Abstract: A method of mesoscopic photogrammetry can be carried out using a set of images captured from a camera on a mobile computing device. Upon receiving the set of images, the method generates a composite image, which can include applying homographic rectification to warp all images of the set of images onto a common plane; applying a rectification model to undo perspective distortion in each image of the set of images; and applying an undistortion model for adjusting for camera imperfections of a camera that captured each image of the set of images. A height map is generated co-registered with the composite image, for example, by using an untrained CNN whose weights/parameters are optimized in order to optimize the height map. The height map and the composite image can be output for display.

Abstract: Content-adaptive online training for end-to-end (E2E) neural image compression (NIC) using a neural network performed by at least one processor, is provided, including receiving an input image, to an E2E NIC framework, including one or more blocks, preprocessing a first neural network of the E2E NIC framework, based on the one or more blocks, computing updated parameters using the preprocessed first neural network, encoding the one or more blocks and the updated parameters, updating the first neural network based on the encoded updated parameters, and generating a compressed representation of the encoded one or more blocks using the updated first neural network.

Abstract: A method of processing a digital image for use by a digital image classifier comprises: processing the digital image with computational models of a retinal ganglion cell (RGC) to produce sets of digital image features; and combining the sets of digital image features to produce a multi-channel retina model image. The method may be used in digital image classification and in training a digital image classifier. The creation and use of multi-channel retina model images improves the ability to detect pertinent image features during image classification and so improves the overall classification process.

Abstract: Techniques related to automatically segmenting video frames into per pixel fidelity object of interest and background regions are discussed. Such techniques include applying tessellation to a video frame to generate feature frames corresponding to the video frame and applying a segmentation network implementing context aware skip connections to an input volume including the feature frames and a context feature volume corresponding to the video frame to generate a segmentation for the video frame.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that generate from a first pair and a second pair of images of livestock that are within an enclosure and that are taken at different times using a stereoscopic camera, at least two distance distributions of the aquatic livestock within the enclosure. The distance distributions can be used to determine a measure associated with an optical property of the water within the enclosure. A signal associated with the measure can be provided.

Abstract: According to one embodiment, a learning method of causing a statistical model for outputting a distance to a subject to learn by using an image including the subject as an input is provided. The method includes acquiring an image for learning including a subject having an already known shape, acquiring a first distance to the subject included in the image for learning, from the image for learning, and causing the statistical model to learn by restraining the first distance with the shape of the subject included in the image for learning.

Abstract: A method may include obtaining core image data regarding a geological region of interest. The method may further include obtaining well log data regarding the geological region of interest from one or more wells. The method may further include determining a sliding window that corresponds to a predetermined window size. The method may further include determining various quantitative image attributes using the core image data, the well log data, and the sliding window. The quantitative image attributes may be determined in a continuous manner by moving the sliding window along the core image data. The method may further include generating predicted rock data for the geological region of interest using the quantitative image attributes, a machine-learning algorithm, and a machine-learning model.

Abstract: A system and method for compressing and decompressing image data, which provides better compression and minimal representation of the input image with minimal loss compared to previous Deep Learning codecs. The system can provide for quantization during training, flexible addition of filters, and conditional complexity of image compression. The Deep Learning codec generates codes that are directly usable with Machine Learning algorithms, thus boosting the performance of Machine Learning algorithms.

Abstract: An image classification system is provided for determining a likely classification of an image using multiple machine learning models that share a base machine learning model. The image classification system may be a browser-based system on a user computing device that obtains multiple machine learning models over a network from a remote system once, stores the models locally in the image classification system, and uses the models multiple times without needing to subsequently request the machine learning models again from the remote system. The image classification system may therefore determine likely a classification associated with an image by running the machine learning models on a user computing device.

Abstract: A control device of a projection system including an optical system that projects an image generated in a display portion based on input image data to a projection object, and an imaging portion that images the projection object, includes: a distance determination portion that acquires first captured image data of the image projected to the projection object from the imaging portion and determines a distance from an object present between the projection object and the optical system to the optical system based on a first sharpness of a part or an entire part of the first captured image data and a second sharpness of the input image data.

Abstract: A computer vision system and method for detecting and modeling features of a building in a plurality of images is provided. The system includes at least one computer system in communication with a database of aerial imagery, and computer vision system code executed by the at last one computer system which automatically detects contours and infers interior roof features of the building. The system first processes the plurality of images to identify a plurality of two-dimensional (2D) line segments in each image. Then, the system processes the plurality of 2D line segments to generate a plurality of three-dimensional (3D) line segments. The plurality of 2D line segments are then processed to detect a contour of the structure, and the contour of the structure is utilized by the system to infer interior roof lines from the structure. A model of the roof of the structure is finally generated using the detected contour and interior roof lines.

