Canon Kabushiki Kaisha

Boe Technology Group Co., Ltd.

Beijing Boe Display Technology Co., Ltd.

Beijing Boe Optoelectronics Technology Co., Ltd.

Beijing Dajia Internet Information Technology Co., Ltd.

Xian Li

Dongchao Wen

Dongyue Zhao

Ming Jin Chen

Bo Wu

Zhanchang Bu

Yong Jiang

Yang Chu

Weihong Deng

Jiani Hu

Donghui Sun

Yang Zhang

Bochang Wang

Yan Yang

Haijun Shi

Qi Hu

Tingze Dong

Wenjia Sun

Yaohai Huang

Lifeng Xu

Fuguo Zhu

Limin Tian

You Lv

Hongzhi Ma

Hailong Zhou

Ou Hu

Yixiao Cheng

The present disclosure relates to training method and apparatus for an object recognition model. There provides a training sample optimization apparatus for a neural network model for object recognition, comprising: for each training sample in a training sample database, a fluctuation determination unit configured to determine a fluctuation of model prediction of the training sample relative to a corresponding labeled identity of the training sample in a case of training the neural network model; and an optimization unit configured to determine whether the training sample can be used for training of the neural network model in the next training epoch, based on the fluctuation of the training sample.

Method and apparatus for training an object recognition model

The present invention relates to method and apparatus for training a neural network for object recognition. A training method which includes inputting a training image set containing an object to be recognized, dividing the image samples in the training image set into simple samples and hard samples, for each kind of the image sample and the variation image sample, performing, a transitive transfer, calculating a distillation loss of the transferred student feature of the image sample relative to a teacher feature extracted from corresponding image sample of the other kind, classifying, the image sample, and calculating a classification loss of the image sample, calculating a total loss related to the training image set, and updating parameters of the neural network according to the calculated total loss.

Training method and training apparatus for a neural network for object recognition

A packaging unit, a component packaging structure and a preparation method thereof. The packaging unit includes a bonding substrate and spacers formed on the bonding substrate through a patterning process, wherein the bonding substrate is reserved with packaging regions for applying sealant. When the packaging unit is used to package a component, because the spacer(s) is supported between the bonding substrate and the base substrate, the packaging unit is easy to separate from the base substrate At the same time, the packaging unit has little or no damage to the base substrate and elements formed on the base substrate, thus effectively protecting the performance of the base substrate and the elements on the base substrate.

Packaging unit, component packaging structure and preparation method thereof

Disclosed are a method, a system, a server and an intelligent terminal for aggregating and displaying comments. The method includes: obtaining multimedia interactive information to be displayed; generating aggregated comments with same types of multimedia interactive information in the multimedia interactive information based on a preset aggregated rule; transmitting the aggregated comments to a client for displaying; obtaining a sharing path for a user to share data; and publishing the aggregated comments in a comment area of different sharing platforms or a comment area of applications based on the sharing path, wherein the sharing path comprises network links for sharing same data to the different sharing platforms or the applications.

Method, system, server and intelligent terminal for aggregating and displaying comments

One of the aspects of the present invention discloses a feature point detection method. The method comprises: acquiring a face region in an input image; acquiring first positions of first feature points and second feature points according to a pre-generated first model; estimating second positions of the first feature points according to the first positions of the first feature points and pre-generated second models; detecting third positions of the first feature points and the second feature points according to the second positions of the first feature points, the first positions of the second feature points and pre-generated third models. According to the present invention, the final detected face shape could approach to the actual face shape much more.

Feature point detection method and apparatus, image processing system, and monitoring system

A backlight module, a display module and a display device are disclosed. The display module includes a backlight module; a display panel located at a light exit side of the backlight module; and a first optical adhesive layer located between the backlight module and the display panel. The display panel and the backlight module are adhered to each other through the first optical adhesive layer.

Backlight module, display module and display device

One of the aspects of the present disclosure discloses an apparatus for recognizing expression of a face in a face region of an image, comprising: a unit configured to detect feature points of the face in the face region of the image; a unit configured to determine a face shape of the face in the face region based on the detected feature points; a unit configured to determine a group that the face in the face region belongs to based on the determined face shape and pre-defined shape groups; and a unit configured to determine an expression of the face in the face region based on pre-generated first models corresponding to the determined group and features extracted from at least one region in the face region, wherein the at least one of the regions are regions which are labeled out in the pre-generated first models corresponding to the determined group.

Apparatus and method for recognizing expression of a face, image processing apparatus and system

One of the aspects of the present invention discloses an image processing apparatus and an image processing method. The image processing apparatus comprises: an image acquisition unit configured to acquire an image containing a face; a region location unit configured to locate at least one region which represents attributes of the face in the acquired image; a feature extraction unit configured to extract features from the located regions; and a feature integration unit configured to integrate the features of the located regions which are symmetrical with each other based on symmetry of the face. According to the present invention, the dimension of the features used for image processing could be reduced and the image processing accuracy could be maintained as much as possible.

Image processing apparatus and image processing method

A backlight module and a display device are disclosed. The backlight module includes a bottom reflecting plate; a light guide plate (LGP) fixed over the bottom reflecting plate by means of glue; and a transparent material layer disposed between the bottom reflecting plate and the LGP, wherein a refractivity of the transparent material layer is at least lower than a refractivity of the LOP. The display device includes the backlight module.

Backlight module and display device

In the present invention, an attribution is extracted from each region obtained by segmentation of an image, relationships among the regions are described, and a composition of the image is evaluated based on the attributions and the relationships.

Image composition evaluating apparatus, information processing apparatus and methods thereof

An apparatus includes a unit configured to acquire an object shape regression model, which comprises an average object shape, a plurality of regression functions and a plurality of feature selection maps; a unit configured to set an initial object shape for the object image based on the average object shape; a unit configured to calculate at least one feature vector with respect to a plurality of feature points; a unit configured, for each coordinate of the plurality of feature points, to select feature fragments from the calculated feature vector based on a corresponding one of the plurality of feature selection maps and assemble the feature fragments into a sub feature vector; and a unit configured, for at least one coordinate of at least one feature point, to predict a coordinate increment based on the corresponding sub feature vector and a corresponding one of the plurality of regression functions.

Object shape aligning apparatus, object processing apparatus and methods thereof

The present invention relates to method, apparatus and storage medium for enhancing document image, and method, apparatus and storage medium for character recognition. For enhancing the document image especially half-tone block image and improving the recognition ratio thereof, the block image is segmented into line images, which are subject to noise reduction. Then, based on the connected component densities, the noise-reduced line images are sorted into three types including normal line image, broken-stroke line image and hollow-stroke line image. Based on their types and other properties, the noise-reduced line images are enhanced, generating enhanced line images, which as a whole constitutes an enhanced block image.

Growing community of inventors

Beijing, China

Xian Li