Abstract: A system and method are provided for denoising images. A standard image module is configured to generate a standard anatomy feature and a standard noise feature from a standard image and reconstruct the standard image from the standard anatomy feature and the standard noise feature. A reduced quality image module is configured to generate a reduced quality anatomy feature and a reduced quality noise feature from a reduced quality image, and reconstruct the reduced quality image from the reduced quality anatomy feature and the reduced quality noise feature. A loss calculation module is provided for calculating loss metrics at least partially based on a comparison between 1) the reconstructed standard image and the standard image, and 2) the reconstructed reduced quality image and the reduced quality image. Upon providing the standard image module with the reduced quality anatomy feature, the standard image module outputs a reconstructed standard transfer image.

Abstract: This paper discloses a careless driving determination apparatus. The careless driving determination apparatus captures a plurality of face images of a driver of a vehicle in a predetermined period using a driver monitor camera. Then, it determines whether each of the plurality of face images shows first status in which the driver wears a wearing object or second status in which the driver does not wear the wearing object, the wearing object covering a part of a face of the driver. Then, it calculates a distribution range of angles of face directions or angles of gaze directions of the driver. Then, it sets a threshold range based on ratio of face images that show the first status and ratio of face images that show the second status. Then, it determines that the driver is in a careless driving state when the distribution range is included in the threshold range.

Abstract: An embodiment of the present invention provides a learning method, a learning apparatus, and a learning program for decomposing a two-dimensional X-ray image into a variety of regions, and an image processing method, an image processing apparatus, and an image processing program using a result of learning. A learning method according to an aspect of the present invention includes generating a masked CT image from a three-dimensional CT image, and generating a third pseudo X-ray image from the masked CT image. Then, a second pseudo X-ray image generated by projecting an original CT image is compared with the third pseudo X-ray image as a reference, and a parameter for use in generating the second pseudo X-ray image is updated based on a comparison result. A processor repeats the processing of each step until a predetermined condition is satisfied.

Abstract: The present disclosure achieves accurate tracking of sunlit orbital objects, including small, dim orbital debris, using a ground-based telescope and detector which tracks the orbital object. The angular position of the orbital object relative to background celestial objects is accurately determined over a trajectory, allowing accurate determination of the orbit parameters.

Abstract: In a method for enhancing accuracy and efficiency in automated visual inspection of vessels, a vessel containing a sample is oriented such that a line scan camera has a profile view of an edge of a stopper of the vessel. A plurality of images of the edge of the stopper is captured by the first line scan camera while spinning the vessel, where each image of the plurality of images corresponds to a different rotational position of the vessel. A two-dimensional image of the edge of the stopper is generated based on at least the plurality of images, and pixels of the two-dimensional image are processed, by one or more processors executing an inference model that includes a trained neural network, to generate output data indicative of a likelihood that the sample is defective.

Abstract: An output device including: a memory; and a processor coupled to the memory, the processor configured to: acquire a satellite image in which a target region is photographed and event information relating to events that have occurred in the target region; and output, from among roads in the target region, a road for which a safety degree calculated based on the satellite image and the event information is less than a threshold value.

Abstract: In an embodiment, an apparatus comprises one or more processors and one or more memories communicatively coupled to the one or more processors and storing instructions which, when processed by the one or more processors, cause: receiving a digital image of a particular item of mail and storing the digital image; causing data to be extracted from the digital image using Optical Character Recognition (OCR) or by processing encoded data; based on the extracted data, matching the particular item of mail to particular mailing data from the data stream; determining, based, at least in part, on the extracted data and the particular mailing data, one or more actions to take with respect to the particular item of mail and, in response, causing performance of the one or more actions.

Abstract: A method for predicting a scattered signal of an X-ray for an examination object includes: scanning each phantom in a scanning manner in which a scattering degree of each phantom in a plurality of phantoms is less than a reference scattering degree, so as to obtain first projection data of each phantom; scanning each phantom in a scanning manner in which the scattering degree of each phantom in the plurality of phantoms is equal to the reference scattering degree, so as to obtain second projection data of each phantom; obtaining a real scattered signal of each phantom by subtracting the first projection data of the phantom from the second projection data of the phantom; training a learning model based on the second projection data of each phantom and the real scattered signal of each phantom to obtain a trained learning model; and applying the trained learning model to projection data of the X-ray for the examination object to predict the scattered signal of the projection data of the X-ray.

Abstract: A facial expression-based detection method for deepfake by generative artificial intelligence (AI) constructs an AIR-Face facial dataset for generative AI-created face detection training, and uses an untrained information feature space for real and fake classification. Nearest linear detection is performed in this space to significantly improve the generalization ability of detecting fake images, especially those created by new methods such as diffusion models or autoregressive models. The detection method improves the performance of extracting features of generative AI-created faces through phased trainings, and detects generative AI-created faces through the feature space. Compared with other methods, the detection method scientifically and effectively improves the accuracy of generative AI-created face recognition, and fully mines the potential semantic information of generative AI-created faces through phased trainings.

Abstract: Systems and methods for image segmentation are described. Embodiments of the present disclosure receive a training image and a caption for the training image, wherein the caption includes text describing an object in the training image; generate a pseudo mask for the object using a teacher network based on the text describing the object; generate a mask for the object using a student network; compute noise information for the training image using a noise estimation network; and update parameters of the student network based on the mask, the pseudo mask, and the noise information.

