribute marking device based on MFC
  • Interactive face image attribute marking device based on MFC
  • Interactive face image attribute marking device based on MFC

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Below by embodiment the present invention will be further described, and its purpose is only to understand research content of the present invention better but not limit protection scope of the present invention.

[0024] Such as figure 1 As shown, the MFC-based interactive face image attribute labeling method of the present invention includes the following steps a~e:

[0025] Step a: the face detection step, load the face image, use the face detector to detect the face in the image, and save the face position. Specifically, the description text (such as figure 2 shown), the system will sequentially load the face images in the text and automatically detect the faces in the images. Here, the face detector can quickly and accurately detect the faces in the input image to be marked, and the detector supports face positioning under multi-scale, multi-angle, multi-ethnic and multi-illumination conditions.

[0026] Step b: a default label generating step, for the faces de...

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 provides an interactive face image attribute marking device based on MFC (Microsoft Foundation Classes), and the method comprises the steps: step a, face detection step: a face image is loaded, faces in the image are detected through a face detector, and face positions are saved; step b, default label generation step: default labels of attributes of the faces which are detected in the step a and displayed on a display interface in sequence are generated and displayed on the interface; step c, label correction step: after the generation of default labels of attributes, and when the displayed attributes of the faces does not match with the default labels is discovered, matched label items are selected from pull-down menus of unmatched labels; step d, missed face marking step: when a face is missed to detect, the face needs to mark is selected, and the matched labels are selected according to the step c; and step e, marking information saving step: face image data with marked attributes is saved. According to the invention, the efficiency and precision for face attribute marking task can be improved.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to an interactive face image attribute labeling method based on MFC (Microsoft Foundation Classes, Microsoft Foundation Class Library). Background technique [0002] Face attribute recognition, including gender, age, whether to wear glasses, whether it is blurry, etc., is increasingly used in face multi-task recognition, and the annotation of these attributes comes from manual annotation. The development of face technology is becoming more and more mature. The demand for attribute resources and description text is massive. At present, face attribute annotation is basically manual annotation, which is complex, slow, and inefficient. Therefore, there is a need for a face attribute labeling method with a friendly interface, simple operation, and high efficiency, which can provide a large amount of accurate description text for face multi-task learning and speed up the developm...

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 Applications(China)
IPC IPC(8): G06K9/62G06K9/00
CPCG06V40/16G06V40/161G06V40/179G06F18/40
Inventor 刘洋王剑邦张如高
Owner ENC DATA SERVICE CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap