Abstract: Aspects of the disclosure provide for mechanisms for identification of objects in images using neural networks. A method of the disclosure includes: obtaining an image, representing each element of a plurality of elements of the image via an input vector of a plurality of input vectors, each input vector having one or more parameters pertaining to visual appearance of a respective element of the image, providing the plurality of input vectors to a first subnetwork of a neural network to obtain a plurality of output vectors, wherein each of the plurality of output vectors is associated with an element of the image, identifying, based on the plurality of output vectors, a sub-plurality of elements of the image as belonging to the image of the object, and determining, based on locations of the sub-plurality of elements, a location of an image of an object within the image.

Abstract: There is disclosed a method of determining a digital document suitability for OCR processing, the method executable by a user electronic device, the user electronic device configured for capturing a digital image of a document. The method comprises: acquiring by the user electronic device, the digital image of the document; determining, by a classifier executed by the user electronic device, an OCR suitability parameter associated with the digital image, the OCR suitability parameter indicative of whether the digital image is suitable for producing an output of the OCR processing of an acceptable quality, the classifier having been trained to determine the OCR suitability parameter at least partially based on a level of noise associated with the digital image; in response to the OCR suitability parameter being below a pre-determined threshold, causing the user electronic device to re-acquire the digital image.

Abstract: Systems and methods for reconstructing a document from a series of document images. An example method comprises: receiving a plurality of image frames, wherein each image frame of the plurality of image frames contains at least a part of an image of an original document; identifying a plurality of visual features in the plurality of image frames; performing spatial alignment of the plurality of image frames based on matching the identified visual features; splitting each of the plurality of image frames into a plurality of image fragments; identifying one or more text-depicting image fragments among the plurality of image fragments; associating each identified text-depicting image fragment with an image frame in which that image fragment has an optimal value of a pre-defined quality metric among values of the quality metric for that image fragment in the plurality of image frames; and producing a reconstructed image frame by blending image fragments from the associated image frames.

Abstract: The current document is directed to methods and systems that straighten curvature in the text lines of text-containing digital images, including text-containing digital images generated from the two pages of an open book. Initial processing of a text-containing image identifies the outline of a text-containing page. Next, contours are generated to represent each text line. The midpoints and inclination angles of the links or vectors that comprise the contour lines are determined. A model is constructed for the perspective-induced curvature within the text image. In one implementation, the model, essentially an inclination-angle map, allows for assigning local displacements to pixels within the page image which are then used to straighten the text lines in the text image. In another implementation, the model is essentially a pixel-displacement map which is used to straighten the text lines in the text image.

Abstract: Systems and methods for generating document image marking are disclosed. An example method comprises: identifying key points in each of a plurality of images; adding each image to one or more clusters, the adding comprising adding the key points one or more indices associated with the clusters wherein a minimum number of the key points correspond to key points in the indices; analyzing each of the images of the cluster as a candidate image by generating a marking along the boundaries of a document within a candidate image; verifying the marking by comparing the marking with boundaries of documents depicted within a number of other images in the cluster; and selecting the candidate image as the reference image when the marking is verified more than a predetermined number of times; and detecting a document marking along the boundaries of a document depicted within an input image using the reference image.

Abstract: Systems and methods for reconstructing a document from a series of document images. An example method comprises: receiving a plurality of image frames, wherein each image frame of the plurality of image frames contains at least a part of an image of an original document; identifying a plurality of visual features in the plurality of image frames; performing spatial alignment of the plurality of image frames based on matching the identified visual features; splitting each of the plurality of image frames into a plurality of image fragments; identifying one or more text-depicting image fragments among the plurality of image fragments; associating each identified text-depicting image fragment with an image frame in which that image fragment has an optimal value of a pre-defined quality metric among values of the quality metric for that image fragment in the plurality of image frames; and producing a reconstructed image frame by blending image fragments from the associated image frames.

Abstract: There is disclosed a method of analyzing a digital image of a document (to determine, as example, a document suitability for server-based OCR processing) in a computer system that includes a user electronic device (for acquiring or storing a digital image of a document) connectable to a server (for executing the server-based OCR processing of the digital image to create a recognized-text document). The method is executable by the user electronic device and comprises: acquiring the digital image of the document; analyzing an OCR quality parameter associated with a compressed digital image to be created from the digital image using a compression algorithm and a compression parameter; in response to the OCR quality parameter being above or equal to a pre-determined threshold: transmitting the compressed digital image to the server.

Abstract: There is disclosed a method of determining a digital document suitability for OCR processing, the method executable by a user electronic device, the user electronic device configured for capturing a digital image of a document. The method comprises: acquiring by the user electronic device, the digital image of the document; determining, by a classifier executed by the user electronic device, an OCR suitability parameter associated with the digital image, the OCR suitability parameter indicative of whether the digital image is suitable for producing an output of the OCR processing of an acceptable quality, the classifier having been trained to determine the OCR suitability parameter at least partially based on a level of noise associated with the digital image; in response to the OCR suitability parameter being below a pre-determined threshold, causing the user electronic device to re-acquire the digital image.

