Geometrical feature-based human face aesthetics analyzing method

Abstract

The invention provides a geometrical feature-based human face aesthetics analyzing method, which comprises the steps of: carrying out combining description through combined strategy-based local geometrical features and constructing weak classifiers by using memory-based dynamically weighted kernel density estimation (MDKDE); and realizing effective integration of the features by using an Adaboost ensemble learning mechanism so as to obtain accurate classifications for human face aesthetics. Different from the traditional geometrical feature-based human face aesthetics analyzing technique, the geometrical feature-based human face aesthetics analyzing method selects the local geometrical features which are used for describing human face aesthetics from multiple angles, such as Euclidean distance, gradient and area and the like to compose single descriptions for the human face aesthetics, and combined feature description is obtained by combining descriptions of the local geometrical features, and the weak classifiers for Adaboost ensemble learning are constructed by using the MDKDE, thus a good classifying result for randomly input human face images is obtained.

Description

technical field [0001] The present invention relates to the technical field of human face aesthetic analysis methods, in particular to a geometric feature-based human face aesthetic analysis method. Background technique [0002] Facial beauty is the unity of individuality and commonality. Individuality means that everyone's appearance is different and has its own beauty characteristics. Commonality means that everyone's beauty is different, but they all follow certain rules. Since ancient times, people's pursuit of beauty has never stopped. Philosophers, psychologists, and estheticians have also been trying to find the essence of beauty, and formed many aesthetic laws. For example, Chinese classical aesthetic standards have become the standard of Chinese culture. Important ideological systems, the "three courts and five eyes" theory of traditional Chinese aesthetics, the "golden ratio" that has been admired since ancient Greece, and the new "golden ratio" recently discovered...

AI Technical Summary

Problems solved by technology

[0013] (1) For the subspace-based algorithm, it needs to perform position calibration preprocessing on the input face image, and is susceptible to illumination, pose changes, image quality, etc.

[0014] (2) For the method based on geometric features, firstly, this method is less robust to strong expression changes and posture changes; secondly, general geometric features only describe the basic shape and structural relationship of the face, Local subtle features, such as texture features, are ignored, resulting in partial information loss; in addition, manual calibration of geometric relationships is required, with a large workload, and manual intervention is required in the experimental process, which cannot be fully automated

Images