-
公开(公告)号：US20240126508A1
公开(公告)日：2024-04-18
申请号：US18074245
申请日：2022-12-02
发明人： Tay-Jyi LIN
CPC分类号： G06F7/523 , G06F7/50 , G06F7/5443
摘要： A device for computing an inner product includes a data memory, an inverted index memory (IIM), a weight mapping table, a controller, a pre-accumulator, and a multiplier-accumulate (MAC) module. The data memory stores data groups. Each data group includes data values. The IIM stores a data address and a corresponding weight index value of each data group in the data memory. The weight mapping table stores a weight value corresponding to the weight index value. The controller and the IIM drive the data memory to sequentially output the data values of the data groups and drive the mapping table to sequentially output weight values. The pre-accumulator accumulates the data values of each data group to generate accumulation values. The MAC module computes the accumulation and the weight value that correspond to each data group based on a distributive law, thereby generating an inner product value.
-
公开(公告)号：US11810300B2
公开(公告)日：2023-11-07
申请号：US17394724
申请日：2021-08-05
发明人： Hsiang-Chen Wang , Tsung-Yu Yang , Yu-Sheng Chi , Ting-Chun Men
CPC分类号： G06T7/0014 , G06T3/40 , G06V10/754 , G06V10/76 , G06T2207/10036 , G06T2207/30096
摘要： This application provides a method for detecting images of testing object using hyperspectral imaging. Firstly, obtaining a hyperspectral imaging information according to a reference image, hereby, obtaining corresponded hyperspectral image from an input image and obtaining corresponded feature values for operating Principal components analysis to simplify feature values. Then, obtaining feature images by Convolution kernel, and then positioning an image of an object under detected by a default box and a boundary box from the feature image. By Comparing with the esophageal cancer sample image, the image of the object under detected is classifying to an esophageal cancer image or a non-esophageal cancer image. Thus, detecting an input image from the image capturing device by the convolutional neural network to judge if the input image is the esophageal cancer image for helping the doctor to interpret the image of the object under detected.
-
公开(公告)号：US11777225B2
公开(公告)日：2023-10-03
申请号：US17171342
申请日：2021-02-09
CPC分类号： H01Q15/148 , H01Q15/0086 , H01Q15/147
摘要： A method of manufacturing an electromagnetic wave reflecting structure includes the steps of presetting an operating frequency, a reflected wave pointing angle, an incident wave pointing angle, and an incident distance of an electromagnetic wave; obtaining an electromagnetic wave reflecting structure phase distribution of an electromagnetic wave reflecting structure according to the operating frequency, the reflected wave pointing angle, the incident wave pointing angle, and the incident distance; and arranging a plurality of reflecting elements on a substrate according to the electromagnetic wave reflecting structure phase distribution and a reflecting element phase curve of any one of the reflecting elements at the operating frequency.
-
公开(公告)号：US20230282010A1
公开(公告)日：2023-09-07
申请号：US18162077
申请日：2023-01-31
发明人： HSIANG-CHEN WANG , KUAN-LIN CHEN , YU-MING TSAO , JEN-FENG HSU
CPC分类号： G06V20/70 , G06V10/82 , G06V10/7715 , G06V10/764 , G06V10/751 , G06V10/26 , G06V2201/03
摘要： The present application discloses a method for detecting image by using semantic segmentation. To input an image with data augmentation, and then encode and decode using a neural network. At least one semantically divided, and finally the at least one semantically divided is compared with the sample to classify as a target or a non-target. In this way, the CNN is used to detect whether the image is the SCC image or not, and locate the section, thereby assisting the doctor in interpreting the esophagus image.
-
公开(公告)号：US20230281962A1
公开(公告)日：2023-09-07
申请号：US18165586
申请日：2023-02-07
发明人： HSIANG-CHEN WANG , TING-CHUN MEN , YU-MING TSAO , YU-LIN LIU
CPC分类号： G06V10/7715 , G06V10/751 , G06V10/82
摘要： A method for detecting objects in hyperspectral imaging is revealed. First obtaining a hyperspectral imaging information by a reference image. Then converting an input image according to the hyperspectral imaging information to get a hyperspectral image. A plurality of hyperspectral eigenvalues is obtained after image analysis of the hyperspectral image. Next getting a plurality of dimensionality reduction eigenvalues by a principal component analysis (PCA). Then performing convolution operation on the dimensionality reduction eigenvalues to get a value of a convolution matrix for extracting a feature image from an image of an object to be detected in the input image. Generating an anchor box and a prediction box in the feature image to get a bounded image. Lastly matching and comparing the bounded image with a sample image to determine whether the input image is a target object image. Thereby the method provides assistance for physicians in gastrointestinal image diagnosis.