Abstract: There is disclosed a method of analyzing a digital image of a document (to determine, as example, a document suitability for server-based OCR processing) in a computer system that includes a user electronic device (for acquiring or storing a digital image of a document) connectable to a server (for executing the server-based OCR processing of the digital image to create a recognized-text document). The method is executable by the user electronic device and comprises: acquiring the digital image of the document; analyzing an OCR quality parameter associated with a compressed digital image to be created from the digital image using a compression algorithm and a compression parameter; in response to the OCR quality parameter being above or equal to a pre-determined threshold: transmitting the compressed digital image to the server.

Abstract: The current document is directed to methods and systems that straighten curvature in the text lines of text-containing digital images, including text-containing digital images generated from the two pages of an open book. Initial processing of a text-containing image identifies the outline of a text-containing page. Next, contours are generated to represent each text line. The midpoints and inclination angles of the links or vectors that comprise the contour lines are determined. A model is constructed for the perspective-induced curvature within the text image. In one implementation, the model, essentially an inclination-angle map, allows for assigning local displacements to pixels within the page image which are then used to straighten the text lines in the text image. In another implementation, the model is essentially a pixel-displacement map which is used to straighten the text lines in the text image.

Abstract: Systems and method for improving the quality of document images are provided. One method includes identifying a plurality of image fragments within a previously received document image that includes text. The method further includes separating the plurality of image fragments into a plurality of classes. Each class includes a subset of the plurality of image fragments that are substantially similar to one another. The method further includes, for each of the plurality of classes: (1) processing a class of image fragments to generate a combined and substantially enlarged image fragment for the class; and (2) filtering the combined and substantially enlarged image fragment to generate a filtered image fragment for the class. The method further includes generating an improved document image by replacing or modifying the image fragments within the document image based on the filtered image fragments.

Abstract: Systems and methods for improving the quality of recognition of the object based on a series of frame images of objects are described herein. A plurality of images depicting the same object are received. A first image is selected from the plurality of images. The first image may be an image with the highest quality from plurality of images. For each image in the plurality of images, motion estimation of elements of an image in the plurality of images and the first image is performed. Based on the results of motion estimation, motion compensation and signal accumulation of the object in the images in the plurality of images using the first image are performed. A high resolution image of the object obtained based on the motion compensation and signal accumulation is generated. Character recognition on the resulting high resolution image is performed.

Abstract: Systems and method for improving the quality of document images are provided. One method includes identifying a plurality of image fragments within a previously received document image that includes text. The method further includes separating the plurality of image fragments into a plurality of classes. Each class includes a subset of the plurality of image fragments that are substantially similar to one another. The method further includes, for each of the plurality of classes: (1) processing a class of image fragments to generate a combined and substantially enlarged image fragment for the class; and (2) filtering the combined and substantially enlarged image fragment to generate a filtered image fragment for the class. The method further includes generating an improved document image by replacing or modifying the image fragments within the document image based on the filtered image fragments.

Abstract: Methods, devices, and systems for capturing documents are provided. A frame in a viewfinder is selected and is converted into a binary version. Segmentation of the binarized version of the frame is performed using computed horizontal and vertical histograms. At least one document is identified in the selected frame. The at least one document is captured upon determining that values of the one or more parameters associated with the document match predetermined values of corresponding one or more parameters.

Abstract: Systems and method for improving the quality of document images are provided. One method includes identifying a plurality of image fragments within a previously received document image that includes text. The method further includes separating the plurality of image fragments into a plurality of classes. Each class includes a subset of the plurality of image fragments that are substantially similar to one another. The method further includes, for each of the plurality of classes: (1) processing a class of image fragments to generate a combined and substantially enlarged image fragment for the class; and (2) filtering the combined and substantially enlarged image fragment to generate a filtered image fragment for the class. The method further includes generating an improved document image by replacing or modifying the image fragments within the document image based on the filtered image fragments.

Abstract: Systems and method for improving the quality of document images are provided. One method includes identifying a plurality of image fragments within a previously received document image that includes text. The method further includes separating the plurality of image fragments into a plurality of classes. Each class includes a subset of the plurality of image fragments that are substantially similar to one another. The method further includes, for each of the plurality of classes: (1) processing a class of image fragments to generate a combined and substantially enlarged image fragment for the class; and (2) filtering the combined and substantially enlarged image fragment to generate a filtered image fragment for the class. The method further includes generating an improved document image by replacing or modifying the image fragments within the document image based on the filtered image fragments.

Abstract: Methods, devices, and systems for capturing documents are provided. A frame in a viewfinder is selected and is converted into a binary version. Segmentation of the binarized version of the frame is performed using computed horizontal and vertical histograms. At least one document is identified in the selected frame. The at least one document is captured upon determining that values of the one or more parameters associated with the document match predetermined values of corresponding one or more parameters.

Abstract: Systems and methods for improving the quality of recognition of the object based on a series of frame images of objects are described herein. A plurality of images depicting the same object are received. A first image is selected from the plurality of images. The first image may be an image with the highest quality from plurality of images. For each image in the plurality of images, motion estimation of elements of an image in the plurality of images and the first image is performed. Based on the results of motion estimation, motion compensation and signal accumulation of the object in the images in the plurality of images using the first image are performed. A high resolution image of the object obtained based on the motion compensation and signal accumulation is generated. Character recognition on the resulting high resolution image is performed.