Abstract: A computer-implemented method of detecting an object depicted in a digital image includes: detecting a plurality of identifying features of the object, wherein the plurality of identifying features are located internally with respect to the object; projecting a location of region(s) of interest of the object based on the plurality of identifying features, where each region of interest depicts content; building and/or selecting an extraction model configured to extract the content based at least in part on: the location of the region(s) of interest, the of identifying feature(s), or both; and extracting the some or all of the content from the digital image using the extraction model. Corresponding system and computer program product embodiments are disclosed. The inventive concepts enable reliable extraction of data from digital images where portions of an object are obscured/missing, and/or depicted on a complex background.

Abstract: A method of detecting an object depicted in a digital image includes: detecting a plurality of identifying features of the object, wherein the plurality of identifying features are located internally with respect to the object; projecting a location of region(s) of interest of the object based on the plurality of identifying features, where each region of interest depicts content; building and/or selecting an extraction model configured to extract the content based at least in part on: the location of the region(s) of interest, the of identifying feature(s), or both; and extracting the some or all of the content from the digital image using the extraction model. Corresponding system and computer program product embodiments are disclosed. The inventive concepts enable reliable extraction of data from digital images where portions of an object are obscured/missing, and/or depicted on a complex background.

Abstract: According to an exemplary embodiment, a method for pre-cropping digital image data includes: dividing the digital image into segments; computing a color value distance between corresponding pixels of neighboring segments of the digital image; comparing the color value distance(s) against a minimum color distance threshold; clustering neighboring segments having a color value distance less than or equal to the minimum color distance threshold; computing a connected structure based on the clustered segments; computing a polygon bounding the connected structure; comparing a fraction of segments included in the connected structure and the polygon, relative to a total number of segments in the digital image, to a minimum included segment threshold; and in response to determining the fraction of segments in the connected structure and the polygon, relative to the total number of segments meets or exceeds a minimum included segment threshold, cropping the digital image based on edges of the polygon.

Abstract: Computer-implemented methods for detecting objects within digital image data based on color transitions include: receiving or capturing a digital image depicting an object; sampling color information from a first plurality of pixels of the digital image, wherein each of the first plurality of pixels is located in a background region of the digital image; optionally sampling color information from a second plurality of pixels of the digital image, wherein each of the second plurality of pixels is located in a foreground region of the digital image; assigning each pixel a label of either foreground or background using an adaptive label learning process; binarizing the digital image based on the labels assigned to each pixel; detecting contour(s) within the binarized digital image; and defining edge(s) of the object based on the detected contour(s). Corresponding systems and computer program products configured to perform the inventive methods are also described.

Abstract: Systems, computer program products, and techniques for detecting and/or reconstructing objects depicted in digital image data within a three-dimensional space are disclosed. The concepts utilize internal features for detection and reconstruction, avoiding reliance on information derived from location of edges. The inventive concepts provide an improvement over conventional techniques since objects may be detected and/or reconstructed even when edges are obscured or not depicted in the digital image data. In one aspect, detecting a document depicted in a digital image includes: detecting a plurality of identifying features of the document, wherein the plurality of identifying features are located internally with respect to the object; projecting a location of one or more edges of the document based at least in part on the plurality of identifying features; and outputting the projected location of the one or more edges of the document to a display of a computer, and/or a memory.

Abstract: Computer-implemented methods for detecting objects within digital image data based on color transitions include: receiving or capturing a digital image depicting an object; sampling color information from a first plurality of pixels of the digital image; optionally sampling color information from a second plurality of pixels of the digital image; generating or receiving a representative background color profile based on the color information sampled from the first plurality of pixels; generating or receiving a representative foreground color profile based on the color information sampled from the second plurality of pixels and/or the first plurality of pixels; assigning each pixel a label; binarizing the digital image based on the labels; detecting contour(s) within the binarized digital image; and defining edge(s) of the object based on the detected contour(s). Corresponding systems and computer program products configured to perform the inventive methods are also described.

