-
公开(公告)号：US10405052B2
公开(公告)日：2019-09-03
申请号：US15956492
申请日：2018-04-18
Inventor： Mei Jiang , Hailong Liu , Jian Liu , Bo Chen
IPC: H04N21/482 , H04N21/414 , H04N21/4363 , H04N21/44 , H04N21/81
Abstract: A digital video conversion device is communicatively coupled to a TV set and a TV signal source, respectively, to pass TV signals from the TV signal source to the TV set. Upon receipt of a TV channel identification request from a mobile terminal via a wireless communication channel, the digital video conversion device acquires an image from the TV signals currently broadcasted on the TV set and extracts a plurality of station logo characteristic sets from the image, each station logo characteristic set corresponding to one of a plurality of station logo templates. After calculating a similarity score between each station logo characteristic set and a corresponding station logo template, the digital video conversion device identifies one of the plurality of station logo templates as matching the image based on their similarity scores and returns TV channel information associated with the identified station logo template to the mobile terminal.
-
公开(公告)号：US12272116B2
公开(公告)日：2025-04-08
申请号：US17728762
申请日：2022-04-25
Inventor： Yugeng Lin , Dianping Xu , Bolun Cai , Yanhua Cheng , Chen Ran , Minhui Wu , Mei Jiang , Yike Liu , Lijian Mei , Huajie Huang , Xiaoyi Jia , Jinchang Xu , Zhikang Tan , Haoyu Li
IPC: G06V10/74 , G06F16/55 , G06F16/56 , G06F16/58 , G06T7/00 , G06V10/26 , G06V10/764 , G06V30/148 , G06V30/19
Abstract: A method includes: obtaining a first image including a target item; selecting a plurality of reference images corresponding to the first image from a database; performing word segmentation on item text information corresponding to the plurality of reference images to obtain a plurality of words; and extracting a key word meeting a reference condition from the plurality of words, and determining the extracted key word as an item name of the target item.
-
3.发明授权公开(公告)号：US11790198B2
公开(公告)日：2023-10-17
申请号：US17968732
申请日：2022-10-18
Inventor： Jie Miao , Chen Ran , Dianping Xu , Xiaoyi Jia , Mei Jiang , Yugeng Lin
CPC classification number: G06K7/1417 , G06K19/06037
Abstract: A method for processing an encoded pattern, a storage medium, and an electronic device are disclosed in this application. An electronic device acquires a first encoded pattern to be recognized, the first encoded pattern being a pattern including predefined information encoded therein. The electronic device increases resolution of the first encoded pattern through a target model to obtain a target encoded pattern having a target resolution and corrects an edge of a sub-pattern in the target encoded pattern to obtain a second encoded pattern. Finally, the electronic device decodes the second encoded pattern using a code recognition module to obtain the predefined information. This application resolves the technical problem that an encoded pattern cannot be accurately recognized.
-
4.发明授权公开(公告)号：US11710293B2
公开(公告)日：2023-07-25
申请号：US17020636
申请日：2020-09-14
Inventor： Jie Miao , Chen Ran , Dianping Xu , Xiaoyi Jia , Mei Jiang , Yugeng Lin
CPC classification number: G06V10/255 , G06F18/214 , G06N3/08 , G06V10/454 , G06V10/82 , G06V20/64 , G06K7/1413 , G06K7/1417 , G06V2201/07
Abstract: This application relates to a target detection method performed at a computer device. The method includes: obtaining a to-be-detected image; extracting a first image feature and a second image feature corresponding to the to-be-detected image; performing dilated convolution to the second image feature, to obtain a third image feature corresponding to the to-be-detected image; performing classification and regression to the first image feature and the third image feature, to determine candidate position parameters corresponding to a target object in the to-be-detected image and degrees of confidence corresponding to the candidate position parameters; and selecting a valid position parameter from the candidate position parameters according to their corresponding degrees of confidence, and determining a position of the target object in the to-be-detected image according to the valid position parameter. The solutions in this application can improve robustness and consume less time.
-
公开(公告)号：US11200395B2
公开(公告)日：2021-12-14
申请号：US17105119
申请日：2020-11-25
Inventor： Chen Ran , Dianping Xu , Yugeng Lin , Jie Miao , Xiaoyi Jia , Mei Jiang
Abstract: A graphic code recognition method includes: displaying a target image, the target image comprising at least two graphic codes; in response to receiving a graphic code recognition operation on the target image for selecting one of the at least two graphic codes to recognize, obtaining graphic code position information of the at least two graphic codes in the target image; determining a target graphic code indicated by the graphic code recognition operation according to the graphic code position information, the target graphic code belonging to the at least two graphic codes; and displaying a target graphic code recognition result corresponding to the target graphic code.
