Identification photo ear detection and extraction method based on facial outline analysis

Abstract

The invention discloses an identification photo ear detection and extraction method based on facial outline analysis. The method is used for automatically judging whether an identification photo head portrait is upright or not, detecting whether ears exist in an identification photo or not and finally extracting ear areas of the identification photo. According to the algorithm, an outer skin outline line and a facial outline line are analyzed, and observation is conducted on the basis that the human facial outline line meets a parabolic equation to a certain degree. The method comprises the steps that an ear existence detection method based on outer skin outline parabola fitting is proposed, the outer skin outline is fit through a parabola, and when a fitting result is good, it shows that the outer skin outline coincides with the facial outline, and no ear exists; otherwise, when the ears exist, a dynamic programming algorithm based on gradient and parabola guiding is proposed for identifying the facial outline, the ear areas and the facial skin area can be segmented through the facial outline line, and then effective extraction of the ear areas is achieved. The algorithm can be used for automatically judging qualification of a selfie identification photo, and the extracted ear areas can be used for aftertreatment of an identification photo image.

Description

technical field [0001] The invention relates to the field of computer image processing, in particular to an ear detection and extraction method based on facial contour analysis. Background technique [0002] ID photos are one of the basic information for human identification. They are usually embedded in the text of ID cards, passports, etc., or affixed to application forms for admission, employment, etc., and are used to verify the uniqueness of user data. They have a wide range of applications in all aspects of social life. application. Traditionally, ID photos are taken by professionals. In the photo studio, the user sits at a designated position, adjusts his posture under the guidance of the photographer, and finally the photographer takes a ID photo that meets the requirements. With the rapid development of the mobile Internet, mobile phone software for taking photos of ID cards and selfies has appeared. The user takes a picture of his face and uploads it to the serve...

AI Technical Summary

Problems solved by technology

[0004] However, none of the above methods can be used for ear detection and extraction of ID photos.

Because the ID photo is taken from the front of the face, the ear information is very little, and the internal structure of the ear cannot be seen, only the general outline of the ear can be seen, resulting in very few ear features that can be extracted; moreover, different people’s Ear shape and contour vary greatly

Therefore, the supervised ear learning and recognition method that extracts features first and then trains a statistical model is not only difficult to design, but also very complex and less robust, and is not suitable for ear detection and extraction of ID photos.

Images