Rapid detection fuzzy method of face in street view image

Abstract

The invention discloses a rapid detection fuzzy method of a face in a street view image. The method comprises the following steps of: removing a region which does not contain a face region; detecting a standby region of the face according to an Adaboost detection algorithm of a Harr-like characteristic; setting a certain restriction condition according to shape and color characteristics of the face to remove a non-face region; and carrying out smooth fuzzy treatment in horizontal and vertical directions on all the face regions to obtain a result image. According to the rapid detection fuzzy method disclosed by the invention, a skin color detection method based on bayesian statistics and a human shoulder image detection method based on an HOG (Histogram of Oriented Gradient) characteristic are introduced to remove the non-face region; and a rapid and robust face detection algorithm is provided based on the Harr-like characteristic and the shape and skin color characteristics of the face region. According to the rapid detection fuzzy method disclosed by the invention, horizontal and vertical templates are ingeniously utilized to carry out the smooth fuzzy treatment on the face region, so that the fuzzy effect is guaranteed and the processing speed is greatly improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a fast method for detecting blurred faces in street view images. Background technique [0002] In the past few years, online street view map products have developed rapidly. One of the most representative is the Google Street View service. The large scale and accuracy of Street View images allow users to efficiently search for specific locations of points of interest, and to virtually walk through street-level environments. Therefore, a series of interesting and beneficial applications have emerged, such as: virtual tourism, real estate search, enhanced driving navigation, etc. However, in the process of capturing street view images, some information with personal privacy is often captured, mainly including human faces and license plates. To preserve these privacy, face and license plate regions are detected and blurred. [0003] Face detection in street view images ...

AI Technical Summary

Problems solved by technology

[0003] Face detection in street view images is different from traditional face detection. The difficulty of detection is mainly reflected in the following aspects: 1. The size of street view images is large, the background is very complex, the illumination changes greatly, and the contrast is small; 2. The face 3. The area occupied by the face has low resolution and partial occlusion

[0004] Traditional face detection and blurring methods are not optimized for this type of street view images, and it takes a long time. Therefore, the present invention designs a fast detection blur method for faces in street view images

Images