Abstract: Methods, systems, and computer program products are provided for stroke attribute matrices. User input strokes may be converted into attributes encoded in one or more stroke attribute matrices (SAMs), such as bitmaps, for image or other multidimensional analysis. One or more convolutional neural networks (CNNs) may recognize letters, symbols, shapes and gestures in SAMs. A selector may select output classifications from among multiple CNNs. A sequence analyzer may select a sequence of selected CNN outputs. Stroke information may comprise, for example, velocity (e.g. direction and speed), tilt, pressure, line width, pen up/down events, hover height, etc. Stroke information may be stored, for example, in bitmap color channels (e.g. to facilitate human review). For example, an x, y velocity vector and x, y tilt may be encoded, respectively, as RGBA components of pixel data. Stroke crossings may be encoded, for example, by combining attribute values at pixels where strokes intersect.

Abstract: A computing device is configured to verify a user's identity, intent to authenticate, and/or possession of secret knowledge by evaluating biometric and/or environmental data. In embodiments, such verification is performed by evaluating a user's reaction to a stimulus based on such data. Biometric data may comprise eye tracking data, and a computing device may be configured to use such data to verify that the person has gazed through objects in a predetermined order. In embodiments, the user's intent to authenticate is verified by combining such eye tracking data with other biometric data. Physiological and other types of biometric data may be used to evaluate the user for indicia of duress. Embodiments may be configured to provide modified access to the computing device or resources stored thereon where indicia of duress have been detected. Such modified access may comprise hiding information stored on the device.

Abstract: Methods, systems, and computer program products are provided for stroke attribute matrices. User input strokes may be converted into attributes encoded in one or more stroke attribute matrices (SAMs), such as bitmaps, for image or other multidimensional analysis. One or more convolutional neural networks (CNNs) may recognize letters, symbols, shapes and gestures in SAMs. A selector may select output classifications from among multiple CNNs. A sequence analyzer may select a sequence of selected CNN outputs. Stroke information may comprise, for example, velocity (e.g. direction and speed), tilt, pressure, line width, pen up/down events, hover height, etc. Stroke information may be stored, for example, in bitmap color channels (e.g. to facilitate human review). For example, an x, y velocity vector and x, y tilt may be encoded, respectively, as RGBA components of pixel data. Stroke crossings may be encoded, for example, by combining attribute values at pixels where strokes intersect.

Abstract: Methods, systems, and computer program products are provided for stroke attribute matrices. User input strokes may be converted into attributes encoded in one or more stroke attribute matrices (SAMs), such as bitmaps, for image or other multidimensional analysis. One or more convolutional neural networks (CNNs) may recognize letters, symbols, shapes and gestures in SAMs. A selector may select output classifications from among multiple CNNs. A sequence analyzer may select a sequence of selected CNN outputs. Stroke information may comprise, for example, velocity (e.g. direction and speed), tilt, pressure, line width, pen up/down events, hover height, etc. Stroke information may be stored, for example, in bitmap color channels (e.g. to facilitate human review). For example, an x, y velocity vector and x, y tilt may be encoded, respectively, as RGBA components of pixel data. Stroke crossings may be encoded, for example, by combining attribute values at pixels where strokes intersect.

Abstract: Methods, systems, and computer program products are provided for stroke attribute matrices. User input strokes may be converted into attributes encoded in one or more stroke attribute matrices (SAMs), such as bitmaps, for image or other multidimensional analysis. One or more convolutional neural networks (CNNs) may recognize letters, symbols, shapes and gestures in SAMs. A selector may select output classifications from among multiple CNNs. A sequence analyzer may select a sequence of selected CNN outputs. Stroke information may comprise, for example, velocity (e.g. direction and speed), tilt, pressure, line width, pen up/down events, hover height, etc. Stroke information may be stored, for example, in bitmap color channels (e.g. to facilitate human review). For example, an x, y velocity vector and x, y tilt may be encoded, respectively, as RGBA components of pixel data. Stroke crossings may be encoded, for example, by combining attribute values at pixels where strokes intersect.

Abstract: Methods for cooperative text recommendation acceptance of completion options in a user interface are performed by systems and devices. A user provides inputs via a user interface (UI) that are stored in an input buffer. As a portion of a first input is received, completion options for some part of the first input are determined based on statistical probabilities and the portion. A completion option is selected and displayed via the UI as completing the first input in a differentiated manner from the user-entered input. The user then either generates an acceptance command for the completion option or continues providing the first input and the UI adapts the remaining completion option portion. Acceptance commands are accepted as space characters or as alphanumeric characters representing additional input that follows the first input and the completion option. Statistical likelihoods are used to account for typographical errors and misspellings in user inputs.

