Abstract: As set forth herein, a computer-implemented method facilitates pre-analyzing an image and automatically suggesting to the user the most suitable regions within an image for text-based personalization. Image regions that are spatially smooth and regions with existing text (e.g. signage, banners, etc.) are primary candidates for personalization. This gives rise to two sets of corresponding algorithms: one for identifying smooth areas, and one for locating text regions. Smooth regions are found by dividing the image into blocks and applying an iterative combining strategy, and those regions satisfying certain spatial properties (e.g. size, position, shape of the boundary) are retained as promising candidates. In one embodiment, connected component analysis is performed on the image for locating text regions. Finally, based on the smooth and text regions found in the image, several alternative approaches are described herein to derive an overall metric for “suitability for personalization.

Abstract: What is disclosed is a handheld device having at least one illuminator for projecting source light and a video camera for capturing images of a region of interest of a subject being monitored for a desired physiological function. The handheld device is positioned such that light reflected off the subject's region of interest is received by a sensor. A determination is then made as to how a physiological signal extracted from video images captured by the video camera can be improved by an adjustment to the illuminator with respect to intensity, spectrally, spatially, and/or temporally, to improve accuracy of a measurement of a desired physiological function. The illuminator is adjusted and video images of a region of interest are captured by the video camera and processed to extract a physiological signal corresponding to that physiological function. That signal is used to monitor the desired physiological function. Various embodiments are disclosed.

Abstract: Methods and systems for continuously monitoring the gaze direction of a driver of a vehicle over time. Video is received, which is captured by a camera associated with, for example, a mobile device within a vehicle, the camera and/or mobile device mounted facing the driver of the vehicle. Frames can then be extracted from the video. A facial region can then be detected, which corresponds to the face of the driver within the extracted frames. Features descriptors can then be computed from the facial region. A gaze classifier derived from the vehicle, the driver, and the camera can then be applied, wherein the gaze classifier receives the feature descriptors as inputs and outputs at least one label corresponding to one or more predefined finite number of gaze classes to identify the gaze direction of the driver of the vehicle.

Abstract: Methods and systems for detecting anomalies in transportation related video footage. In an offline training phase, receiving video footage of a traffic location can be received. Also, in an offline training phase, event encodings can be extracted from the video footage and collected or compiled into a training dictionary. One or more input video sequences captured at the traffic location or a similar traffic location can be received in an online detection phase. Then, an event encoding corresponding to the input video sequence can be extracted. The event encoding can be reconstructed with a low rank sparsity prior model applied with respect to the training dictionary. The reconstruction error between actual and reconstructed event encodings can then be computed in order to determine if an event thereof is anomalous by comparing the reconstruction error with a threshold.

Abstract: A computer-based method for generating a compressed data stream, including using a specially programmed computer to: access a first compressed data stream including a first plurality of sequentially arranged frames including respective compressed frame data; access a second compressed data stream including a second plurality of sequentially arranged frames including respective compressed frame data; compare respective compressed data for sequentially matched pairs of frames in the first and second pluralities of frames; select, based on the comparison, common and unique portions in the first data stream; and select, based on the comparison, first and second portions in the second data stream, matched with the common and unique portions, respectively, in the sequence. The first portion has respective compressed frame data equal to the respective compressed frame data for the common portion.

Abstract: A method is provided for creation of a substrate fluorescence mask having background color(s), UV mark color(s), and distraction color(s), to be printed as an image on a substrate containing optical brightening agents. The method includes selecting one or more UV mark colors for the mask such that the UV mark colors exhibit low contrast against the background color(s) under normal illumination and high contrast against the background color(s) under UV illumination. One or more distraction colors are also selected, such that the distraction color(s) exhibit low contrast against the background color(s) under UV illumination and exhibit high contrast against the background color(s) under normal illumination. A distraction pattern, formed from one or more distraction colors, is also selected.

Abstract: Provided are methods and systems for generating a binarized representation of a document using a mobile device configured to provide a Flashed and No-flashed image of the document. According to an exemplary method, the Flash and No-flash images are aligned and blended, where the resulting image includes the No-flash image where any hot spots are included in the Flash image. After blending, the blended image is binarized.

Abstract: A system creates an electronic file corresponding to a printed artifact by launching a video capture module that causes an imaging sensor of a mobile electronic device to capture a video of a scene that includes the printed artifact. The system analyzes image frames in the video in real time as the video is captured to identify a suitable instance. The suitable instance is a frame or sequence of frames that contains at least a portion of the printed artifact and that also satisfies one or more image quality criteria or other criteria. Upon identification of each suitable instance, the system will automatically cause a photo capture module of the device to capture a still image of the printed artifact. The still image has a resolution that is higher than that of the image frames in the video. The system will save the captured still images to a computer-readable file.

Abstract: Systems and methods are provided for real time dynamic triggering of a conspicuous signal for a vehicle on a path of travel. A sensor array detects environmental factors presenting a predetermined risk to the vehicle. A decision module assesses the environmental factors and the associated risks and determines if the conspicuousness signal is warranted and a type of signal to be made. An actuating module actuates the conspicuousness signal based on the determining of the decision module.

Abstract: A device and method for providing a visual cue for improved text imaging on a mobile device. The method includes determining a minimum text size for accurate optical character recognition (OCR) of an image captured by the mobile device, receiving an image stream of a printed substrate, and displaying the image stream and a visual cue superimposed onto the image stream, wherein the visual cue is indicative of the minimum text size. The method further includes capturing a digital image of the image stream, wherein the digital image does not include the visual cue. Additionally, the method further includes notifying a user of the mobile device when text displayed within the image stream is at least as large as the minimum text size.

