Abstract: Various embodiments described herein utilize multiple levels of generative adversarial networks (GANs) to facilitate generation of digital images based on user-provided images. Some embodiments comprise a first generative adversarial network (GAN) and a second GAN coupled to the first GAN, where the first GAN includes an image generator and at least two discriminators, and the second GAN includes an image generator and at least one discriminator. According to some embodiments, the (first) image generator of the first GAN is trained by processing a user-provided image using the first GAN. For some embodiments, the user-provided image and the first generated image, generated by processing the user-provided image using the first GAN, are combined to produce a combined image. For some embodiments, the (second) image generator of the second GAN is trained by processing the combined image using the second GAN.

Abstract: A computer system is provided comprising a classification model management server computer configured, by instructions, to: receive a new image from a user device; apply a first digital model to first regions within the new image for classifying each of the first regions into a particular class; apply a second digital model to second regions within the new image for classifying each of the second regions into a particular class; and transmit classification data related to the class of the first regions and the class of the second regions to the user device. In connection therewith, the second regions each generally correspond to a combination of multiple first regions.

Abstract: An electronic device includes an input configured to receive a signature from a user; a communication interface configured to communicate with a server; and a controller configured to classify the signature into at least one stroke, to transmit authentication information for the at least one stroke to the server, and to control the communication interface to receive a result of authentication of the signature from the server.

Abstract: Systems, methods, and computer program products for performing semi-supervised contrastive learning of visual representations are provided. For example, the present disclosure provides systems and methods that leverage particular data augmentation schemes and a learnable nonlinear transformation between the representation and the contrastive loss to provide improved visual representations. Further, the present disclosure also provides improvements for semi-supervised contrastive learning.

Abstract: To perform 3-dimensional interpolation, a 3-dimensional model of an input text character is generated. For example, a 2-dimensional character may be given depth using an extrusion transformation. The 3-dimensional model of the input text character is compared to 3-dimensional models of candidate characters and the results of the 3-dimensional comparisons are used to select the optical character recognition (OCR) output for the input text character. The 3-dimensional comparison may be performed directly on the 3-dimensional models. Alternatively, a set of 2-dimensional images may be generated for each 3-dimensional model and 2-dimensional comparisons performed. By use of the additional information gathered from the comparisons of the 3-dimensional models, the correct OCR output character can be identified with greater confidence.

Abstract: A text extraction computing method that comprises calculating an estimated character pixel height of text from a digital image. The method may scale the digital image using the estimated character pixel height and a preferred character pixel height. The method may binarizes the digital image. The method may remove distortions using a neural network trained by a cycle GAN on a set of source text images and a set of clean text images. The set of source text images and clean text images are unpaired. The source text images may be distorted images of text. Calculating the estimated character pixel height may include summarizing the rows of pixels into a horizontal projection, and determining a line-repetition period from the projection, and quantifying the portion of the line-repetition period that corresponds to the text as the estimated character pixel height. The method may extract characters from the digital image using OCR.

Abstract: A processor may receive an image and identify a plurality of characters in the image using a machine learning (ML) model. The processor may generate at least one word-level bounding box indicating one or more words including at least a subset of the plurality of characters and/or may generate at least one field-level bounding box indicating at least one field including at least a subset of the one or more words. The processor may overlay the at least one word-level bounding box and the at least one field-level bounding box on the image to form a masked image including a plurality of optically-recognized characters and one or more predicted fields for at least a subset of the plurality of optically-recognized characters.

Abstract: A computing device may access visually rich documents comprising an image and metadata. A graph, based on the image or metadata, can be generated for a visually rich document. The graph's nodes can correspond to words from the visually rich document. Features for nodes can be determined by the device. The device may generate model labeled graphs by assigning a pseudo-label to nodes using a pretrained model. The device may generate a plurality of graph labeled graphs by assigning a pseudo-label to nodes by matching a first node from a first graph to at least a second node from a second graph. The device may generate a plurality of updated graphs by cross referencing labels from the model labeled graphs and the graph labeled graphs. Until a change in labels is below a threshold, a model can be trained to perform key-value extraction using the updated graphs.

Abstract: Techniques for assuring the quality of mobile document image captured using a mobile device are provided. These techniques include performing one or more tests to assess the quality of images of documents captured using the mobile device. The tests can be selected based on the type of document that was imaged, the type of mobile application for which the image quality of the mobile image is being assessed, and/or other parameters such as the type of mobile device and/or the characteristics of the camera of the mobile device that was used to capture the image. The image quality assurance techniques can also be implemented on can be implemented on a mobile device and/or on a remote server where the mobile device routes the mobile image to the remote server processing and the test results are be passed from the remote server to the mobile device.

Abstract: Provided are a method and device for image processing, a terminal device and a storage medium. The method includes: a high-brightness region is determined based on brightness of pixels in a first image, the brightness of the pixels in the high-brightness region being higher than the brightness of the pixels around the high-brightness region; a diffraction region in the first image is determined based on the high-brightness region, the diffraction region being an image region around the high-brightness region; and brightness of the diffraction region is reduced to obtain a second image. Through the method, after the brightness of the diffraction region is reduced, an overlap image formed by diffraction is alleviated, and the image is more real.

