Abstract: This application provides a method of detecting printing defects. The method includes obtaining a first image of each character in a reference image. A third image of each character is obtained based on the first image of each character, a fourth image of each character is obtained based on a second image of each character obtained from an image to be detected. Once a fifth image of each character is obtained based on the third image of each character, a sixth image of each character is obtained according to the fourth image and the fifth image of each character, a detection result of each character in the image to be detected is determined according to the fifth image and the sixth image of the each character.

Abstract: An image processing method includes: performing target object detection on an initial image to obtain an object detection result, and performing image saliency detection on the initial image to obtain a saliency detection result; cropping the initial image based on the object detection result and the saliency detection result to obtain a corresponding cropped image; acquiring an image template for indicating an image style, and acquiring layer information corresponding to the image template; and adding the layer information to the cropped image based on the image template to obtain a target image corresponding to the image style indicated by the image template.

Abstract: Certain aspects of the present disclosure provide techniques for adaptive sampling for rendering using deep learning. This includes receiving, at a sampler in a rendering pipeline, a plurality of rendered pixel data, wherein the sampler includes a first machine learning (ML) model. It further includes generating a sampling map for the rendering pipeline using the first ML model and the plurality of rendered pixel data, including predicting a plurality of pixel values in the sampling map based on a generated distribution of pixel values. It further includes rendering an image using the sampler, the sampling map, and a denoiser in the rendering pipeline.

Abstract: An artificial intelligence-based image processing method implemented by a computer device is provided. The method includes: acquiring an image; performing element region detection on the image to determine an element region in the image; detecting a target element region in the image using an artificial intelligence-based technique; generating a target element envelope region by searching an envelope for the detected target element region; and fusing the element region and the target element envelope region to obtain a target element region outline.

Abstract: A vison-based landing system comprises a processor onboard an aerial vehicle, an onboard vision sensor, onboard aiding sensors, and a data storage unit. The processor hosts an adaptive feature extraction module operative to perform a method that comprises capturing an image of a landing area having a plurality of edge features; calculating an estimated slope of an expected edge feature; calculating an expected gradient direction of the expected edge feature; selecting a horizontal basis kernel for the expected edge feature along an expected horizontal gradient; selecting a vertical basis kernel for the expected edge feature along an expected vertical gradient; calculating a combined convolution kernel for the expected edge feature based on the horizontal and vertical basis kernels, the estimated slope, and the expected gradient direction; and performing a convolution operation on the image using the combined convolution kernel to obtain an edge feature image of the landing area.

Abstract: An image detection obtains original image. The original image is corrected to obtain a corrected image. Median filtering is performed on the corrected image to obtain a filtered image. A contrast of the filtered image is adjusted to obtain an adjusted image. Bilateral filtering is performed on the adjusted image to obtain an enhanced image. Defects in the enhanced image is detected. The method can detect defects in images accurately and efficiently.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to perform a downstream computer vision task. One of the methods includes pre-training an initial neural network that shares layers with the neural network to perform an initial computer vision task and then training the neural network on the downstream computer vision task.

Abstract: A method for re-recognizing an object image is provided based on multi-feature information capture and correlation analysis weights of an input feature map by using a convolutional layer with a spatial attention mechanism and a channel attention mechanism, causing channel and spatial information to effectively combined, which not only focus on an important feature and suppress an unnecessary feature, but also improve a representation of a feature. A multi-head attention mechanism is used to process a feature after an image is divided into blocks to capture abundant feature information and determine a correlation between features to improve performance and efficiency of object image retrieval. The convolutional layer with the channel attention mechanism and the spatial attention mechanism is combined with a transformer having the multi-head attention mechanism to focus on globally important features and capture fine-grained features, thereby improving performance of re-recognition.