-
公开(公告)号：US11741968B2
公开(公告)日：2023-08-29
申请号：US17475903
申请日：2021-09-15
发明人： Tay Jyi Lin , Yu Chia Hu , Yi-Hsuan Ting , Ching Wei Yeh , Jinn-Shyan Wang
摘要： A personalized voice conversion system includes a cloud server and an intelligent device that communicates with the cloud server. The intelligent device upstreams an original voice signal to the cloud server. The cloud server converts the original voice signal into an intelligible voice signal based on an intelligible voice conversion model. The intelligent device downloads and plays the intelligible voice signal. Based on the original voice signal and the corresponding intelligible voice signal, the cloud server and the intelligent device train an off-line voice conversion model provided to the intelligent device. When the intelligent device stops communicating with the cloud server, the intelligent device converts a new original voice signal into a new intelligible voice signal based on the off-line voice conversion model and plays the new intelligible voice signal.
-
公开(公告)号：US20230154049A1
公开(公告)日：2023-05-18
申请号：US17729228
申请日：2022-04-26
发明人： Hsiang-Chen WANG , Yu-Ming TSAO , Yu-Lin LIU
CPC分类号： G06T7/90 , G06F17/18 , G06T2207/10024 , G06T2207/10036 , G06T2207/20081
摘要： A method of measuring chromaticity of a target object is implemented using a computer device that stores a plurality of light source spectrum datasets each associated with a specific object. The method includes: obtaining a captured color image of the target object; generating a spectral image based on the captured color image using a spectral transformation matrix; obtaining one of the plurality of light source spectrum datasets that is associated with the target object; and calculating a chromaticity dataset of the target object based on the spectral image and the one of the plurality of light source spectrum datasets.
-
公开(公告)号：US20230074722A1
公开(公告)日：2023-03-09
申请号：US17508768
申请日：2021-10-22
发明人： Jinn Shyan WANG , Chien Tung LIU , Chih Jung LIU
IPC分类号： G11C11/419
摘要： A memory device and an operation method thereof is disclosed. The memory device includes a SRAM cell and a power supply assist circuit connected to the SRAM cell. The power supply assist circuit includes a first transistor, a second transistor, a third transistor, a fourth transistor, and a fifth transistor. The first transistor receives a power supply voltage. The control terminals of the first transistor and the second transistor are connected to each other. The third transistor switches, in response to a first control signal, to connect the control terminal and the connect terminal of the second transistor. The fourth transistor switches, in response to a second control signal, to drive the control terminal of the second transistor to a system ground voltage. The fifth transistor switches, in response to a third control signal, to drive the control terminal of the first transistor to the power supply voltage.
-
公开(公告)号：US20230026329A1
公开(公告)日：2023-01-26
申请号：US17475903
申请日：2021-09-15
发明人： Tay Jyi LIN , Yu Chia HU , Yi-Hsuan TING , Ching Wei YEH , Jinn-Shyan WANG
摘要： A personalized voice conversion system includes a cloud server and an intelligent device that communicates with the cloud server. The intelligent device upstreams an original voice signal to the cloud server. The cloud server converts the original voice signal into an intelligible voice signal based on an intelligible voice conversion model. The intelligent device downloads and plays the intelligible voice signal. Based on the original voice signal and the corresponding intelligible voice signal, the cloud server and the intelligent device train an off-line voice conversion model provided to the intelligent device. When the intelligent device stops communicating with the cloud server, the intelligent device converts a new original voice signal into a new intelligible voice signal based on the off-line voice conversion model and plays the new intelligible voice signal.
-
公开(公告)号：US20230022594A1
公开(公告)日：2023-01-26
申请号：US17707211
申请日：2022-03-29
发明人： Chien-Yen CHEN , Yi-Hsun HUANG , Pin-Yun LIN , Wei-Fan YE
摘要： A method for producing photocatalytic mortar includes providing a mortar-producing material including a fine aggregate and cement, a reactant mixture including a zinc source and urea, and a microorganism-containing mixture including water and a urease-producing microorganism, subjecting the microorganism-containing mixture and the reactant mixture to microbial induced precipitation in the mortar-producing material, subjecting zinc carbonate crystal-containing mortar produced to curing for the same to undergo hydration, and subjecting cured mortar to hydrothermal synthesis, so that zinc carbonate crystals therein are converted to nano zinc oxide crystals.
-
-
-
-
-
-
-
-
-
搜索结果
370 条记录 (耗时 0.029 秒)
