Portrait processing method, device, system and readable storage medium
A processing method and portrait technology, applied in the field of image processing, can solve problems such as insufficient stability, high subjectivity in labeling aesthetic scores, unreasonable calculation of aesthetic scores, etc., and achieve the effect of accurate target cropping frame, reasonable and stable calculation method
Active Publication Date: 2021-10-12
MEGVII BEIJINGTECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, since the above-mentioned deep learning model is generally trained by the loss between the labeled aesthetic score and the predicted aesthetic score of the training sample image, and the labeled aesthetic score has a large subjectivity, the calculation of the above aesthetic score is not reasonable enough. , not stable enough, resulting in the target cropping frame obtained based on the above image cropping method is often not accurate enough
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0091] In order to make the purpose, technical solutions and advantages of the present application, the present application will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended to explain the present application and is not intended to limit the present application.
[0092] The portrait method provided by the present application, but it is not limited to, figure 1 The application environment is shown. The photographing device 12 can acquire the object to be processed to be identified, and transmit the person to the computer device 11; the computer device 11 can generate a plurality of candidate cutters to be processed according to the portrait of the port, and calculate each candidate The aesthetic score of cropping frame, as well as the aesthetic score based on the candidate shears, and selects at least one candidate shears as the target crop frame. A...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present application relates to a portrait processing method, device, system and readable storage medium. The method includes: obtaining a portrait to be processed, and generating a plurality of candidate cropping frames of the portrait to be processed; inputting the portrait to be processed into a skeleton detection network model for skeleton detection processing, and obtaining the skeleton node positions of the portrait to be processed; and according to each candidate cropping frame and the position of the skeleton node, calculate the first-class aesthetic quantization value of each candidate cropping frame; perform cropping processing on the portrait to be processed according to each candidate cropping frame, and obtain each candidate cropping image of the portrait to be processed; and input each candidate cropping image into the aesthetic network model to obtain the second type of aesthetic quantization value of each candidate cropping frame; according to the first type of aesthetic quantization value and / or the second type of aesthetic quantization value of each candidate cropping frame, select at least one candidate cropping frame as the target of the portrait to be processed crop box. The target cropping frame obtained by this method is often more accurate.
Description
Technical field [0001] The present application relates to the field of image processing, in particular to a portrait processing method, device, system, and readable storage medium. Background technique [0002] Based on the pursuit of beauty, people typically cut the image, to enhance the composition effect of the image, so that the beauty of the image obtained after cropping increases, and the body is more prominent. [0003] In recent years, there are many studies to try to treat images with deep learning. Illustratively, some candidate cuttingbacks can be obtained according to different aspect ratios, and the processing image is cropped based on each candidate cutfrinter to obtain each candidate cut image; then based on the depth learning model to extract each The image features of the candidate crop image are characterized according to the image features of each candidate cut image, and the aesthetic score of each candidate cut image is calculated, and the candidate cutting f...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06K9/00
CPCG06V40/20G06F18/23G06F18/214
Inventor 牛然森
Owner MEGVII BEIJINGTECH CO LTD