Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

Anhui Gsh Bio-tech Co., Ltd.

Boe Technology Group Co., Ltd.

Beijing Boe Display Technology Co., Ltd.

Baidu Online Network Technology (beijing) Co., Ltd.

Shanshan Liu

Chengquan Zhang

Hui Liu

Xiaoqiang Zhang

Pengyuan Lv

Yongfa Qin

Wenwen Zhou

Ying Li

Shufu Xie

Xuan Li

Lili Jia

Donglei Li

Honghao Yu

Mengyi En

Hailun Xu

Haifeng Wang

Chen Chen

Errui Ding

Bochang Wang

Guang Cheng Li

Tian Wu

Junyu Han

Jingdong Wang

Hao Zhou

Xiaoyan Wang

Yuning Du

Kun Yao

Chenxia Li

Hua Lu

Liang Wu

Sijin Wu

Ye Sun

Yao Xiao

Yongfeng Chen

Qiming Peng

Yangliu Xu

Meina Qiao

Pingnan Chang

Jia Zhou

Jin Tian

The present disclosure provides a character recognition model training method and apparatus, a character recognition method and apparatus, a device and a medium, relating to the technical field of artificial intelligence, and specifically to the technical fields of deep learning, image processing and computer vision, which can be applied to scenarios such as character detection and recognition technology. The specific implementing solution is: partitioning an untagged training sample into at least two sub-sample images; dividing the at least two sub-sample images into a first training set and a second training set; where the first training set includes a first sub-sample image with a visible attribute, and the second training set includes a second sub-sample image with an invisible attribute; performing self-supervised training on a to-be-trained encoder by taking the second training set as a tag of the first training set, to obtain a target encoder.

Character recognition model training method and apparatus, character recognition method and apparatus, device and storage medium

The present invention discloses a production method of enzymatic reaction using adenosine instead of ATP. The method comprises the following steps: (1) adding ATP regeneration enzyme, AK enzyme and adenosine in proportion to carry out an enzymatic reaction in an enzymatic reaction system; (2) separating the ATP regeneration enzyme and AK enzyme by either directly separating ATP regeneration enzyme and AK enzyme immobilized in a reaction tank, or separating free ATP regeneration enzyme and AK enzyme by an ultrafiltration membrane in a filter; and (3) separating and purifying the filtrate of step (2) to obtain a product. The disclosed method provides: greatly reduced industrial production costs; faster reaction rate; stable enzyme recovery system that is energy efficient and environmentally friendly; and capability of reusing the byproducts or collecting them for the production of ATP.

Production method of enzymatic reaction using adenosine instead of ATP

Provided are methods and apparatuses for navigation guidance and establishing a three-dimensional real scene model, a device and a medium, which relate to the field of artificial intelligence and, in particular, intelligent transportation technologies. A specific implementation includes: determining a navigation route of a navigation device and candidate three-dimensional real scene data corresponding to the navigation route; where the candidate three-dimensional real scene data includes candidate location information, candidate three-dimensional model data and a candidate observation viewing angle; matching real-time positioning information of the navigation device with the candidate location information in the candidate three-dimensional real scene data to obtain target three-dimensional real scene data; and simulating target three-dimensional model data in the target three-dimensional real scene data at a target observation viewing angle in the target three-dimensional real scene data and at a location corresponding to the real-time positioning information to obtain a real-time navigation guidance image.

Methods and apparatuses for navigation guidance and establishing a three-dimensional real scene model, device and medium

The present invention discloses a production method of enzymatic reaction using adenosine instead of ATP. The method comprises the following steps: (1) adding ATP regeneration enzyme, AK enzyme and adenosine in proportion to carry out an enzymatic reaction in an enzymatic reaction system; (2) separating the ATP regeneration enzyme and AK enzyme by either directly separating ATP regeneration enzyme and AK enzyme immobilized in a reaction tank or separating free ATP regeneration enzyme and AK enzyme by an ultrafiltration membrane in a filter; and (3) separating and purifying the filtrate of step (2) to obtain a product. The disclosed method provides: greatly reduced industrial production costs; faster reaction rate; stable enzyme recovery system that is energy efficient and environmentally friendly; and capability of reusing the byproducts or collecting them for the production of ATP.

The present disclosure provides a method for visual question answering, which relates to fields of computer vision and natural language processing. The method includes: acquiring an input image and an input question; detecting visual information and position information of each of at least one text region in the input image; determining semantic information and attribute information of each of the at least one text region based on the visual information and the position information; determining a global feature of the input image based on the visual information, the position information, the semantic information, and the attribute information; determining a question feature based on the input question; and generating a predicted answer for the input image and the input question based on the global feature and the question feature. The present disclosure further provides a device for visual question answering, a computer device and a medium.

