-
公开(公告)号：US11257255B2
公开(公告)日：2022-02-22
申请号：US16702294
申请日：2019-12-03
发明人： Shih-Jong James Lee , Hideki Sasaki
摘要： A computerized domain matching image conversion method for transportable imaging applications first performs a target domain A to source domain B matching converter training by computing means using domain B training images and at least one domain A image to generate an A to B domain matching converter. The method then applies the A to B domain matching converter to a domain A application image to generate its domain B matched application image. The method further applies a domain B imaging application analytics to the domain B matched application image to generate an imaging application output for the domain A application image.
-
公开(公告)号：US11373066B2
公开(公告)日：2022-06-28
申请号：US16416115
申请日：2019-05-17
发明人： Shih-Jong James Lee , Hideki Sasaki
IPC分类号： G06K9/62 , G06N3/04 , G06K9/00 , G06V30/194
摘要： A computerized method of deep model matching for image transformation includes inputting pilot data and pre-trained deep model library into computer memories; performing a model matching scoring using the pilot data and the pre-trained deep model library to generate model matching score; and performing a model matching decision using the model matching score to generate a model matching decision output. Additional pilot data may be used to perform the model matching scoring and the model matching decision iteratively to obtain improved model matching decision output. Alternatively, the pre-trained deep model library may be pre-trained deep adversarial model library in the method.
-
公开(公告)号：US11797337B2
公开(公告)日：2023-10-24
申请号：US17000174
申请日：2020-08-21
CPC分类号： G06F9/4881 , G06F9/3005 , G06F9/5061
摘要： A computerized efficient data processing management method for imaging applications first performs a data flow graph generation by computing means using at least one image data and at least one requested task to generate a data flow graph. The method then applies a task execution scheduling using the data flow graph generated, a caching system configuration, the at least one image data and at least one requested task to schedule execution of the at least one requested task to generate task execution output. In addition, an adaptive data processing method performs caching system update and an optimal data processing method further performs data flow graph update.
-
公开(公告)号：US11508051B2
公开(公告)日：2022-11-22
申请号：US16894708
申请日：2020-06-05
发明人： Shih-Jong James Lee , Hideki Sasaki
摘要： A computerized model compatibility regulation method for imaging applications first performs a target domain B application by computing means using at least one image X and target domain B image analytics to generate a target domain B application output for X. The method then applies a reference domain A application by computing means to generate reference domain A application output for X. The method further performs a compatibility assessment to generate at least one compatibility result for X. In addition, the method checks the compatibility result for X and if the check output is incompatible, the method performs online correction to generate a corrected application output for X.
-
公开(公告)号：US20220058052A1
公开(公告)日：2022-02-24
申请号：US17000174
申请日：2020-08-21
摘要： A computerized efficient data processing management method for imaging applications first performs a data flow graph generation by computing means using at least one image data and at least one requested task to generate a data flow graph. The method then applies a task execution scheduling using the data flow graph generated, a caching system configuration, the at least one image data and at least one requested task to schedule execution of the at least one requested task to generate task execution output. In addition, an adaptive data processing method performs caching system update and an optimal data processing method further performs data flow graph update.
-
公开(公告)号：US11468286B2
公开(公告)日：2022-10-11
申请号：US15609000
申请日：2017-05-30
发明人： Shih-Jong James Lee , Hideki Sasaki
摘要： A computerized prediction guided learning method for classification of sequential data performs a prediction learning and a prediction guided learning by a computer program of a computerized machine learning tool. The prediction learning uses an input data sequence to generate an initial classifier. The prediction guided learning may be a semantic learning, an update learning, or an update and semantic learning. The prediction guided semantic learning uses the input data sequence, the initial classifier and semantic label data to generate an output classifier and a semantic classification. The prediction guided update learning uses the input data sequence, the initial classifier and label data to generate an output classifier and a data classification. The prediction guided update and semantic learning uses the input data sequence, the initial classifier and semantic and label data to generate an output classifier, a semantic classification and a data classification.
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.015 秒)