Abstract: Systems, methods, devices, media, and computer-readable instructions are described for local image tagging and processing in a resource-constrained environment such as a mobile device. In some embodiments, characteristics associated with images are used to determine whether to store content (e.g., images and video clips) as ephemeral content or non-ephemeral content. Based on the determination, the image is stored in a non-ephemeral camera roll storage of the mobile device, or an ephemeral local application storage. Additional storage operations such as encryption or backup copying may additionally be determined and performed based on the analysis of the content. In some embodiments, such images may be indexed, sorted, and searched based on the image tagging operations used to characterize the content.

Abstract: An image display apparatus according to an embodiment of the present technology includes a display control unit and a processing executing unit. The display control unit controls display of a designation image capable of designating a region with respect to a target image. The processing executing unit executes processing associated with the designation image on a designated region designated by the designation image. The processing executing unit executes, on an overlap region in which a first designated region designated by a first designation image and a second designated region designated by a second designation image overlap with each other, first processing associated with the first designation image and second processing associated with the second designation image. The display control unit moves the second designation image in conjunction with movement of the first designation image when the overlap region exists.

Abstract: A system can comprise a processor that can facilitate performance of operations, comprising accessing a document comprising a plurality of text bounding boxes, wherein each respective text bounding box of the plurality of text bounding boxes comprises respective text, for each respective text bounding box, determining respective text bounding box coordinates and respective text bounding box input embeddings, based on the respective text bounding box coordinates, determining respective text bounding box positional encodings for each respective text bounding box, based on a transformer-based deep learning model applied to the respective text bounding box input embeddings, respective text bounding box coordinates, respective text bounding box positional encodings, and bias information representative of a modification to an attention weight of the transformer-based deep learning model, determining respective output embeddings for each respective text bounding box, and based on the respective output embeddings, ge

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods for utilizing a machine learning model trained to determine subtle pose differentiations to analyze a repository of captured digital images of a particular user to automatically capture digital images portraying the user. For example, the disclosed systems can utilize a convolutional neural network to determine a pose/facial expression similarity metric between a sample digital image from a camera viewfinder stream of a client device and one or more previously captured digital images portraying the user. The disclosed systems can determine that the similarity metric satisfies a similarity threshold, and automatically capture a digital image utilizing a camera device of the client device. Thus, the disclosed systems can automatically and efficiently capture digital images, such as selfies, that accurately match previous digital images portraying a variety of unique facial expressions specific to individual users.

Abstract: A neural network system that includes: multiple subnetworks that includes: a first subnetwork including multiple first modules, each first module including: a pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a pass-through output; an average pooling stack of neural network layers that collectively processes the subnetwork input for the first subnetwork to generate an average pooling output; a first stack of convolutional neural network layers configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output; a second stack of convolutional neural network layers that are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and a concatenation layer configured to concatenate the pass-through output, the average pooling output, the first stack output, and the second stack output to generate a first module output for the first module.

Abstract: A device, method, and non-transitory computer readable medium are described. The method includes receiving a dataset including hand written Arabic words and hand written Arabic alphabets from one or more users. The method further includes removing whitespace around alphabets in the hand written Arabic words and the hand written Arabic alphabets in the dataset. The method further includes splitting the dataset into a training set, a validation set, and a test set. The method further includes classifying one or more user datasets from the training set, the validation set, and the test set. The method further includes identifying the target user from the one or more user datasets. The identification of the target user includes a verification accuracy of the hand written Arabic words being larger than a verification accuracy threshold value.

Abstract: A system includes: an image sensor configured to acquire an image; an image processor configured to generate a quantized image based on the acquired image using a trained quantization filter; and an output interface configured to output the quantized image.

Abstract: Methods and systems are provided for assessing the presence of functionally significant stenosis in one or more coronary arteries, further known as a severity of vessel obstruction. The methods and systems can implement a prediction phase that comprises segmenting at least a portion of a contrast enhanced volume image data set into data segments corresponding to wall regions of the target organ, and analyzing the data segments to extract features that are indicative of an amount of perfusion experiences by wall regions of the target organ. The methods and systems can obtain a feature-perfusion classification (FPC) model derived from a training set of perfused organs, classify the data segments based on the features extracted and based on the FPC model, and provide, as an output, a prediction indicative of a severity of vessel obstruction based on the classification of the features.

Abstract: A device, method, and non-transitory computer readable medium are described. The method includes receiving a dataset including hand written Arabic words and hand written Arabic alphabets from one or more users. The method further includes removing whitespace around alphabets in the hand written Arabic words and the hand written Arabic alphabets in the dataset. The method further includes splitting the dataset into a training set, a validation set, and a test set. The method further includes classifying one or more user datasets from the training set, the validation set, and the test set. The method further includes identifying the target user from the one or more user datasets. The identification of the target user includes a verification accuracy of the hand written Arabic words being larger than a verification accuracy threshold value.