Abstract: A method and a system for detecting anomalies within a voluminous private data are provided. The voluminous private data, including sensitive information corresponding to one or more objects within the voluminous private data is received. The sensitive information within the voluminous private data is identified, and identified sensitive information is modified to generate a modified voluminous private data. The sensitive information is marked in the modified voluminous private data to generate a marked voluminous private data. The anomaly within the marked voluminous private data is detected.

Abstract: Methods and systems are disclosed for updating camera geometric calibration utilizing scene analysis. Geometric calibration parameters can be derived with respect to one or more cameras and selected reference points of interest identified from a scene acquired by one or more of such cameras. The camera geometric calibration parameters can be applied to image coordinates of the selected reference points of interest to provide real-world coordinates at a time of initial calibration of the camera(s). A subset of a video stream from the camera(s) can then be analyzed to identify features of a current scene captured by the camera(s) that match the selected reference points of interest and provide a current update of the camera geometric calibration parameters with respect to the current scene.

Abstract: A method of editing color characteristics of an electronic image includes: a) receiving an original electronic image at a color editing subsystem; b) analyzing the original electronic image to identify original color characteristics and to identify a recommended set of color editing options, the recommended set of color editing options being less than a complete set of color editing options provided by the color editing subsystem; c) presenting the recommended set to a user via a user interface device; d) receiving a color editing instruction from the user interface device in response to the user selecting a corresponding color editing option from the recommended set; and e) adjusting the original color characteristics to form an adjusted electronic image having adjusted color characteristics based at least in part on the color editing instruction. An apparatus for editing color characteristics of an electronic image is also provided.

Abstract: Methods, systems, and processor-readable media for pruning a training dictionary for use in detecting anomalous events from surveillance video. Training samples can be received, which correspond to normal events. A dictionary can then be constructed, which includes two or more classes of normal events from the training samples. Sparse codes are then generated for selected training samples with respect to the dictionary derived from the two or more classes of normal events. The size of the dictionary can then be reduced by removing redundant dictionary columns from the dictionary via analysis of the sparse codes. The dictionary is then optimized to yield a low reconstruction error and a high-interclass discriminability.

Abstract: As set forth herein, systems and methods facilitate providing an efficient edge-detection and closed-contour based approach for finding text in natural scenes such as photographic images, digital, and/or electronic images, and the like. Edge information (e.g., edges of structures or objects in the images) is obtained via an edge detection technique. Edges from text characters form closed contours even in the presence of reasonable levels of noise. Closed contour linking and candidate text line formation are two additional features of the described approach. A candidate text line classifier is applied to further screen out false-positive text identifications. Candidate text regions for placement of text in the natural scene of the electronic image are highlighted and presented to a user.

Abstract: The teachings as provided herein relate to a watermark embedded in an image that has the property of being relatively indecipherable under normal light, and yet decipherable under UV light. This fluorescent mark comprises a substrate containing optical brightening agents, and a first dot design printed as an image upon the substrate. The first dot design has as a characteristic the property of strongly suppressing substrate fluorescence. A second dot design having a property of providing a differing level of substrate fluorescence suppression from that of the first dot design such that when rendered in close spatial proximity with the first dot design image print, the resultant image rendered substrate suitably exposed to an ultra-violet light source, will yield a discernable image evident as a fluorescent mark.

Abstract: A method and system for detecting anomalies in video footage. A training dictionary can be configured to include a number of event classes, wherein events among the event classes can be defined with respect to n-diminensional feature vectors. One or more nonlinear kernel function can be defined, which transform the n-dimensional feature vectors into a higher dimensional feature space. One or more test events can then be received within an input video sequence of the video footage. Thereafter, a determination can be made if the test event(s) is anomalous by applying a sparse reconstruction with respect to the training dictionary in the higher dimensional feature space induced by the nonlinear kernel function.

Abstract: What is disclosed is a system and method for estimating color for pixels in an infrared image. In one embodiment, an infrared image is received which has been captured using a N-band infrared imaging system comprising a multi-spectral camera or a hyperspectral camera. The IR image is composed of an array of pixels with N intensity values having been collected for each pixel in the image. Then, for each pixel of interest, a search metric is used to search a database of vector samples to identify a visible-IR set which is closest to the intensity values of the IR band vector collected for the pixel. A visible vector representation is then estimated for the pixel based upon the visible portion corresponding to the closest visible-IR set. Thereafter, color coordinates for this pixel are computed from the visible vector. The method repeats for all pixels of interest in the IR image.

Abstract: A system and method of providing annotated trajectories by receiving image frames from a video camera and determining a location based on the image frames from the video camera. The system and method can further include the steps of determining that the location is associated with a preexisting annotation and displaying the preexisting annotation. Additionally or alternatively, the system and method can further include the steps of generating a new annotation automatically or based on a user input and associating the new annotation with the current location.

Abstract: As set forth herein, a computer-implemented method is employed to place personalized text into an image. A location within the image is selected where the text is to be placed, and region is grown around the selected location. The 3D geometry of the surface is estimated proximate to the location and sets of parallel straight lines in the image are identified and selected to define a bounding polygon into which text may be inserted. Optionally, a user is permitted to adjust the bounding polygon once it has been automatically generated.