Face portrait synthesis method based on directional graph model
A face portrait and synthesis method technology, applied in the field of image processing, can solve the problems of face portrait detail distortion, ignore domain constraints, increase the complexity of face portrait, etc., achieve the effect of obvious details and overcome the inconspicuous details
Active Publication Date: 2018-11-30
XIDIAN UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The disadvantage of this type of method is that the method of linear combination can be regarded as filtering by a low-pass filter, which will filter out some high-frequency detail information, resulting in distortion of the details of the final synthesized face image.
But this method ignores domain constraints, and it is a two-step framework, which increases the complexity of face portrait synthesis
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
[0020] refer to figure 1 , the implementation steps of the present invention are as follows:
[0021] Step 1, divide training portrait sample set, training photo sample set and test sample set.
[0022] Take L portraits from the portrait-photo pair set to form a training portrait sample set T R , and take out the training portrait sample set T R One-to-one correspondence of the portraits in L photos constitutes the training photo sample set T E , the remaining portrait-photo pairs form a test sample set, and a test photo A is selected from the test sample set.
[0023] Step 2, divide the portraits in the training portrait sample set and the photos in the training photo sample set into blocks.
[0024] The training image sample set T R The portrait and training photo sample set T in E The photos in are divided into overlapping blocks of the same size.
[0025] Step 3, forming a set of photo blocks to be selected and a set of portrait blocks to be selected.
[0026] Acco...
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 invention discloses a face image synthesis method based on a direction diagram model, which mainly solves the problem that the details of the face image synthesis are not obvious in the existing method. Its realization steps are: (1) dividing training portrait sample set, training photo sample set and test photo sample set; (2) carrying out block division to the portrait in training portrait sample set, the photo in training photo sample set and test photo; (3) ) According to the divided image blocks, photo block sets to be selected and image block sets to be selected are formed; (4) pixel value features and direction features are extracted to training portraits and photo sample block sets; (5) image block weight sets to be selected are calculated; (6) Calculating a pseudo portrait block set according to the weight value set of the portrait blocks to be selected; (7) Generating a pseudo portrait according to the pseudo portrait block set. Because the present invention considers the domain constraint of the human face image itself, the detailed parts of the generated human face portrait are obvious, and can be used for human face retrieval and recognition in the field of public security.
Description
technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a face portrait synthesis method, which can be used for face retrieval and recognition in the field of public security. Background technique [0002] Face-based identification technology is one of the most convenient and effective identification technologies in public security management. For example, in the case of criminal investigation, when it is difficult to obtain photos of the suspect due to objective reasons, the forensic doctor can draw a portrait of the suspect based on the description of the witnesses. However, due to the different imaging principles of photos and portraits, there are large differences in shape and texture, which brings many difficulties to face recognition based on portraits. Face portrait synthesis technology is to convert the photos in the police face database into fake portraits through image processing technology, and then th...
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): G06T5/50G06K9/00G06K9/62
CPCG06T5/50G06T2207/10004G06T2207/20212G06V40/161G06V40/172G06F18/23213
Inventor 高新波张宇航王楠楠李洁孙雷雨朱明瑞于昕晔彭春蕾马卓奇曹兵查文锦
Owner XIDIAN UNIV