Method and apparatus for visual question answering, computer device and medium

The present disclosure discloses a method and apparatus for recognizing a text. The method comprises: acquiring images of a text area of an input image, the acquired images including a text centerline graph, a text direction offset graph, a text boundary offset graph, and a text character classification graph; extracting coordinates of feature points of a character center from the text centerline graph; sorting the extracted coordinates of the feature points based on the text direction offset graph to obtain a coordinate sequence of the feature points; determining a polygonal bounding box of the text area based on the coordinate sequence of the feature points of the character center and the text boundary offset graph; and determining a classification result of the feature points of the character center, based on the coordinate sequence of the feature points of the character center and the text character classification graph.

Method and apparatus for recognizing text

The present application discloses a method and an apparatus for recognizing text content, and an electronic device, and relates to a text recognition technique in the field of computer technology. The specific implementation is as follows: acquiring a dial picture; detecting at least one text centerline and a bounding box corresponding to each text centerline in the dial picture; and recognizing text content in each line of text in the dial picture based on the at least one text centerline and the bounding box corresponding to each text centerline.

Method and apparatus for recognizing text content and electronic device

The present invention relates an enzymatic method for preparing glutathione, comprising the following steps: (1) producing glutathione in a reactor using GshF enzyme, ATP regeneration enzyme and AK enzyme; (2) separating immobilized GshF enzyme, ATP regeneration enzyme and AK enzyme in the reactor, or separating free GshF enzyme using a filtration device; (3) separating the filtrate obtained in step (2) to obtain a crude product GSH and a small amount of ATP, ADP and AMP; and (4) subjecting the GSH obtained in step (3) to concentration, crystallization, and drying to prepare a finished GSH. The described method provides: greatly reduced industrial production costs; faster reaction rate; stable enzyme recovery system that is energy efficient and environmentally friendly; and capability of reusing the byproducts or collecting them for the production of ATP.

Method for enzymatic preparation of glutathione

A character recognition method, a character recognition apparatus, an electronic device and a computer readable storage medium are disclosed. The character recognition method includes: determining semantic information and first position information of each individual character recognized from an image; constructing a graph network according to the semantic information and the first position information of each individual character; and determining a character recognition result of the image according to a feature of each individual character calculated by the graph network.

Character recognition method and apparatus, electronic device and computer readable storage medium

The present application discloses a method and an apparatus for optical character recognition, an electronic device and a storage medium, and relates to the fields of artificial intelligence and deep learning. The method may include: determining, for a to-be-recognized image, a text bounding box of a text area therein, and extracting a text area image from the to-be-recognized image according to the text bounding box; determining a bounding box of text lines in the text area image, and extracting a text-line image from the text area image according to the bounding box; and performing text sequence recognition on the text-line image, and obtaining a recognition result. The application of the solution in the present application can improve a recognition speed and the like.

Optical character recognition method and apparatus, electronic device and storage medium

An optical film includes a light-transmissive substrate and a first annular lens group. The light-transmissive substrate has a first surface and a second surface opposite to each other. The first annular lens group is disposed on the second surface, and the first annular lens group is configured to allow light to pass through. The reflectivity of the first annular lens group decreases along a direction away from a central axis of the first annular lens group, and an extending direction of the central axis is the same as a thickness direction of the light-transmissive substrate.

Optical film and method of manufacturing the same, backlight module, and display apparatus

A light guide plate and a manufacturing method thereof, a backlight module, and a display device are provided. The light guide plate includes a light incident surface, a light reflection surface, and a light-emitting surface; the light reflection surface includes a first prism structure array, the first prism structure array includes first prisms arranged in sequence in a first direction, and the first direction is perpendicular to the light incident surface; the first prism structure array is configured to enable light emitted from the light incident surface to be emitted toward the light-emitting surface; and the light-emitting surface includes a second cylindrical structure array, the second cylindrical structure array includes second cylindrical structures arranged side by side in a second direction, the second direction is perpendicular to the first direction, and a first plane including the first direction and the second direction is perpendicular to the light incident surface.

Light guide plate and manufacturing method thereof, backlight module and display device

The present disclosure provides a method and a device for generating an image. The method includes: a, obtaining a character recognition result corresponding to a first image, the character recognition result including one or more characters and a first confidence of each character; b, determining a second confidence of a character set including at least one of the one or more characters according to the first confidence of each character in the character set; c, determining a refined character set corresponding to the first image based on the second confidence; and d, performing image processing on a sub image corresponding to the refined character set in the first image, to obtain a second image, an annotation text corresponding to the second image including the refined character set.

Method and device for generating image

The present disclosure provides a method and for acquiring text data of a trademark image, a computer device and a non-transitory computer readable storage medium. The method includes the followings. A trademark database including one or more mappings among trademark feature information, trademark description information and trademark text information is established. A to-be-processed image including image description information is acquired. Trademark feature information corresponding to the to-be-processed image is determined. The trademark text information corresponding to the trademark feature information as the text data of the trademark image corresponding to the to-be-processed image according to the one or more mappings in the trademark database when the trademark description information corresponding to the trademark feature information corresponding to the to-be-processed image is contained in the image description information corresponding to the to-be-processed image.

Method and device for acquiring text data from trademark image, computer device and storage medium

Growing community of inventors

Beijing, China

Shanshan Liu