Abstract: A system and method for image correction is provided. The method includes: receiving an original image; obtaining an image relating to a region of interest (ROI); detecting an artifact in the image relating to the ROI; generating an artifact image based on the artifact; and correcting the original image based on the artifact image.

Abstract: An apparatus for sorting is described and includes acquiring a multiplicity of synchronized image signals of a product stream which is to be sorted; generating a multiplicity of fused sensor signals; forming an image model previously acquired from the objects to be sorted; identifying objects in the product stream, and generating object presence and defect signals; determining a spatial orientation of the objects in the product stream; detecting the defects and removing the defects from the product stream.

Abstract: A system includes an image depth prediction neural network implemented by one or more computers. The image depth prediction neural network is a recurrent neural network that is configured to receive a sequence of images and, for each image in the sequence: process the image in accordance with a current internal state of the recurrent neural network to (i) update the current internal state and (ii) generate a depth output that characterizes a predicted depth of a future image in the sequence.

Abstract: Described herein are neural network-based systems, methods and instrumentalities associated with estimating the motion of an anatomical structure. The motion estimation may be performed using a feature pyramid and/or a motion pyramid that correspond to multiple image scales. The motion estimation may be performed using neural networks and parameters that are learned via a training process involving a student network and a teacher network pre-pretrained with abilities to apply progressive motion compensation.

Abstract: A biometric imaging device is provided with: placement unit that supports a biological object, imaging unit that takes images of the biological object, and determining unit that determines whether or not the biological object is placed on the placement unit, based on whether or not a feature of the biological object has changed at a place where the placement unit and the biological object are in contact, in the image(s).

Abstract: An encoding apparatus partitions a digital image into multiple regions for subsequent encoding. A first encryption code is associated with a first region, a second encryption code is associated with a second region and the first code, and a third code is associated with the first code, the second code and a third region. An authentication apparatus authenticates the digital image in an inverse process.

Abstract: Embodiments disclosed herein provide for systems and methods of separating characters associated with ligatures in digitized documents. The systems and methods provide for a ligature detection engine configured to identify the ligatures, and a ligature processing engine configured to identify and remove the glyphs attaching the separate characters forming the ligature.

Abstract: The present application discloses a face super-resolution realization method and apparatus, an electronic device and a storage medium, and relate to fields of face image processing and deep learning. The specific implementation solution is as follows: a face part in a first image is extracted; the face part is input into a pre-trained face super-resolution model to obtain a super-sharp face image; a semantic segmentation image corresponding to the super-sharp face image is acquired; and the face part in the first image is replaced with the super-sharp face image, by utilizing the semantic segmentation image, to obtain a face super-resolution image.

Abstract: Example embodiments that analyze images to characterize aspects of the images rely on a same neural network to characterize multiple aspects in parallel. Because additional neural networks are not required for additional aspects, such an approach scales with increased aspects.

Abstract: A learning model may provide a hierarchy of convolutional layers configured to perform convolutions upon image features, each layer other than a topmost layer convoluting the image features at a lower resolution to a higher layer, and each layer other than a bottommost layer returning the image features to a lower layer. Each layer fuses the lower resolution image features received from a higher layer with same resolution image features convoluted at the layer, so as to combine large-scale and small-scale features of images. Layers of the hierarchy may be substantially equal to a number of lateral convolutions at a bottommost convolutional layer. The bottommost convolutional layer ultimately passes the fused features to an attention mapping module, which utilizes two attention mapping pathways in combination to detect non-local dependencies and interactions between large-scale and small-scale features of images without de-emphasizing local interactions.

Abstract: A method for detecting an object in a first distorted image using a sliding window algorithm, comprising: receiving an inverse of a mathematical representation of a distortion of the first distorted image; wherein the detection of an object comprises sliding a sliding window over the first distorted image, the sliding window comprising a feature detection pattern, and for each position of a plurality of positions in the first distorted image: transforming the sliding window based on the inverse of the mathematical representation of the distortion at the position, wherein the step of transforming the sliding window comprises transforming the feature detection pattern of the sliding window such that a resulting distortion of the feature detection pattern of the transformed sliding window corresponds to the distortion of the first distorted image at the position; and using the transformed sliding window comprising the transformed feature detection pattern in the sliding window algorithm.