Abstract: Systems, computer program products, and techniques for detecting and/or reconstructing objects depicted in digital image data within a three-dimensional space are disclosed, according to various exemplary embodiments. The inventive concepts uniquely utilize internal features to accomplish reconstruction, thereby avoiding reliance on reconstructing objects based on information derived from location of edges. The inventive concepts thus provide an improvement over conventional object reconstruction since objects may be detected and/or reconstructed even when edges are obscured or not depicted in the digital image data. In one aspect, reconstructing an object depicted in a digital image includes using a processor to: detect a plurality of identifying features of the object, where the identifying features are located internally with respect to the object; and reconstruct the digital image of the object within a three dimensional coordinate space based at least in part on some or all of the identifying features.

Abstract: A method of detecting an object depicted in a digital image includes: detecting a plurality of identifying features of the object, wherein the plurality of identifying features are located internally with respect to the object; projecting a location of region(s) of interest of the object based on the plurality of identifying features, where each region of interest depicts content; building and/or selecting an extraction model configured to extract the content based at least in part on: the location of the region(s) of interest, the of identifying feature(s), or both; and extracting the some or all of the content from the digital image using the extraction model. Corresponding system and computer program product embodiments are disclosed. The inventive concepts enable reliable extraction of data from digital images where portions of an object are obscured/missing, and/or depicted on a complex background.

Abstract: According to one aspect, a computer-implemented method of discovering processes for robotic process automation (RPA) includes: recording a plurality of event streams, each event stream corresponding to a human user interacting with a computing device to perform one or more tasks; concatenating the event streams; segmenting some or all of the concatenated event streams to generate one or more individual traces performed by the user interacting with the computing device, each trace corresponding to a particular task; clustering the traces according to a task type; identifying, from among some or all of the clustered traces, one or more candidate processes for robotic automation; prioritizing the candidate processes; and selecting at least one of the prioritized candidate processes for robotic automation. Further aspects building upon the above include generating RPA models to perform tasks determined to be processes for RPA. Corresponding systems and computer program products are also described.

Abstract: In various embodiments, computer program products for detecting, estimating, calculating, etc. characteristics of a document based on reference objects depicted on the document are disclosed. In one approach, a computer program product for processing a digital image depicting a document includes instructions executable by a computer for analyzing the digital image to determine one or more of a presence and a location of one or more reference objects; determining one or more geometric characteristics of at least one of the reference objects; defining one or more region(s) of interest based at least in part on one or more of the determined geometric characteristics; and detecting a presence or absence of an edge of the document within each defined region of interest. Additional embodiments leverage the type of document depicted in the image, multiple frames of image data, and/or calculate or extrapolate document edges rather than locating edges in the image.

Abstract: Computer program products for performing workflows using a mobile device, without requiring tactile input from the user. The workflow is thus “touchless” and may utilize input preferably including optical data and/or audio data. Tactile input may be optionally provided in some embodiments, but the workflow is configured to be performed without any tactile input. Accordingly, in one embodiment, a computer program product includes a computer readable medium having computer readable and/or executable program instructions embodied therewith, the program instructions being configured to cause a processor to: invoke a mobile application using a mobile device; receive auditory input via the mobile device; and perform a business workflow via the mobile application based on the auditory input. Corresponding systems and computer program product embodiments configured for touchless mobile workflows are also described.

Abstract: In various embodiments, methods, systems, and computer program products for processing digital images captured by a mobile device are disclosed. The exemplary image processing techniques are coupled with inbound and outbound communications protocols and workflows configured to facilitate closed-loop processing, such that a method includes initiating a workflow; providing one or more of case information and raw data to the workflow; processing one or more of the case information and the raw data to generate a processing result; storing at least some of the case information in association with the processing result, wherein the associated case information acts as an identifier of the processing result; transmitting at least the processing result and the identifier; receiving, in response to the transmitting, a reply comprising the identifier; and retrieving at least the processing result using the identifier.

Abstract: A method includes: receiving or capturing an image comprising an identity document (ID) using a mobile device; classifying the ID; analyzing the ID based at least in part on the ID classification; determining at least some identifying information from the ID; at least one of building an ID profile and updating the ID profile, based at least in part on the analysis; providing at least one of the ID and the ID classification to a loan application workflow and/or a new financial account workflow; and driving at least a portion of the workflow based at least in part on the ID and the ID classification. Corresponding systems and computer program products are also disclosed.

