Patents by Inventor Jinghong Miao
Jinghong Miao has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11361189Abstract: An image generation method and a computing device employing the method includes: acquiring a plurality of original images; and processing the plurality of original images to obtain a training data set. An anti-neural network model is trained according to the training data set. A candidate image is generated through the trained anti-neural network model. The candidate image is complemented through a detail completion network model to obtain a target image according to a comparison image. Thereby, a style of the generated image is the same as that of the comparison image. A more realistic image can be randomly generated saving the time and energy of artificially creating an image.Type: GrantFiled: December 3, 2019Date of Patent: June 14, 2022Assignee: Ping An Technology (Shenzhen) Co., Ltd.Inventors: Yuchuan Gou, Jinghong Miao, Ruei-Sung Lin, Bo Gong, Mei Han
-
Patent number: 11176371Abstract: An environment monitoring method and an electronic device are provided, the method divides the satellite image into a plurality of first divided images with overlapping areas, a first multi-dimensional feature map is obtained by inputting the plurality of first divided images into an environment monitoring model, the environmental monitoring model fully combines the correlation between the environmental information of different dimensions, the environmental features of a plurality of different dimensions are correlated through an association network. By utilizing the environment monitoring method, a large area of the environment monitoring effectively is realized, and accuracy of environmental detection is improved.Type: GrantFiled: December 26, 2019Date of Patent: November 16, 2021Assignee: Ping An Technology (Shenzhen) Co., Ltd.Inventors: Xi Yao, Qi Chen, Ruei-Sung Lin, Bo Gong, Yi Zhao, Mei Han, Jinghong Miao
-
Patent number: 11120595Abstract: In a face swap method carried out by an electronic device, a first head image is segmented from a destination image. First facial landmarks and a first hair mask are obtained according to the first head image. A second head image is segmented from a source image. Second facial landmarks and a second hair mask are obtained according to the second head image. If at least one eye landmark in the second facial landmarks is covered by hair, the second head image and the second hair mask are processed and repaired so as to obtain a swapped-face image with eyes not covered by hair.Type: GrantFiled: December 27, 2019Date of Patent: September 14, 2021Assignee: Ping An Technology (Shenzhen) Co., Ltd.Inventors: Jinghong Miao, Yuchuan Gou, Minghao Li, Jui-Hsin Lai, Bo Gong, Mei Han
-
Patent number: 11080834Abstract: An image processing method and an electronic device are provided, the method extracts a first object mask of a texture image and a second object mask of a to-be-optimized image. An image recognition model is used to obtain a first content matrix, a first texture matrix, a second content matrix, a second texture matrix, a first mask matrix, and a second mask matrix. A total loss of the to-be-optimized image is determined, and the total loss is minimized by adjusting a value of each pixel of the to-be-optimized image, thereby an optimized image is obtained. By utilizing the image processing method, quality of final image is improved.Type: GrantFiled: December 26, 2019Date of Patent: August 3, 2021Assignee: Ping An Technology (Shenzhen) Co., Ltd.Inventors: Jinghong Miao, Yuchuan Gou, Bo Gong, Mei Han
-
Patent number: 11062504Abstract: A method for generating a model for facial sculpture based on a generative adversarial network (GAN) includes training a predetermined GAN based on a three dimensional (3D) face dataset of multiple 3D face images to obtain an initial sculpture generation model. A curvature conversion on each of the multiple 3D face images is performed to obtain a distribution map of curvature value and the distribution map of curvature value of each of the multiple 3D face images is added as attention information to the initial sculpture generation model, to train and generate a face sculpture generation model. A target 3D face data and predetermined face curvature parameters are received, and the target 3D face data and the predetermined face curvature parameters are inputted into the face sculpture generation model to generate a face sculpture model. A computing device using the method is also provided.Type: GrantFiled: December 27, 2019Date of Patent: July 13, 2021Assignee: Ping An Technology (Shenzhen) Co., Ltd.Inventors: Minghao Li, Jinghong Miao, Yuchuan Gou, Bo Gong, Mei Han
-
Publication number: 20210201544Abstract: In a face swap method carried out by an electronic device, a first head image is segmented from a destination image. First facial landmarks and a first hair mask are obtained according to the first head image. A second head image is segmented from a source image. Second facial landmarks and a second hair mask are obtained according to the second head image. If at least one eye landmark in the second facial landmarks is covered by hair, the second head image and the second hair mask are processed and repaired so as to obtain a swapped-face image with eyes not covered by hair.Type: ApplicationFiled: December 27, 2019Publication date: July 1, 2021Inventors: Jinghong Miao, Yuchuan Gou, Minghao Li, Jui-Hsin Lai, Bo Gong, Mei Han
-
Publication number: 20210201564Abstract: A method for generating a model for facial sculpture based on a generative adversarial network (GAN) includes training a predetermined GAN based on a three dimensional (3D) face dataset of multiple 3D face images to obtain an initial sculpture generation model. A curvature conversion on each of the multiple 3D face images is performed to obtain a distribution map of curvature value and the distribution map of curvature value of each of the multiple 3D face images is added as attention information to the initial sculpture generation model, to train and generate a face sculpture generation model. A target 3D face data and predetermined face curvature parameters are received, and the target 3D face data and the predetermined face curvature parameters are inputted into the face sculpture generation model to generate a face sculpture model. A computing device using the method is also provided.Type: ApplicationFiled: December 27, 2019Publication date: July 1, 2021Inventors: Minghao Li, Jinghong Miao, Yuchuan Gou, Bo Gong, Mei Han
-
