Abstract: Systems and methods for identifying and segmenting objects from images include a preprocessing module configured to adjust a size of a source image; a region-proposal module configured to propose one or more regions of interest in the size-adjusted source image; and a prediction module configured to predict a classification, bounding box coordinates, and mask. Such systems and methods may utilize end-to-end training of the modules using adversarial loss, facilitating the use of a small training set, and can be configured to process historical documents, such as large images comprising text. The preprocessing module within the systems and methods can utilize a conventional image scaler in tandem with a custom image scaler to provide a resized image suitable for GPU processing, and the region-proposal module can utilize a region-proposal network from a single-stage detection model in tandem with a two-stage detection model paradigm to capture substantially all particles in an image.

Abstract: Systems and methods for identifying and segmenting objects from images include a preprocessing module configured to adjust a size of a source image; a region-proposal module configured to propose one or more regions of interest in the size-adjusted source image; and a prediction module configured to predict a classification, bounding box coordinates, and mask. Such systems and methods may utilize end-to-end training of the modules using adversarial loss, facilitating the use of a small training set, and can be configured to process historical documents, such as large images comprising text. The preprocessing module within said systems and methods can utilize a conventional image scaler in tandem with a custom image scaler to provide a resized image suitable for GPU processing, and the region-proposal module can utilize a region-proposal network from a single-stage detection model in tandem with a two-stage detection model paradigm to capture substantially all particles in an image.

Abstract: OCR-text correction system and method embodiments are described. The OCR-text correction embodiments comprise or cooperate with a transformer-based sequence-to-sequence language model. The model is pretrained to denoise corrupted text and is fine-tuned using OCR-correction-specific examples. Text obtained at least in part through OCR is applied to the fine-tuned pretrained transformer model to detect at least one error in a subset of the text. Responsive to detecting the at least one error, the fine-tuned pretrained transformer model outputs an updated subset of the text to correct the at least one error.

Abstract: Disclosed herein relates to example embodiments for recognizing handwritten information in a genealogical record. A computing server may receive a genealogical record. The genealogical record may take the form of an image of a physical form having a structured layout, fields, and handwritten information. The computing server may divide the genealogical record into a plurality of areas based on the structured layout. The computing server may identify, for a particular area, a type of field that is included within the particular area. The computing server may select a handwriting recognition model for identifying the handwritten information in the particular area. The handwriting recognition model may be selected based on the type of the field. The computing server may input an image of the particular area to the handwriting recognition model to generate text of the handwritten information. The computing server may store the text of the handwritten information.

Abstract: A simplified handwriting recognition approach includes a first network comprising convolutional neural network comprising one or more convolutional layers and one or more max-pooling layers. The first network receives an input image of handwriting and outputs an embedding based thereon. A second network comprises a network of cascaded convolutional layers including one or more subnetworks configured to receive an embedding of a handwriting image and output one or more character predictions. The subnetworks are configured to downsample and flatten the embedding to a feature map and then a vector before passing the vector to a dense neural network for character prediction. Certain subnetworks are configured to concatenate an input embedding with an upsampled version of the feature map.

Abstract: Systems and methods for handwriting recognition using language modeling facilitate improved results by using a trained language model to improve results from a handwriting recognition machine learning model. The language model may be a character-based language model trained on a dataset pertinent to field values on which the handwriting recognition model is to be used. A loss prediction module may be trained with the handwriting recognition model and/or the language model and used to determine whether a prediction from the handwriting recognition model should be refined by passing the prediction through the trained language model.

Abstract: Systems and methods for identifying and segmenting objects from images include a preprocessing module configured to adjust a size of a source image; a region-proposal module configured to propose one or more regions of interest in the size-adjusted source image; and a prediction module configured to predict a classification, bounding box coordinates, and mask. Such systems and methods may utilize end-to-end training of the modules using adversarial loss, facilitating the use of a small training set, and can be configured to process historical documents, such as large images comprising text. The preprocessing module within said systems and methods can utilize a conventional image scaler in tandem with a custom image scaler to provide a resized image suitable for GPU processing, and the region-proposal module can utilize a region-proposal network from a single-stage detection model in tandem with a two-stage detection model paradigm to capture substantially all particles in an image.