专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20200265308A1 MODEL OPTIMIZATION METHOD, DATA IDENTIFICATION METHOD AND DATA IDENTIFICATION DEVICE 审中-公开
公开(公告)号：US20200265308A1
公开(公告)日：2020-08-20
申请号：US16748107
申请日：2020-01-21
申请人： FUJITSU LIMITED
发明人： Mengjiao Wang , Rujie Liu
IPC分类号： G06N3/08 , G06N3/04
摘要： The present disclosure relates to a model optimization method, a data identification method and a data identification device. A method for optimizing a data identification model comprises: acquiring a loss function of a data identification model to be optimized; calculating weight vectors in the loss function which correspond to classes; performing normalization processing on the weight vectors; updating the loss function by increasing an included angle between any two of the weight vectors; optimizing the data identification model to be optimized based on the updated loss function.

2. 发明授权

US10552712B2 Training device and training method for training image processing device 有权
公开(公告)号：US10552712B2
公开(公告)日：2020-02-04
申请号：US15843719
申请日：2017-12-15
申请人： Fujitsu Limited
发明人： Wei Shen , Rujie Liu
IPC分类号： G06K9/62 , G06N3/08 , G06K9/00 , G06N3/04
摘要： The disclosure relates to a training device and method for an image processing device and an image processing device. The training device is used for training first and second image processing units, comprising: a training unit to input a first realistic image without a specific feature into the first image processing unit to generate a first generated image with the specific feature through first image processing, and to input a second realistic image with the specific feature into the second image processing unit to generate a second generated image without the specific feature through second image processing; and a classifying unit performing classification processing to discriminate realistic and generated images, wherein the training unit performs first training processing of training the classifying unit based on the realistic and generated images, and performs second training processing of training the first and second image processing units based on the training result.

3. 发明申请

US20190122394A1 IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD 审中-公开
公开(公告)号：US20190122394A1
公开(公告)日：2019-04-25
申请号：US16136940
申请日：2018-09-20
申请人： FUJITSU LIMITED
发明人： Wei SHEN , Rujie Liu
IPC分类号： G06T9/00 , G06N3/08 , G06N3/04 , H04N19/61
摘要： An image processing apparatus and an image processing method where the apparatus includes: a self-encoder configured to perform self-encoding on an input image to generate multiple feature maps; a parameter generator configured to generate multiple convolution kernels for a convolution neural network based on the multiple feature maps; and an outputter configured to generate, by using the convolution neural network, an output result of the input image based on the input image and the multiple convolution kernels. With the image processing apparatus and the image processing method according to the present disclosure, an accuracy of processing an image by using the CNN network can be improved.

4. 发明授权

US11514264B2 Method and apparatus for training classification model, and classification method 有权
公开(公告)号：US11514264B2
公开(公告)日：2022-11-29
申请号：US17076320
申请日：2020-10-21
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Fei Li , Rujie Liu
IPC分类号： G06K9/62 , G06N3/08
摘要： A method for training a classification model includes: performing training on the classification model using first and second sample sets, to calculate a classification loss; extracting a weight vector and a feature vector of each sample; calculating a mean weight vector and a mean feature vector of all samples in the first sample set; calculating a weight loss based on a difference of the weight vector of each sample in the second sample set from the mean weight vector, and calculating a feature loss based on a difference of a feature vector of each sample in the second sample set from the mean feature vector; calculating a total loss of the classification model based on the classification loss and at least one of the feature loss and the weight loss; and adjusting a parameter of the classification model until a predetermined condition is satisfied.

5. 发明申请

US20210150261A1 METHOD AND APPARATUS FOR TRAINING CLASSIFICATION MODEL, AND CLASSIFICATION METHOD 有权
公开(公告)号：US20210150261A1
公开(公告)日：2021-05-20
申请号：US17076320
申请日：2020-10-21
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Fei Li , Rujie Liu
IPC分类号： G06K9/62 , G06N3/08
摘要： A method for training a classification model includes: performing training on the classification model using first and second sample sets, to calculate a classification loss; extracting a weight vector and a feature vector of each sample; calculating a mean weight vector and a mean feature vector of all samples in the first sample set; calculating a weight loss based on a difference of the weight vector of each sample in the second sample set from the mean weight vector, and calculating a feature loss based on a difference of a feature vector of each sample in the second sample set from the mean feature vector; calculating a total loss of the classification model based on the classification loss and at least one of the feature loss and the weight loss; and adjusting a parameter of the classification model until a predetermined condition is satisfied.

6. 发明授权

US10776918B2 Method and device for determining image similarity 有权
公开(公告)号：US10776918B2
公开(公告)日：2020-09-15
申请号：US15816315
申请日：2017-11-17
申请人： Fujitsu Limited
发明人： Mengjiao Wang , Rujie Liu
IPC分类号： G06T7/00 , G06K9/62 , G06K9/46 , G06T7/11 , G06T7/136 , G06T7/13
摘要： The present application relates to method and device for determining image similarity that includes: dividing a target image into multiple regions based on positions of pixels relative to a reference point in the target image, and dividing a reference image into multiple regions based on positions of pixels relative to a reference point in the reference image; determining, based on feature points in the target image and feature points in the reference image as well as the regions obtained by dividing the target image and the regions obtained by dividing the reference image, similarity between a distribution of the feature points in the target image and a distribution of the feature points in the reference image. According to the method of the present application, the similarity is described more reasonably.