Abstract: Systems, methods, and computer program products for smart, automated capture of textual information using optical sensors of a mobile device, and selective provision of such textual information to a user interface for facilitating performance of downstream workflows are disclosed. The capture and provision is context-aware, and determines context of the optical input, and optionally invokes a contextually-appropriate workflow based thereon. The techniques also provide capability to normalize, correct, and/or validate the captured optical input and provide the corrected, normalized, validated, etc. information to the contextually-appropriate workflow. As a result, the overall process of capturing information from optical input using a mobile device, invoking an appropriate workflow, and providing captured information to the workflow is significantly simplified and improved in terms of accuracy of data transfer/entry, speed and efficiency of workflows, and user experience.

Abstract: Techniques for binarization and extraction of information from image data are disclosed. The inventive concepts include independently binarizing portions of the image data on the basis of individual features, e.g. per connected component, and using multiple different binarization thresholds to obtain the best possible binarization result for each portion of the image data. Determining the quality of each binarization result may be based on attempted recognition and/or extraction of information therefrom. Independently binarized portions may be assembled into a contiguous result. In one embodiment, a method includes: identifying a region of interest within a digital image; generating a plurality of binarized images based on the region of interest using different binarization thresholds; subjecting the region of interest within a digital image to a plurality of thresholding and extraction iterations; and extracting data from some or all of the plurality of binarized images.

Abstract: Computerized techniques for real-time object detection from video data include: defining an analysis profile comprising an initial number of analysis cycles dedicated to each of a plurality of detectors, each detector being independently configured to detect objects according to a unique set of analysis parameters; receiving a plurality of frames of digital video data, the digital video data depicting an object; analyzing the plurality of frames using the plurality of detectors and in accordance with the analysis profile, wherein analyzing the plurality of frames produces an analysis result for each of the plurality of detectors; determining a confidence score for each of the analysis results; and updating the analysis profile by adjusting the number of analysis cycles dedicated to at least one of the plurality of detectors based on the confidence scores. Corresponding systems and computer program products are also disclosed.

Abstract: Computer-implemented methods for detecting objects within digital image data based on color transitions include: receiving or capturing a digital image depicting an object; sampling color information from a first plurality of pixels of the digital image; optionally sampling color information from a second plurality of pixels of the digital image; generating or receiving a representative background color profile based on the color information sampled from the first plurality of pixels; generating or receiving a representative foreground color profile based on the color information sampled from the second plurality of pixels and/or the first plurality of pixels; assigning each pixel a label; binarizing the digital image based on the labels; detecting contour(s) within the binarized digital image; and defining edge(s) of the object based on the detected contour(s). Corresponding systems and computer program products configured to perform the inventive methods are also described.

Abstract: Techniques for improved binarization and extraction of information from digital image data are disclosed in accordance with various embodiments. The inventive concepts include independently binarizing portions of the image data on the basis of individual features, e.g. per connected component, and using multiple different binarization thresholds to obtain the best possible binarization result for each portion of the image data independently binarized. Determining the quality of each binarization result may be based on attempted recognition and/or extraction of information therefrom. Independently binarized portions may be assembled into a contiguous result. In one embodiment, a method includes: identifying a region of interest within a digital image; generating a plurality of binarized images based on the region of interest using different binarization thresholds; and extracting data from some or all of the plurality of binarized images. Corresponding systems and computer program products are also disclosed.

Abstract: A method of detecting an object depicted in a digital image includes: detecting a plurality of identifying features of the object, wherein the plurality of identifying features are located internally with respect to the object; projecting a location of region(s) of interest of the object based on the plurality of identifying features, where each region of interest depicts content; building and/or selecting an extraction model configured to extract the content based at least in part on: the location of the region(s) of interest, the of identifying feature(s), or both; and extracting the some or all of the content from the digital image using the extraction model. Corresponding system and computer program product embodiments are disclosed. The inventive concepts enable reliable extraction of data from digital images where portions of an object are obscured/missing, and/or depicted on a complex background.

Abstract: According to one embodiment, a computer-implemented method for cleaning up a data set having a possible incorrect label includes: selecting a plurality of training documents; estimating a quality of an organization of a plurality of categories; and determining whether the quality of the organization is greater than a predetermined quality threshold. Corresponding system and computer program product embodiments are also presented. Other aspects and advantages of the present invention will become apparent from the following detailed description, which, when taken in conjunction with the drawings, illustrate by way of example the principles of the invention.