Abstract: A system for enhancing a low-dose (LD) computed tomography (CT) image is described. The system includes a modularized adaptive processing neural network (MAP-NN) apparatus and a MAP module. The MAP-NN apparatus is configured to receive a LDCT image as input. The MAP-NN apparatus includes a number, T, trained neural network (NN) modules coupled in series. Each trained NN module is configured to generate a respective test intermediate output image based, at least in part, on a respective received test input image. Each test intermediate output image corresponds to an incrementally denoised respective received test input image. The MAP module is configured to identify an optimum mapping depth, D, based, at least in part, on a selected test intermediate output image, the selected test intermediate output image selected by a domain expert. The mapping depth, D, is less than or equal to the number, T.

Abstract: An image segmentation system to perform operations that include causing display of an image within a graphical user interface of a client device, receive a set of user inputs that identify portions of a background and foreground of the image, identify a boundary of an object depicted within the image based on the set of user inputs, crop the object from the image based on the boundary, and generate a media item based on the cropped object, wherein properties of the media object, such as a size and a shape, are based on the boundary of the object.

Abstract: Disclosed is a stereo matching method of images performed by a system implemented by a computer, including the steps of: receiving a pair of images obtained at different time points; generating a feature map by extracting features of each pixel of the pair of images; generating sequentially cost volumes for partial time points based on the feature map and generating a feature map for the entire disparity by fusing the cost volumes using 2D convolution; and generating a final disparity map by refining the generated feature map.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network configured to receive a network input and to assign a respective score to each of a plurality of locations in the network input. In one aspect, a method includes obtaining a training input and a corresponding ground truth output; processing the training input to generate a training output; computing a loss for the training input, comprising: selecting a plurality of candidate locations; setting to zero the training scores for any location in the selected candidate locations that has a ground truth score below a threshold value; for each of a plurality of pairs of locations in the selected candidate locations: computing a pair-wise loss for the pair; and combining the pair-wise losses to compute the loss for the training input; and determining an update to the current values of the parameters.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.

Abstract: According to embodiments of the present disclosure, a method and an apparatus for processing an image, a device, and a storage medium are provided. The method includes: performing an image processing operation on an initial image having a noise associated with an adversarial sample attack, to obtain an intermediate image, the image processing operation including at least one of: reducing resolution of the initial image, or smoothing at least a part of the initial image; determining an image enhancement model matching the image processing operation, the image enhancement model being trained based on a sample image and a reference image, and the reference image being obtained by performing at least the image processing operation on the sample image; and generating a target image by processing the intermediate image using the image enhancement model, the target image having an image quality higher than the intermediate image.

Abstract: According to various embodiments, a pore visualization service providing server based on artificial intelligence may include a data pre-processor for obtaining a user's face image captured by a user terminal from the user terminal and performing pre-processing based on facial feature points based on the face image; a pore image extractor for generating a pore image corresponding to the user's face image by inputting the user's face image that has been pre-processed through the data pre-processing into an artificial neural network; a data post-processor for post-processing the generated pore image; and a pore visualization service providing unit for superimposing the post-processed pore image on the face image and transmitting a pore visualization image to the user terminal.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for predicting object pose. In one aspect, a method includes receiving an image of an object having one or more feature points; providing the image as an input to a neural network subsystem trained to receive images of objects and to generate an output including a heat map for each feature point; applying a differentiable transformation on each heat map to generate respective one or more feature coordinates for each feature point; providing the feature coordinates for each feature point as input to an object pose solver configured to compute a predicted object pose for the object, wherein the predicted object pose for the object specifies a position and an orientation of an object; and receiving, at the output of the object pose solver, a predicted object pose for the object in the image.

Abstract: Methods and systems for identifying quantisation parameters for a Deep Neural Network (DNN). The method includes determining an output of a model of the DNN in response to training data, the model of the DNN comprising one or more quantisation blocks configured to transform a set of values input to a layer of the DNN prior to processing the set of values in accordance with the layer, the transformation of the set of values simulating quantisation of the set of values to a fixed point number format defined by one or more quantisation parameters; determining a cost metric of the DNN based on the determined output and a size of the DNN based on the quantisation parameters; back-propagating a derivative of the cost metric to one or more of the quantisation parameters to generate a gradient of the cost metric for each of the one or more quantisation parameters; and adjusting one or more of the quantisation parameters based on the gradients.