7. 发明授权

US10769499B2 Method and apparatus for training face recognition model 有权
公开(公告)号：US10769499B2
公开(公告)日：2020-09-08
申请号：US16179292
申请日：2018-11-02
申请人： FUJITSU LIMITED
发明人： Meng Zhang , Rujie Liu , Jun Sun
IPC分类号： G06K9/62 , G06K9/00
摘要： A method and apparatus for removing black eyepits and sunglasses in first actual scenario data having an image containing a face acquired from an actual scenario, to obtain second actual scenario data; counting a proportion of wearing glasses in the second actual scenario data; dividing original training data composed of an image containing a face into wearing-glasses and not-wearing-glasses first and second training data, where a proportion of wearing glasses in the original training data is lower than a proportion in the second actual scenario data; generating wearing-glasses third training data based on glasses data and the second training data; generating fourth training data in which a proportion of wearing glasses is equal to the proportion of wearing glasses in the second actual scenario data, based on the third training data and the original training data; and training a face recognition model based on the fourth training data.

8. 发明授权

US10410345B2 Image processing device and image processing method 有权
公开(公告)号：US10410345B2
公开(公告)日：2019-09-10
申请号：US15827570
申请日：2017-11-30
申请人： Fujitsu Limited
发明人： Mengjiao Wang , Rujie Liu
IPC分类号： G06T7/00 , G06T7/187 , G06T7/11 , G06T7/174
摘要： An image processing device and an image processing method are provided. The image processing device includes: an acquisitor configured to acquire multiple slice images arranged in an order; a selector configured to detect the multiple slice images sequentially, to determine a reference slice image and a reference trachea region in the reference slice image; and a branch point determiner configured to determine, with a region growing method, trachea regions of slice images following the reference slice image sequentially by using the reference trachea region as a seed region, and determine connectivity of the trachea regions, until a branch point slice image is determined, where a trachea region of the branch point slice image includes two disconnected regions. With the image processing device and the image processing method, manual intervention can be reduced and a position of the branch point can be determined more accurately.

9. 发明申请

US20180240232A1 IMAGE PROCESSING DEVICE AND IMAGE PROCESSING METHOD 审中-公开
公开(公告)号：US20180240232A1
公开(公告)日：2018-08-23
申请号：US15827570
申请日：2017-11-30
申请人： Fujitsu Limited
发明人： Mengjiao WANG , Rujie Liu
IPC分类号： G06T7/00 , G06T7/187
CPC分类号： G06T7/0012 , G06T7/11 , G06T7/174 , G06T7/187 , G06T2207/10081 , G06T2207/20156 , G06T2207/30061
摘要： An image processing device and an image processing method are provided. The image processing device includes: an acquisitor configured to acquire multiple slice images arranged in an order; a selector configured to detect the multiple slice images sequentially, to determine a reference slice image and a reference trachea region in the reference slice image; and a branch point determiner configured to determine, with a region growing method, trachea regions of slice images following the reference slice image sequentially by using the reference trachea region as a seed region, and determine connectivity of the trachea regions, until a branch point slice image is determined, where a trachea region of the branch point slice image includes two disconnected regions. With the image processing device and the image processing method, manual intervention can be reduced and a position of the branch point can be determined more accurately.

10. 发明授权

US09483818B2 Bleed-through detection method and bleed-through detection apparatus 有权
标题翻译：渗透检测方法和渗透检测装置
公开(公告)号：US09483818B2
公开(公告)日：2016-11-01
申请号：US14584153
申请日：2014-12-29
申请人： FUJITSU LIMITED
发明人： Qiong Cao , Rujie Liu
IPC分类号： G06T7/00
CPC分类号： G06T7/0002 , G06T2207/30168 , G06T2207/30176
摘要： The present invention discloses a bleed-through detection method and a bleed-through detection device. The method includes: obtaining a recto image and a verso image, thereby obtaining pixel pairs including the first points and the corresponding second points; determining some foreground pixels and some background pixels; performing modeling for four types of pixel pairs, so as to form four models; calculating, for a pixel pair that hasn't been modeled, similarities of the pixel pair with respect to the four models respectively, so as to determine a type of the pixel pair; and judging, as bleed-through on the verso image, a second point determined as a background pixel which corresponds to a first point determined as a foreground pixel, and judging, as bleed-through on the recto image, a first point determined as a background pixel which corresponds to a second point determined as a foreground pixel.
摘要翻译：本发明公开了一种渗漏检测方法和渗透检测装置。该方法包括：获得直角图像和二维图像，从而获得包括第一点和对应的第二点的像素对; 确定一些前景像素和一些背景像素; 对四种像素对执行建模，从而形成四个模型; 对于尚未建模的像素对，分别计算像素对相对于四个模型的相似度，以便确定像素对的类型; 并且作为所述通配图像上的渗透判断为被确定为对应于被确定为前景像素的第一点的背景像素的第二点，并且将作为所述正射图像上的渗透判断为被确定为对应于被确定为前景像素的第二点的背景像素。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式