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

Facial detection device, and control method and program for same

A face detection and control method technology, applied in computer parts, TV system parts, image data processing and other directions, can solve the problem of not being omnipotent and unable to expect the success rate of face detection, and achieve the effect of improving the success rate

Inactive Publication Date: 2019-07-30
ORMON CORP
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the method of patent document 1 is very effective, it is not a panacea
In particular, for images with extremely small differences between light and dark between local regions or for images in which the relationship between light and dark is reversed, the method based on gamma transformation cannot expect to improve the success rate of face detection.

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
  • Facial detection device, and control method and program for same
  • Facial detection device, and control method and program for same
  • Facial detection device, and control method and program for same

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention relates to face detection algorithms for automatically detecting faces from images. The present invention can be used as an elemental technology of image sensing, computer vision, robot vision, etc., and as a specific application, it can be applied to detection and tracking of people in surveillance cameras, automatic focusing of built-in cameras in digital cameras or smartphones, It is used in various fields such as human detection in home appliances and face detection engines in face authentication systems.

[0022] Hereinafter, an example of a preferred mode for carrying out the present invention will be described with reference to the drawings. However, the configuration and operation of the device described in the following embodiments are examples, and are not intended to limit the scope of the present invention thereto.

[0023] (Structure of face detection device)

[0024] refer to figure 1 , and the configuration of the face detection d...

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

Provided is a facial detection device having an identification device which, while scanning a search window with respect to an image, uses image characteristics based on the light-dark difference between local regions in the partial image within the search window to determine whether a partial image is an image of a face; wherein the facial detection device determines whether or not a partial image in the search window is a low brightness image, and if it is determined that the partial image is a low brightness image, a determination is made by the identification device using a modified partial image, instead of the partial image, for which the pixel brightness at a prescribed position in the partial image has been modified.

Description

technical field [0001] The present invention relates to a face detection device for detecting a face from an image. Background technique [0002] In recent years, face detection technology that automatically detects faces from images has been implemented in various applications including autofocus of digital cameras and surveillance cameras. Among the most practical algorithms of face detection technology, there is a method of evaluating the face similarity of an image based on the difference between light and dark between local regions. In facial images, there is a tendency, for example, that the eye area is darker than the nose or cheek area, the mouth area is darker than the jaw area, the forehead area is brighter than the eye area, etc., regardless of gender or race. common. Focusing on this tendency, a face or non-face is determined using image features based on the difference in brightness and darkness between local regions. As image features, Haar-like features are...

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): G06T7/00G06K9/00
CPCG06T1/00G06V40/162G06V40/165G06V10/993H04N23/76H04N23/71G06T5/007G06T7/11G06T2207/30201G06V10/60G06V40/161
Inventor 赤木政弘寺井宽晶远藤伸司
Owner ORMON CORP