Abstract: Disclosed herein is an image analysis system including a machine learning model configured to receive input of an image and to output an image feature quantity and a map source for image analysis, a map generation section configured to generate, on the basis of a vector corresponding to an object and the output map source, an attention map indicative of a region associated with the object in the image, and a token generation section configured to generate a token indicative of a feature associated with an event of the object on the basis of the generated attention map and the image feature quantity.

Abstract: An image processing arrangement (100) comprising a controller (101) configured to: a) receive (410) image data; b) perform semantic analysis (430) on the image data to c) identify (432)) a first region (R1) and a second region (R2) and to d) select (434) first settings (S1) and second settings (S2) corresponding to the identified first region (R1) and second region (R2) respectively; e) adapt (440) at least one filter (316, 314) according to the selected first and second settings (S1, S2, Sx); and f) perform (450) image processing on image data based on the adapted at least one filter (316, 314) wherein the first settings (S1) are applied to the at least one filter (316, 314) for the first region (R1) and the second settings (S2) are applied to the at least one filter (316, 314) for the second region (R2).

Abstract: Systems and methods for autofocus using artificial intelligence include (i) capturing a plurality of monochrome images over a nominal focus range, (ii) identifying one or more connected components within each monochrome image, (iii) sorting the identified connected components based on a number of pixels associated with each connected component, (iv) generating a focus quality estimate of at least a portion of the sorted connected components using a machine learning module, and (iv) calculating a target focus position based on the focus quality estimate of the evaluated connected components. The calculated target focus position can be used to perform cell counting using artificial intelligence, such as by (i) generating a seed likelihood image and a whole cell likelihood image based on output—a convolutional neural network and (ii) generating a mask indicative quantity and/or pixel locations of objects based on the seed likelihood image.

Abstract: Disclosed are a coronary artery segmentation method, an electronic device, and a computer-readable storage medium. The coronary artery segmentation method includes: iteratively performing a detection step for a to-be-detected image; for a plurality of the detection steps corresponding to the to-be-detected image, selecting the to-be-detected region in a current detection step from the replaced to-be-detected image in a previous detection step, and using a part of the comparison result in the previous detection step as the regional coronary artery inspiration data in the current detection step; and outputting a finally replaced to-be-detected image as coronary artery segmentation data. This method implements precise segmentation, and effectively distinguishes between a coronary artery and a vein false positive.

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive a training image and a caption for the training image, wherein the caption includes text describing an object in the training image; generate a pseudo mask for the object using a teacher network based on the text describing the object; generate a mask for the object using a student network; and update parameters of the student network based on the mask and the pseudo mask.

Abstract: The present disclosure provides a visual search engine (VSE) configured to perform visual searches. The VSE may receive a query image for searching through a plurality of images stored in a dataset. Different ones of the images stored in the dataset may be indexed or logically grouped together based on a fractal transform that associates images depicting similar content with each other. A fractal transform of the query image may be used to identify a plurality of images from the dataset to be searched based on the query image. A modified image triplet technique using the query image, a derived set of similar images, and a derived set of dissimilar images may be utilized to identify features of the images being searched. Search results logic of the VSE may apply deep learning techniques to the feature sets to identify a set of search results to return for the query image.

Abstract: A method of depth estimation, including, receiving an image frame, determining a relative depth map based on the image frame, receiving a sparse depth frame, preprocessing the sparse depth frame, determining a scale-adjusted relative depth map based on the relative depth map and the preprocessed sparse depth frame and fusing the relative depth map and the scale-adjusted relative depth map to produce an absolute depth map.

Abstract: Techniques for segmenting sensor data are discussed herein. Data can be represented in individual levels in a multi-resolution voxel space. A first level can correspond to a first region of an environment and a second level can correspond to a second region of an environment that is a subset of the first region. In some examples, the levels can comprise a same number of voxels, such that the first level covers a large, low-resolution region, while the second level covers a smaller, higher-resolution region, though more levels are contemplated. Operations may include analyzing sensor data represented in the voxel space from a perspective, such as a top-down perspective. From this perspective, techniques may generate masks that represent objects in the voxel space. Additionally, techniques may generate segmentation data to verify and/or generate the masks, or otherwise cluster the sensor data.

Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information via analysis of visual data of photos of a defined area, and for using the generated mapping information in further automated manners, including to display the generated mapping information via various types of visualizations corresponding graphical user interfaces. In some situations, the defined area includes an interior of a multi-room building, and the generated information includes at least a partial floor plan and/or other modeled representation of the building—in addition, the generating may be further performed without having measured depth information about distances from the photos' acquisition locations to walls or other objects in the surrounding building. The generated floor plan and/or other mapping-related information may be further used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), etc.

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive an image comprising a first region that includes content and a second region to be inpainted. Noise is then added to the image to obtain a noisy image, and a plurality of intermediate output images are generated based on the noisy image using a diffusion model trained using a perceptual loss. The intermediate output images predict a final output image based on a corresponding intermediate noise level of the diffusion model. The diffusion model then generates the final output image based on the intermediate output image. The final output image includes inpainted content in the second region that is consistent with the content in the first region.