Publication number: 20210201456Abstract: An image processing method and an electronic device are provided, the method extracts a first object mask of a texture image and a second object mask of a to-be-optimized image. An image recognition model is used to obtain a first content matrix, a first texture matrix, a second content matrix, a second texture matrix, a first mask matrix, and a second mask matrix. A total loss of the to-be-optimized image is determined, and the total loss is minimized by adjusting a value of each pixel of the to-be-optimized image, thereby an optimized image is obtained. By utilizing the image processing method, quality of final image is improved.Type: ApplicationFiled: December 26, 2019Publication date: July 1, 2021Inventors: Jinghong Miao, Yuchuan Gou, Bo Gong, Mei Han
-
Publication number: 20210200981Abstract: An environment monitoring method and an electronic device are provided, the method divides the satellite image into a plurality of first divided images with overlapping areas, a first multi-dimensional feature map is obtained by inputting the plurality of first divided images into an environment monitoring model, the environmental monitoring model fully combines the correlation between the environmental information of different dimensions, the environmental features of a plurality of different dimensions are correlated through an association network. By utilizing the environment monitoring method, a large area of the environment monitoring effectively is realized, and accuracy of environmental detection is improved.Type: ApplicationFiled: December 26, 2019Publication date: July 1, 2021Inventors: Xi Yao, Qi Chen, Ruei-Sung Lin, Bo Gong, Yi Zhao, Mei Han, Jinghong Miao
-
Patent number: 11048971Abstract: In a method for training an image generation model, a first generator generates a first sample matrix, a first converter generates a sample contour image, a first discriminator optimizes the first generator and the first converter, a second generator generates a second sample matrix according to the first sample matrix, a second converter generates a first sample grayscale image, a second discriminator optimizes the second generator and the second converter, a third generator generates a third sample matrix according to the second sample matrix, a third converter generates a second sample grayscale image, a third discriminator optimizes the third generator and the third converter, a fourth generator generates a fourth sample matrix according to the third sample matrix, a fourth converter generates a sample color image, and a fourth discriminator optimizes the fourth generator and the fourth converter. The image generation model can be trained easily.Type: GrantFiled: December 24, 2019Date of Patent: June 29, 2021Assignee: Ping An Technology (Shenzhen) Co., Ltd.Inventors: Jinghong Miao, Bo Gong, Mei Han
-
Publication number: 20210192275Abstract: In a method for training an image generation model, a first generator generates a first sample matrix, a first converter generates a sample contour image, a first discriminator optimizes the first generator and the first converter, a second generator generates a second sample matrix according to the first sample matrix, a second converter generates a first sample grayscale image, a second discriminator optimizes the second generator and the second converter, a third generator generates a third sample matrix according to the second sample matrix, a third converter generates a second sample grayscale image, a third discriminator optimizes the third generator and the third converter, a fourth generator generates a fourth sample matrix according to the third sample matrix, a fourth converter generates a sample color image, and a fourth discriminator optimizes the fourth generator and the fourth converter. The image generation model can be trained easily.Type: ApplicationFiled: December 24, 2019Publication date: June 24, 2021Inventors: Jinghong Miao, Bo Gong, Mei Han
-
Publication number: 20210166073Abstract: An image generation method and a computing device employing the method includes: acquiring a plurality of original images; and processing the plurality of original images to obtain a training data set. An anti-neural network model is trained according to the training data set. A candidate image is generated through the trained anti-neural network model. The candidate image is complemented through a detail completion network model to obtain a target image according to a comparison image. Thereby, a style of the generated image is the same as that of the comparison image. A more realistic image can be randomly generated saving the time and energy of artificially creating an image.Type: ApplicationFiled: December 3, 2019Publication date: June 3, 2021Inventors: Yuchuan Gou, Jinghong Miao, Ruei-Sung Lin, Bo Gong, Mei Han
-
Publication number: 20210166058Abstract: An image generation method and a computing device using the method, includes creating an image database with a plurality of original images, and obtaining a plurality of first outline images of an object by detecting an outline of the object in each of the original images. Numerous first feature matrixes are obtained by calculating a feature matrix of each of the first outline images. A second feature matrix of a second outline image input by a user is calculated. A target feature matrix is selected from the plurality of first feature matrixes, the target feature matrix has a minimum difference as the second feature matrix. A target image corresponding to the target feature matrix is matched and displayed from the image database. The method and device allow detection of an object outline in an image input by users and the generation of an image with the detected outline.Type: ApplicationFiled: December 3, 2019Publication date: June 3, 2021Inventors: Jinghong Miao, Yuchuan Gou, Ruei-Sung Lin, Bo Gong, Mei Han
-
Patent number: 10991154Abstract: A method for generating a model for facial sculpture based on a generative adversarial network (GAN) includes training a predetermined GAN based on a three-dimensional (3D) face dataset of multiple 3D face images to obtain a curvature map generation model and training a predetermined image translation model based on dataset of multiple image pairs to obtain a height map generation model. Target 3D face data is received, and the target 3D face data is inputted into the curvature map generation model to generate a target curvature map, and the target curvature map is inputted to the height map generation model to generate a target height map. The target height map is performed a 3D reconstruction to obtain a facial sculpture model corresponding to the target 3D face data. A computing device using the method is also provided.Type: GrantFiled: December 27, 2019Date of Patent: April 27, 2021Assignee: Ping An Technology (Shenzhen) Co., Ltd.Inventors: Minghao Li, Jinghong Miao, Yuchuan Gou, Bo Gong, Mei Han