A system and methods for selecting a region of pixels in an image displayed on a touch-sensitive interface is disclosed. The method for selecting the region of pixels is based on determined connectivity of pixels in the image indicating content of the image and includes determining connected pixels on the image representing the content without performing character recognition, detecting a text selection gesture indicative of selecting the region in the image, determining coordinates of the text selection gesture performed on the touch-sensitive interface and selecting the region in the image by bounding a first set of pixels located at a proximity from the coordinates of the text selection gesture.

In an image processing apparatus, a character recognizing unit identifies a character image in a document image. A font matching unit determines a character code and a font type corresponding to the identified character image. A fore-and-background setting unit sets the document image as a background image and sets a standard character image based on the determined character code and the determined font type. A background image correcting unit (a) deletes a deletion area in the background image, the deletion area taking a same position as the character image or the standard character image, (b) interpolates a differential area between the character image and the standard character image in a specific neighborhood area that contacts with the deletion area on the basis of the background image, and (c) interpolates the deletion area on the basis of the back ground image.

A apparatus and method are provided for processing images. In one embodiment, the apparatus includes an image sensor configured to capture real time images from an environment of a user. The apparatus also includes a mobile power source, and at least one processor device configured to process, at an initial resolution, images to determine existence of a trigger, and access rules associating image context with image capture resolution to enable images of a first context to be processed at a lower capture resolution than images of a second context. The processor device analyzes at least one first image, selects a first image capture resolution rule, and applies the first image capture resolution rule to a subsequent captured image. The processor device analyzes at least one second image, selects a second image capture resolution rule, and applies the second image capture resolution rule to a second subsequent captured image.

An object-extraction method includes generating multiple partition objects based on an electronic document, and receiving a first user selection of a data element via a user interface of a compute device. In response to the first user selection, and using a machine learning model, a first subset of partition objects from the multiple partition objects is detected and displayed via the user interface. A user interaction, via the user interface, with one of the partition objects is detected, and in response, a weight of the machine learning model is modified, to produce a modified machine learning model. A second user selection of the data element is received via the user interface, and in response and using the modified machine learning model, a second subset of partition objects from the multiple partition objects is detected and displayed via the user interface, the second subset different from the first subset.

Example embodiments that analyze images to characterize aspects of the images rely on a same neural network to characterize multiple aspects in parallel. Because additional neural networks are not required for additional aspects, such an approach scales with increased aspects.

Provided are a computer program product, system, and method for training and using a vector encoder to determine vectors for sub-images of text in an image to subject to optical character recognition. A vector encoder is trained to encode images representing text into vectors in a vector space. Vectors of images representing similar text have a high degree of cohesion in the vector space. Vectors of images representing dissimilar text have a low degree of cohesion in the vector space. An input image is processed to determine sub-images of the input image that bound text represented in the input image. The sub-images are inputted to the vector encoder to output sub-image vectors. The vector encoder generates a search vector for search text. Optical character recognition is applied to at least one region of the input image including the sub-images having sub-image vectors matching the search vector.

A spatial alignment computer system for string alignment within a document processed using an optical character recognition (OCR) tool is provided. The computer system includes a processor in communication with a memory, wherein the processor is programmed to receive a plurality of bounding boxes of a document scanned using an OCR tool, identify a centroid of each bounding box of the plurality of bounding boxes, calculate coordinates for each centroid of each bounding box of the plurality of bounding boxes using a weighted Euclidean distance approach, sort the weighted Euclidean distance of the centroid of each bounding box in ascending order to obtain a sorting index, and based upon the sorting index, align one or more output strings associated with each bounding box of the plurality of bounding boxes.