Tencent Technology (Shenzhen) Company Limited

Tsinghua University

Tencent Technology Company Limited

Xiaowei Guo

Feiyue Huang

Pai Peng

Xing Sun

Xinyang Jiang

Rui Wang

Cong Yao

Ruixin Zhang

Xiang Bai

Baoguang Shi

Kailin Wu

Kai Feng Li

Yi Cheng Zhang

Bin Hua Liu

Xuan Zhou

Yang He

Juhong Wang

Bin Liu

Yi Zhang

Shimin Hu

Kun Xu

Haolei Yuan

Weiming Dong

Jia Chang

Xiaoguang Yu

Shuguang Huang

Chengzhao Zhang

Zongqiao Yu

Yuqiang Ren

Xingjia Pan

Changsheng Xu

This application discloses a region recognition method, apparatus, and device, and a readable storage medium, and relates to the field of artificial intelligence. The method includes: acquiring an input image, the input image including image content of a to-be-recognized region; acquiring a first rotation angle of the image content in the input image, the first rotation angle being estimated by using a recognition model; rotating a convolution kernel in the recognition model at the first rotation angle, and performing convolution processing on an image feature of the input image using the rotated convolution kernel to obtain a target feature; recognizing the target feature to obtain region data; and determining, in the input image by using the region data, a target region corresponding to the image content.

Region recognition method, apparatus and device, and readable storage medium

This application discloses an image feature recognition method performed at a computing device. The computing device obtains a first neural network model by training parameters in a second neural network model using a first training set and a second training set consecutively, image features of training pictures in the first training set being marked and image features of training pictures in the second training set being not marked. After obtaining a first neural network model, the computing device obtains a recognition request for recognizing an image feature in a target picture. The computing device then recognizes the image feature in the target picture by applying the target picture to the first neural network model. Finally the computing device returns a first recognition result of the first neural network model, the first recognition result indicating an image feature (for example, a pathological feature) recognized in the target picture.

Image feature recognition method and apparatus, storage medium, and electronic apparatus

An object recognition method is performed at an electronic device. The method includes: pre-processing a target image, to obtain a pre-processed image, the pre-processed image including three-dimensional image information of a target region of a to-be-detected object, processing the pre-processed image by using a target data model, to obtain a target probability, the target probability being used for representing a probability that an abnormality appears in a target object in the target region of the to-be-detected object; and determining a recognition result of the target region of the to-be-detected object according to the target probability, the recognition result being used for indicating the probability that the abnormality appears in the target region of the to-be-detected object. The object recognition method can effectively improve accuracy of object recognition and avoid a case of incorrect recognition.

Object recognition method and device, and storage medium

An image processing method is provided, including: obtaining a target image; invoking an image recognition model including: a backbone network, a pooling module and a dilated convolution module that are connected to the backbone network and that are parallel to each other, and a fusion module connected to the pooling module and the dilated convolution module; performing feature extraction on the target image by extracting, using the backbone network, a feature map of the target image, separately processing, using the pooling module and the dilated convolution module, the feature map, to obtain a first result outputted by the pooling module and a second result outputted by the dilated convolution module, and fusing the first result and the second result by using the fusion module into a model recognition result of the target image; and determining a semantic segmentation labeled image of the target image based on the model recognition result.

Image processing method and device, computer apparatus, and storage medium

Embodiments of the present disclosure provide an image classification method for a computer device. The method includes obtaining an original image and a category of an object included in the original image; adjusting a display parameter of the original image to satisfy a value condition to obtain an adjusted original image; and transforming the display parameter of the original image according to a distribution condition that distribution of the display parameter needs to satisfy, to obtain a transformed image. The method also includes training a neural network model based on the category of the object and a training set constructed by the adjusted original image and the transformed image; and determining a category of an object included in a to-be-predicted image based on the trained neural network model.

Image classification method, computer device, and computer-readable storage medium

Provided is a border detection method, server, and storage medium. The method including detecting a plurality of first straight line segments in a to-be-detected image, the to-be-detected image comprising a target region of a to-be-determined border; generating a plurality of first candidate borders of the target region according to the plurality of first straight line segments; obtaining a plurality of second candidate borders of the target region from the plurality of first candidate borders; extracting border features of the plurality of second candidate borders; and obtaining an actual border of the target region from the plurality of second candidate borders according to the border features of the plurality of second candidate borders and a border detection model, the border detection model being used to determine a detected value of each candidate border, and the detected value representing a similarity between each candidate border and the actual border.