-
Patent Agency Ranking
公开(公告)号：US10540531B2
公开(公告)日：2020-01-21
申请号：US15993738
申请日：2018-05-31
Inventor： Mei Jiang , Hailong Liu , Pengfei Xiong
IPC: G06K7/14
Abstract: A method and an apparatus for image identification are provided. For example, the processing circuitry of the apparatus obtains first feature values of a first image feature for pixels in an image for barcode detection. The processing circuitry calculates measures that are indicative of changes of the first feature values in multiple directions within the image and determines a target area in the image for the barcode detection according to the measures. Further, the processing circuitry divides the target area into a plurality of sub-areas, and filters the sub-areas to determine a target sub-area for the barcode detection. Then, the processing circuitry obtains second feature values of a second image feature for the target sub-area. The second image feature is derived from the first image feature. The processing circuitry then identifies a barcode type in the target sub-area according to the second image feature.
-
7.发明授权公开(公告)号：US11507766B2
公开(公告)日：2022-11-22
申请号：US17080633
申请日：2020-10-26
Inventor： Jie Miao , Chen Ran , Dianping Xu , Xiaoyi Jia , Mei Jiang , Yugeng Lin
Abstract: A method for processing an encoded pattern, a storage medium, and an electronic device are disclosed in this application. An electronic device acquires a first encoded pattern to be recognized, the first encoded pattern being a pattern obtained after predefined information is encoded therein. The electronic device increases resolution of the first encoded pattern through a target model to obtain a second encoded pattern, the target model being obtained through training by using a predetermined third encoded pattern as an input and a predetermined fourth encoded pattern as an output, the third encoded pattern being obtained by decreasing resolution of the fourth encoded pattern, the third and the first encoded patterns being encoded in the same manner. Finally, the electronic device decodes the second encoded pattern using a code recognition module to obtain the predefined information. This application resolves the technical problem that an encoded pattern cannot be accurately recognized.
-
公开(公告)号：US11494577B2
公开(公告)日：2022-11-08
申请号：US17003507
申请日：2020-08-26
Inventor： Dianping Xu , Chen Ran , Jie Miao , Xiaoyi Jia , Mei Jiang , Yugeng Lin
Abstract: The present disclosure describes method, apparatus, and storage medium for identifying an identification code. The method includes obtaining, by a computer device, a to-be-detected picture. The computer device includes a memory storing instructions and a processor in communication with the memory. The method also includes detecting, by the computer device, an identification code in the to-be-detected picture to obtain a detection result, the detection result comprising target information of a target code corresponding to the identification code; sampling, by the computer device, the target code according to the target information, to obtain a sampled image; and decoding, by the computer device, the sampled image, to obtain an identification result corresponding to the identification code.
-
公开(公告)号：US09980009B2
公开(公告)日：2018-05-22
申请号：US15176030
申请日：2016-06-07
Inventor： Mei Jiang , Hailong Liu , Jian Liu , Bo Chen
IPC: H04N21/482 , H04N21/414 , H04N21/4363 , H04N21/44 , H04N21/81
CPC classification number: H04N21/482 , H04N21/41407 , H04N21/43637 , H04N21/44008 , H04N21/8146
Abstract: A digital video conversion device is communicatively coupled to a TV set and a TV signal source, respectively, so as to pass TV signals from the TV signal source to the TV set. Upon receipt of a TV channel identification request from a mobile terminal via a wireless communication channel, the digital video conversion device acquires an image from the TV signals currently broadcasted on the TV set and extracts a plurality of station logo characteristic sets from the image, each station logo characteristic set corresponding to one of a plurality of station logo templates. After calculating a similarity score between each station logo characteristic set and a corresponding station logo template, the digital video conversion device identifies one of the plurality of station logo templates as matching the image based on their similarity scores and returns TV channel information associated with the identified station logo template to the mobile terminal.
-
公开(公告)号：US20220343074A1
公开(公告)日：2022-10-27
申请号：US17857841
申请日：2022-07-05
Inventor： Bolun CAI , Xiaoyi Jia , Haoyu Li , Yugeng Lin , Dianping Xu , Huajie Huang , Chen Ran , Yike Liu , Lijian Mei , Zhikang Tan , Yanhua Cheng , Jinchang Xu , Minhui Wu , Mei Jiang
IPC: G06F40/279 , G06F40/205 , G06F40/30 , G06N3/08
Abstract: Embodiments of this application disclose a headword extraction method performed by a computer device. The method includes: obtaining a sentence feature of a target sentence and word features of a plurality of words in the target sentence; extracting semantics of the sentence feature of the target sentence to obtain a semantic feature of the target sentence, and extracting semantics of the word feature of each word to obtain a semantic feature of the word; obtaining a respective matching degree between the semantic feature of each of the plurality of words and the semantic feature of the target sentence; and determining, among the plurality of words in the target sentence, a word with a largest corresponding matching degree as a headword of the target sentence. The method can improve the accuracy of headwords extracted from the target sentence.
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.017 seconds)
