Near-optimal skin-color detection method under Gaussian frame

Abstract

In order to solve the problem that the performance is better only when the existing method under the Gaussian frame is in a certain specific interval of false positive rates (FPRs), the invention provides a near-optimal skin-color detection method under the Gaussian frame, which is called as multiple Gaussian models (MGMs) and deduces a discrete and continuous form. The method has good performance for the whole FPR interval and comprises the following steps of: firstly carrying out space normalization on RGB (Red-Green-Blue) colors to obtain an RGB space, then establishing a plurality of optimal single Gaussian models, and finally fusing the optimal models. The MGMs comprise the optical single Gaussian models, and each Gaussian model corresponds to a predefined FPR value. Under the condition of each FPR, the corresponding optimal model can obtain highest true positive rates (TPRs), and the model is solved and obtained by adopting an optimization problem based on a search algorithm. Therefore, for all the FPR values, the MGMs can obtain the near-optimal skin-color detection performance under the Gaussian frame. In addition, the MGMs and the single Gaussian models (SGMs) have the same computational complexity at the test link.

Description

Technical field: [0001] The invention relates to a method for detecting skin color based on a multi-Gaussian model, which belongs to the field of image processing. Background technique: [0002] In the field of image processing and computer vision, skin color detection is of great significance in the application fields of face detection, face recognition and bad image filtering. [0003] In the past few years, several pixel-based skin color detection methods have emerged. These methods can be divided into two categories: the first category is non-parametric models, such as direct threshold method and histogram method in skin color space; the second category is parametric models, such as single Gaussian model, elliptical boundary model, etc. Compared with non-parametric models, parametric models require less training data and lower storage requirements, and are easier to generalize. Menser and Wien used multidimensional Single Gaussian Models (SGMs) to represent the skin co...

AI Technical Summary

Problems solved by technology

However, they are limited in that the methods perform well only when the FPRs are within a small specific range

Images