Character attribute identification method and device, computer equipment and storage medium

Abstract

The invention relates to artificial intelligence, and provides a character attribute identification method and device, computer equipment and a storage medium. The character attribute identification method comprises the steps of classifying to-be-identified character images according to an occlusion area to obtain image types of the to-be-identified character images; if the to-be-identified figureimage is an occlusion image, inputting the to-be-identified figure image and the image type into a multi-scale generative adversarial network, and generating a de-occlusion image of the to-be-identified figure image by the multi-scale generative adversarial network according to the image type; and inputting the de-occlusion image of the figure image to be identified into an attribute identification network for attribute identification. The method can effectively remove the shielding interference in the shielded figure image, recover useful information, and improve the image attribute recognition performance. In addition, the invention also relates to a blockchain technology, and the character attributes of the to-be-identified character image can be stored in the blockchain.

Description

technical field

[0001] The present invention relates to the field of artificial intelligence, in particular to a method, device, computer equipment and storage medium for identifying a person attribute. Background technique

[0002] An important application of image recognition is the identification of human attributes, such as the identification of a person's age, body shape, gender, upper body clothing and color, lower body clothing and color, etc. With the continuous development of deep learning, the performance of person attribute recognition has been significantly improved. However, in practical application scenarios (such as pedestrian monitoring scenes at traffic intersections), there are often problems that people are blocked, such as pedestrians blocking each other, vehicles blocking pedestrians, and so on. The occlusion of a person will not only lose some information, but also introduce certain interference, which makes it difficult for the existing person attribu...

Examples

Embodiment 1

[0078] figure 1 It is a flow chart of the method for identifying human attributes provided by Embodiment 1 of the present invention. The person attribute recognition method is applied to computer equipment. The person attribute recognition method recognizes the person attributes of the occluded person image.

[0079] The character attributes identified by the present invention may include age, body shape, gender, hairstyle, upper body clothing and color, lower body clothing and color, shoes and color, and the like.

[0080] The present invention can be applied to scenes such as smart communities and smart traffic, and is used to identify character attributes of occluded character images in the scene, thereby promoting the construction of smart cities.

[0081] like figure 1 As shown, the character attribute identification method includes:

[0082] 101. Classify images of persons to be recognized according to occlusion regions, and obtain image types of the images of person...

Embodiment 2

[0132] figure 2 It is a structural diagram of a person attribute identification device provided by Embodiment 2 of the present invention. The person attribute identification device 20 is applied to computer equipment. The person attribute identification device 20 identifies the person attributes that block the person image.

[0133] like figure 2 As shown, the person attribute identification device 20 may include an image classification module 201 , a de-occlusion module 202 , and an identification module 203 . The identification module 203 includes a feature extraction sub-module 2031 , a segmentation sub-module 2032 , a pooling sub-module 2033 , a screening sub-module 2034 , and an attribute classification sub-module 2035 .

[0134] The image classification module 201 is configured to classify the image of the person to be recognized according to the occlusion area, and obtain the image type of the image of the person to be recognized.

[0135] The image of the person to...

Embodiment 3

[0185] This embodiment provides a storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, implements the steps in the above embodiments of the method for recognizing personal attributes, for example figure 1 101-107 shown. Alternatively, when the computer program is executed by the processor, the functions of each module in the foregoing apparatus embodiment are implemented, for example, figure 2 in modules 201-203.

technical field

[0001] The present invention relates to the field of artificial intelligence, in particular to a method, device, computer equipment and storage medium for identifying a person attribute. Background technique

[0002] An important application of image recognition is the identification of human attributes, such as the identification of a person's age, body shape, gender, upper body clothing and color, lower body clothing and color, etc. With the continuous development of deep learning, the performance of person attribute recognition has been significantly improved. However, in practical application scenarios (such as pedestrian monitoring scenes at traffic intersections), there are often problems that people are blocked, such as pedestrians blocking each other, vehicles blocking pedestrians, and so on. The occlusion of a person will not only lose some information, but also introduce certain interference, which makes it difficult for the existing person attribu...

Examples

Embodiment 1

[0078] figure 1 It is a flow chart of the method for identifying human attributes provided by Embodiment 1 of the present invention. The person attribute recognition method is applied to computer equipment. The person attribute recognition method recognizes the person attributes of the occluded person image.

[0079] The character attributes identified by the present invention may include age, body shape, gender, hairstyle, upper body clothing and color, lower body clothing and color, shoes and color, and the like.

[0080] The present invention can be applied to scenes such as smart communities and smart traffic, and is used to identify character attributes of occluded character images in the scene, thereby promoting the construction of smart cities.

[0081] like figure 1 As shown, the character attribute identification method includes:

[0082] 101. Classify images of persons to be recognized according to occlusion regions, and obtain image types of the images of person...

Embodiment 2

[0132] figure 2 It is a structural diagram of a person attribute identification device provided by Embodiment 2 of the present invention. The person attribute identification device 20 is applied to computer equipment. The person attribute identification device 20 identifies the person attributes that block the person image.

[0133] like figure 2 As shown, the person attribute identification device 20 may include an image classification module 201 , a de-occlusion module 202 , and an identification module 203 . The identification module 203 includes a feature extraction sub-module 2031 , a segmentation sub-module 2032 , a pooling sub-module 2033 , a screening sub-module 2034 , and an attribute classification sub-module 2035 .

[0134] The image classification module 201 is configured to classify the image of the person to be recognized according to the occlusion area, and obtain the image type of the image of the person to be recognized.

[0135] The image of the person to...

Embodiment 3

[0185] This embodiment provides a storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, implements the steps in the above embodiments of the method for recognizing personal attributes, for example figure 1 101-107 shown. Alternatively, when the computer program is executed by the processor, the functions of each module in the foregoing apparatus embodiment are implemented, for example, figure 2 in modules 201-203.

Images