Skin texture detecting method and apparatus based on Gabor features

Abstract

The invention is applicable to the technical field of image processing, and provides a skin texture detecting method and apparatus based on Gabor features. The method comprises the steps of dividing an image to be detected into a plurality of image blocks; performing convolution in the space for color channels of the image blocks and pre-established Gabor filter banks sequentially, to obtain k*s*r arrays having the same size as that of the image blocks; calculating mean values and variances of the arrays, and taking the mean values and variances as feature values to obtain k*s*r*2 feature values; and taking the k*s*r*2 feature values as feature vectors of the image blocks, and detecting the feature vectors through a pre-established classifier to determine whether the image blocks have skin texture features. The invention can be used for quickly and accurately detecting images having skin texture features.

Description

technical field

[0001] The invention belongs to the technical field of image processing, and in particular relates to a Gabor feature-based skin texture detection method and device. Background technique

[0002] In recent years, image detection has been widely concerned, because the image contains a large amount of texture information, and the texture features of different parts are quite different. Therefore, texture as an important low-level visual feature has received extensive attention, and texture detection has become an important research field in image detection.

[0003] With the rapid development of the Internet, while the Internet brings convenience to people, it also produces a lot of bad information, especially pornographic pictures have a negative impact on young people. In the detection of pornographic images based on skin color, objects similar to skin color such as sandy beaches and wood grains are easily misjudged, but these texture detection can easily fi...

Examples

Embodiment 1

[0024] figure 1 The implementation flow of the Gabor feature-based skin texture detection method provided by Embodiment 1 of the present invention is shown, and the method process is described in detail as follows:

[0025] In step S101, the image to be detected is divided into a plurality of image blocks.

[0026] Exemplarily, in this embodiment, the image to be detected may be divided into image blocks with a size of 16*16.

[0027] It should be noted that since the texture feature is a feature that depends on the relationship with the surrounding pixels of the image, if the image block is too small, it will not reflect this cyclic feature, and the amount of calculation will increase greatly; if the image block is too large , an image block may contain both skin texture features and non-skin texture features, which will reduce the accuracy of skin texture feature detection. In this embodiment, after passing specific experiments, the image is preferably divided into image b...

Embodiment 2

[0093] image 3 The composition structure of the skin texture detection device based on Gabor features provided by Embodiment 2 of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown.

[0094] The skin texture detection device based on Gabor features can be a software unit, a hardware unit, or a combination of software and hardware running in the terminal device, or it can be integrated into the terminal device or run on the terminal device as an independent pendant in the application system.

[0095] The skin texture detection device based on Gabor features specifically includes:

[0096] The first image block division unit 31 is used to divide the image to be detected into a plurality of image blocks;

[0097] The first calculation unit 32 is used to convolve each color channel of each image block with a pre-established Gabor filter bank in the spatial domain to obtain k*s*r matrice...

technical field

[0001] The invention belongs to the technical field of image processing, and in particular relates to a Gabor feature-based skin texture detection method and device. Background technique

[0002] In recent years, image detection has been widely concerned, because the image contains a large amount of texture information, and the texture features of different parts are quite different. Therefore, texture as an important low-level visual feature has received extensive attention, and texture detection has become an important research field in image detection.

[0003] With the rapid development of the Internet, while the Internet brings convenience to people, it also produces a lot of bad information, especially pornographic pictures have a negative impact on young people. In the detection of pornographic images based on skin color, objects similar to skin color such as sandy beaches and wood grains are easily misjudged, but these texture detection can easily fi...

Examples

Embodiment 1

[0024] figure 1 The implementation flow of the Gabor feature-based skin texture detection method provided by Embodiment 1 of the present invention is shown, and the method process is described in detail as follows:

[0025] In step S101, the image to be detected is divided into a plurality of image blocks.

[0026] Exemplarily, in this embodiment, the image to be detected may be divided into image blocks with a size of 16*16.

[0027] It should be noted that since the texture feature is a feature that depends on the relationship with the surrounding pixels of the image, if the image block is too small, it will not reflect this cyclic feature, and the amount of calculation will increase greatly; if the image block is too large , an image block may contain both skin texture features and non-skin texture features, which will reduce the accuracy of skin texture feature detection. In this embodiment, after passing specific experiments, the image is preferably divided into image b...

Embodiment 2

[0093] image 3 The composition structure of the skin texture detection device based on Gabor features provided by Embodiment 2 of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown.

[0094] The skin texture detection device based on Gabor features can be a software unit, a hardware unit, or a combination of software and hardware running in the terminal device, or it can be integrated into the terminal device or run on the terminal device as an independent pendant in the application system.

[0095] The skin texture detection device based on Gabor features specifically includes:

[0096] The first image block division unit 31 is used to divide the image to be detected into a plurality of image blocks;

[0097] The first calculation unit 32 is used to convolve each color channel of each image block with a pre-established Gabor filter bank in the spatial domain to obtain k*s*r matrice...

Images