Border detection method, server and storage medium

An image classification method includes: obtaining an original image and a category of an object included in the original image; adjusting a first display parameter of the original image to obtain an adjusted original image; and transforming a second display parameter of the original image to obtain a new image. The adjusted first display parameter satisfies a value condition; and the transformed second parameter of the new image satisfies a distribution condition. The method also includes training a neural network model based on the category of the included object and a training set constructed by combining the adjusted original image and the new image; and inputting a to-be-predicted image into the trained neural network model, and determining the category of the object included in the to-be-predicted.

Image classification method, server, and computer-readable storage medium

This application provides an image recognition method, a storage medium, and a computer device. The method includes: obtaining a to-be-recognized image; preprocessing the to-be-recognized image, to obtain a preprocessed image; obtaining, through a first submodel in a machine learning model, a first image feature corresponding to the to-be-recognized image, and obtaining, through a second submodel in the machine learning model, a second image feature corresponding to the preprocessed image; and determining, according to the first image feature and the second image feature, a first probability that the to-be-recognized image belongs to a classification category corresponding to the machine learning model. It may be seen that, the solutions provided by this application can improve recognition efficiency and accuracy.

Image recognition method, storage medium and computer device

In some examples, processing circuitry obtains a shallow hash neural network (SHNN) model that has been trained from a HNN model and based on a set of SHNN training images that aggregates image recognition results from at least two reference hash neural network (HNN) models. Further, the processing circuitry performs an image recognition on the image according to the SHNN model, to obtain an image class vector in an image class space. The image class vector includes probability values of respective image classes in the image class space. A probability value of an image class in the image class space is a combination of intermediate probability values of the image class that are resulted from the at least two reference HNN models. Further, the processing circuitry determines one of the image classes for the image according to the probability values of the respective image classes in the image class space.

Image recognition method, apparatus, server, and storage medium

Disclosed are a training method and apparatus for a CNN model, which belong to the field of image recognition. The method comprises: performing a convolution operation, maximal pooling operation and horizontal pooling operation on training images, respectively, to obtain second feature images; determining feature vectors according to the second feature images; processing the feature vectors to obtain category probability vectors; according to the category probability vectors and an initial category, calculating a category error; based on the category error, adjusting model parameters; based on the adjusted model parameters, continuing the model parameters adjusting process, and using the model parameters when the number of iteration times reaches a pre-set number of times as the model parameters for the well-trained CNN model. After the convolution operation and maximal pooling operation on the training images on each level of convolution layer, a horizontal pooling operation is performed. Since the horizontal pooling operation can extract feature images identifying image horizontal direction features from the feature images, such that the well-trained CNN model can recognize an image of any size, thus expanding the applicable range of the well-trained CNN model in image recognition.

Training method and apparatus for convolutional neural network model

An image classification method is provided. The method includes: inputting a to-be-classified image into a plurality of neural network models; obtaining data output by multiple non-input layers specified by each neural network model to generate a plurality of image features corresponding to the plurality of neural network models; respectively inputting the plurality of corresponding image features into linear classifiers, each of the linear classifiers being trained by one of the plurality of neural network models for determining whether an image belongs to a preset class; obtaining, using each neural network model, a corresponding probability that the to-be-classified image comprises an object image of the preset class; and determining, according to each obtained probability, whether the to-be-classified image includes the object image of the preset class.

Image classification method, electronic device, and storage medium

An image processing method is provided. The method includes obtaining a human facial image and providing a total of n number of source images in a preconfigured file, where n is an integer greater than 2, and each source image corresponds to adjusting parameters for the source image in the preconfigured file. The method also includes generating a synthesized human facial image for the each source image by adjusting the human facial image based on the adjusting parameters corresponding to the source image in the preconfigured file, individually synthesizing the each source image and the synthesized human facial image for the each source image to obtain n number frames of synthesized images, and combining the n number frames of synthesized images into a dynamic image in a time order.

Image processing method and apparatus

The present disclosure discloses a method and device for localized blind watermark generation and detection. The method for localized blind watermark generation may include: generating an N-dimensional pseudorandom initial sequence according to a preset key, and generating a 2N-dimensional sequence by inverting the initial sequence bit by bit and appending the inverted sequence to the initial sequence; and extracting the first 2N coefficients of a feature point of an image to form a coefficient sequence, and acquiring a parity of a bit of the coefficient sequence according to a parity of a corresponding bit of the 2N-dimensional sequence. With the present disclosure, redundant expansion may be performed on watermark data to increase the scale of test data with respect to the original bit data before embedding the test data into a transformation domain of the vicinity of a feature point of an image; during detection, a sequence extracted from the transformation domain of the vicinity of a certain feature point is checked bit by bit, and it is determined whether a watermark is embedded in the vicinity of the point base on the result of the examination, thereby enhancing a watermark detecting efficiency.

Growing community of inventors

Shenzhen, China

Xiaowei Guo