Abstract: A computing device is configured to verify a user's identity, intent to authenticate, and/or possession of secret knowledge by evaluating biometric and/or environmental data. In embodiments, such verification is performed by evaluating a user's reaction to a stimulus based on such data. Biometric data may comprise eye tracking data, and a computing device may be configured to use such data to verify that the person has gazed through objects in a predetermined order. In embodiments, the user's intent to authenticate is verified by combining such eye tracking data with other biometric data. Physiological and other types of biometric data may be used to evaluate the user for indicia of duress. Embodiments may be configured to provide modified access to the computing device or resources stored thereon where indicia of duress have been detected. Such modified access may comprise hiding information stored on the device.

Abstract: A system is described that mitigates the unintentional triggering of action keys on keyboards. The system detects and interprets first and second keyboard input events. If the first keyboard input event is interpreted as a character input and the second keyboard input event is interpreted as an action input, the system performs a pattern analysis based at least on an elapsed time between the first and second keyboard input events. If the second keyboard input is determined to be unintentional, the system may mitigate the unintentional triggering of the second keyboard input event by ignoring it or by interpreting the second keyboard input event as something other than the action input. If the second keyboard input is determined to be intentional, then the second keyboard input is accepted as the action input.

Abstract: Methods for enhancing touch selections for content are performed by systems and devices. Users apply a contact instrument such as a finger, stylus, or pen to a touch interface to select content displayed via a user interface. Different amounts of the content are selected based on the characteristics of the contact instrument application to the touch interface and displayed to the user. Additionally, selected portions of content can be expanded or reduced by altering the application of the contact instrument, such as changing pressure or orientation, and by receiving other selection modifying inputs from other input devices. Characteristics of interaction for contact instruments are determined and applied to selection commands by the systems and devices. Context information related to the content is also used in determining the scope of selections.

Abstract: Methods for cooperative text recommendation acceptance of completion options in a user interface are performed by systems and devices. A user provides inputs via a user interface (UI) that are stored in an input buffer. As a portion of a first input is received, completion options for some part of the first input are determined based on statistical probabilities and the portion. A completion option is selected and displayed via the UI as completing the first input in a differentiated manner from the user-entered input. The user then either generates an acceptance command for the completion option or continues providing the first input and the UI adapts the remaining completion option portion. Acceptance commands are accepted as space characters or as alphanumeric characters representing additional input that follows the first input and the completion option. Statistical likelihoods are used to account for typographical errors and misspellings in user inputs.

Abstract: A system is described that mitigates the unintentional triggering of action keys on keyboards. The system detects and interprets first and second keyboard input events. If the first keyboard input event is interpreted as a character input and the second keyboard input event is interpreted as an action input, the system performs a pattern analysis based at least on an elapsed time between the first and second keyboard input events. If the second keyboard input is determined to be unintentional, the system may mitigate the unintentional triggering of the second keyboard input event by ignoring it or by interpreting the second keyboard input event as something other than the action input. If the second keyboard input is determined to be intentional, then the second keyboard input is accepted as the action input.

Abstract: Methods, mobile electronic devices, and computer program products are provided for accepting abbreviated handwritten entry of phrases, sentences or paragraphs, and supplemental information (“hints”), and probabilistically determining the most likely translation of the abbreviated handwriting to a full text counterpart, and displaying same. Abbreviated handwriting is accepted and parsed according to a predefined reduction pattern to produce multi-character handwritten segments and corresponding segment hints. The multi-character handwritten segments and corresponding segment hints are evaluated using n-gram knowledge and/or language models to identify the most likely words corresponding to the multi-character handwritten segments. The most likely words are used to evaluate the abbreviated handwritten entry at the phrase level by evaluating the likelihood of transition from one word to the next amongst the most likely words, to compute phrase probabilities for various combinations of the most likely words.

Abstract: Methods, mobile electronic devices, and computer program products are provided for accepting abbreviated handwritten entry of phrases, sentences or paragraphs, and supplemental information (“hints”), and probabilistically determining the most likely translation of the abbreviated handwriting to a full text counterpart, and displaying same. Abbreviated handwriting is accepted and parsed according to a predefined reduction pattern to produce multi-character handwritten segments and corresponding segment hints. The multi-character handwritten segments and corresponding segment hints are evaluated using n-gram knowledge and/or language models to identify the most likely words corresponding to the multi-character handwritten segments. The most likely words are used to evaluate the abbreviated handwritten entry at the phrase level by evaluating the likelihood of transition from one word to the next amongst the most likely words, to compute phrase probabilities for various combinations of the most likely words.

Abstract: Methods for enhancing touch selections for content are performed by systems and devices. Users apply a contact instrument such as a finger, stylus, or pen to a touch interface to select content displayed via a user interface. Different amounts of the content are selected based on the characteristics of the contact instrument application to the touch interface and displayed to the user. Additionally, selected portions of content can be expanded or reduced by altering the application of the contact instrument, such as changing pressure or orientation, and by receiving other selection modifying inputs from other input devices. Characteristics of interaction for contact instruments are determined and applied to selection commands by the systems and devices. Context information related to the content is also used in determining the scope of selections.