Abstract: A method of document image processing comprises, based on at least a document page image, generating a plurality of semantic tokens that includes a plurality of word tokens and a plurality of special tokens. Each special token among the plurality of special tokens represents a non-textual semantic element of the document image, and generating the plurality of semantic tokens includes predicting, for each special token among the plurality of special tokens, a token type of the special token. The method also comprises generating, for each semantic token among the plurality of semantic tokens, a corresponding semantic token embedding among a plurality of semantic token embeddings; and applying a trained model to process an input that is based on the plurality of semantic token embeddings and a plurality of visual token embeddings based on at least the document page image to generate a semantic processing result.

Abstract: In some embodiments, techniques for document entity extraction are provided. For example, a process may involve processing document images to detect a plurality of regions of interest that includes text objects and non-text objects; for each of the plurality of regions of interest, producing a corresponding text string; and processing the text strings to identify entities. Processing the document images may involve applying a text object detection model to the document images to detect the text objects; and applying at least one non-text object detection model to the document images to detect the non-text objects. Prior to processing the document images, at least two object detection models among the text object detection model and the at least one non-text object detection model were generated by fine-tuning respective instances of a pre-trained object detection model.

Abstract: A computer-implemented method includes accessing, by a processor, an unstructured document. The method also includes performing, by the processor, box detection on the unstructured document to generate a box graph of the unstructured document. Further, the method includes integrating, by the processor, identified text of the unstructured document with the box graph of the unstructured document to build a text graph. Furthermore, the method includes generating, by the processor, a structured text representation of the unstructured document using the text graph.

Abstract: A computer-implemented method, includes accessing, by a processor, a set of asset documents. The method also includes performing, by the processor, feature extraction on text of each document of the set of asset documents using a feature extraction module to generate a set of features, where each feature of the set of features represents a document of the set of asset documents. The method also includes generating, by the processor, a set of lower-dimensional features from the set of features using a singular value decomposition module. The method also includes generating, by the processor, a set of clusters from the set of lower-dimensional features using a clustering module. The method also includes training, by the processor, a machine-learning model of a classification microservice using the set of clusters generated from the clustering module.

Abstract: A display system that can be calibrated and re-calibrated with a minimal amount of manual intervention. To accomplish this, one or more cameras are provided to capture an image of the display screen. The resulting captured image is processed to identify any non-desirable characteristics, including visible artifacts such as seams, bands, rings, etc. Once the non-desirable characteristics are identified, an appropriate transformation function is determined. The transformation function is used to pre-warp the input video signal that is provided to the display such that the non-desirable characteristics are reduced or eliminated from the display. The transformation function preferably compensates for spatial non-uniformity, color non-uniformity, luminance non-uniformity, and other visible artifacts.

Abstract: A display system that can be calibrated and re-calibrated with a minimal amount of manual intervention. To accomplish this, one or more cameras are provided to capture an image of the display screen. The resulting captured image is processed to identify any non-desirable characteristics, including visible artifacts such as seams, bands, rings, etc. Once the non-desirable characteristics are identified, an appropriate transformation function is determined. The transformation function is used to pre-warp the input video signal that is provided to the display such that the non-desirable characteristics are reduced or eliminated from the display. The transformation function preferably compensates for spatial non-uniformity, color non-uniformity, luminance non-uniformity, and other visible artifacts.

Abstract: A display system that can be calibrated and re-calibrated with a minimal amount of manual intervention. To accomplish this, one or more cameras are provided to capture an image of the display screen. The resulting captured image is processed to identify any non-desirable characteristics, including visible artifacts such as seams, bands, rings, etc. Once the non-desirable characteristics are identified, an appropriate transformation function is determined. The transformation function is used to pre-warp the input video signal that is provided to the display such that the non-desirable characteristics are reduced or eliminated from the display. The transformation function preferably compensates for spatial non-uniformity, color non-uniformity, luminance non-uniformity, and other visible artifacts.

Abstract: The present invention overcomes many of the disadvantages of the prior art by providing a display that can be calibrated and re-calibrated with a minimal amount of manual intervention. To accomplish this, the present invention provides one or more cameras to capture an image that is projected on a display screen. In one embodiment, the one or more cameras are placed on the same side of the screen as the projectors. In another embodiment, an array of cameras is provided on either or both sides of the screen for capturing a number of adjacent and/or overlapping capture images of the screen. In either of these embodiments, the resulting capture images are processed to identify any non-desirable characteristics including any visible artifacts such as seams, bands, rings, etc. Once the non-desirable characteristics are identified, an appropriate transformation function is determined.