Abstract: A delivery system may include a pallet wrapper system having a turntable, a camera directed toward an area above the turntable, and a stretch wrap dispenser adjacent the turntable. A computer receives images from the camera of multiple sides of a pallet loaded with packages on the turntable. The computer stitches images from different sides of the stack of packages that correspond to the same package. At least one machine learning model may be used to infer SKUs of each package. Optical character recognition may be performed in parallel on the images. The determination of the SKU of each package may be based upon the inferred SKUs and on the OCR.

Abstract: Aspects of the disclosure provide for mechanisms for identification of table partitions in documents using neural networks. A method of the disclosure includes obtaining a plurality of symbol sequences of a document having at least one table, determining a plurality of vectors representative of symbol sequences having at least one alphanumeric character or a table graphics element, processing the plurality of vectors using a first neural network to obtain a plurality of recalculated vectors, determining an association between a first recalculated vector and a second recalculated vector, wherein the first recalculated vector is representative of an alphanumeric sequence and the second recalculated vector is associated with a table partition, and determining, based on the association between the first recalculated vector and the second recalculated vector, an association between the alphanumeric sequence and the table partition.

Abstract: Embodiments herein disclose a method and electronic device for predicting multi-modal drawings. The method includes: receiving, by the electronic device, at least one of a text input and strokes of a drawing and determining, by the electronic device, features associated with the text input and features associated with the strokes of the drawing. The method includes classifying, by the electronic device, the features associated with the text input and the features associated with the strokes of the drawing into one of a dominant feature and a non-dominant feature and performing, by the electronic device, early concatenation or late concatenation of the features based on the classification; classifying, by the electronic device, the strokes of the drawing based on the concatenation into a category using a deep neural network (DNN) model; and predicting, by the electronic device, primary drawings corresponding to the category.

Abstract: Systems and methods are provided for the denoising of images in the presence of broadband noise based on the detection and/or estimation of in-band noise. According to various example embodiments, an estimate of broadband noise that lies within the imaging band is made by detecting or characterizing the out-of-band noise that lies outside of the imaging band. This estimated in-band noise may be employed for denoise the detected imaging waveform. According to other example embodiments, a reference receive circuit that is sensitive to noise within the imaging band, but is isolated from the imaging energy, may be employed to detect and/or characterize the noise within the imaging band. The estimated reference noise may be employed to denoise the detected in-band imaging waveform.

Abstract: In some examples, a system for detecting text in an image includes a memory device to store a text detection model trained using images of up-scaled text, and a processor configured to perform text detection on an image to generate original bounding boxes that identify potential text in the image. The processor is also configured to generate a secondary image that includes up-scaled portions of the image associated with bounding boxes below a threshold size, and perform text detection on the secondary image to generate secondary bounding boxes that identify potential text in the secondary image. The processor is also configured to compare the original bounding boxes with the secondary bounding boxes to identify original bounding boxes that are false positives, and generate an image file that includes the original bounding boxes, wherein those original bounding boxes that are identified as false positives are removed.

Abstract: A display device, including a content receiving unit configured to receive a high dynamic range image, an image processing unit configured to detect a first region whose luminance value is equal to or greater than a reference luminance value within the high dynamic range image and perform tone mapping on an image of the first region based on feature information of the image of the first region, and a display unit configured to display a low dynamic range image on which the tone mapping is performed.

Abstract: Aspects of the subject disclosure may include, for example, performing, by a processing system, image fusion using two or more groups of images to generate predicted images, wherein each group of the two or more groups has one of a different resolution, a different frequency temporal pattern or a combination thereof than another of the two or more groups. Gap filling can be performed by the processing system to correct images of the two or more groups. Additional embodiments are disclosed.

Abstract: A method for coding information of a point cloud comprises obtaining the point cloud including a set of points in a three-dimensional space; partitioning the point cloud into a plurality of objects and generating occupancy information for each of the plurality of objects; and encoding the occupancy information by taking into account the distance between the plurality of objects.

Abstract: Provided are systems and methods for synthesizing novel views of complex scenes (e.g., outdoor scenes). In some implementations, the systems and methods can include or use machine-learned models that are capable of learning from unstructured and/or unconstrained collections of imagery such as, for example, “in the wild” photographs. In particular, example implementations of the present disclosure can learn a volumetric scene density and radiance represented by a machine-learned model such as one or more multilayer perceptrons (MLPs).

Abstract: A system includes an image sensor, an imaging pipeline, and a display device. The image sensor is configured to capture a first frame of pixel data. The imaging pipeline is coupled to the image sensor to receive the first frame of pixel data. The imaging pipeline includes an adaptive noise filter. The adaptive noise filter is configured to filter a pixel based on noise in the pixel. The imaging pipeline is configured to output a second frame of pixel data. The second frame of pixel data includes pixels filtered by the adaptive noise filter. The display device is coupled to the imaging pipeline to receive the second frame of pixel data. The display device is configured to display the second frame of pixel data.