Abstract: There is provided an information processing apparatus to measure a distance in a real space with a simpler operation, the information processing apparatus including: an acquisition section that acquires an image captured by a predetermined imaging section, and position information based on at least any of a position and a direction of the imaging section; an estimation section that estimates a first position and a second position in a real space, on a basis of a first image and a second image which are the image captured at each of a first viewpoint and a second viewpoint, and first position information and second position information which are the position information about each of the first viewpoint and the second viewpoint; and a measurement section that measures a distance between the first position and the second position on a basis of the estimation result.

Abstract: A free-form lens (for example a phase modulator, lens or deformable mirror) may be made to reproduce a light pattern specified by image data. Source regions on the free-form lens are mapped to target regions areas on an image. Areas of the source regions are adjusted to vary the amount of light delivered to each of the target regions. Adjustment of the source areas may be achieved using a L-BFGS optimization which preferably incorporates smoothness and curl regularizers. Embodiments apply parallel processing to obtain control values for a free form lens in real time or near real time. Apparatus may process image data and display an image by controlling a dynamically variable free form lens using the processed image data.

Abstract: Provided are automated (computerized) methods and systems for analyzing digitized pathology images in a variety of tissues potentially containing diseased or neoplastic cells. The method utilizes a coarse-to-fine analysis, in which an entire image is tiled and shape, color, and texture features are extracted in each tile, as primary features. A representative subset of tiles is determined within a cluster of similar tiles. A statistical analysis (e.g. principal component analysis) reduces the substantial number of “coarse” features, decreasing computational complexity of the classification algorithm. Afterwards, a fine stage provides a detailed analysis of a single representative tile from each group. A second statistical step uses a regression algorithm (e.g. elastic net classifier) to produce a diagnostic decision value for each representative tile. A weighted voting scheme aggregates the decision values from these tiles to obtain a diagnosis at the whole slide level.

Abstract: An automatic optical inspection (AOI) method for inspecting defects on a surface of an object is provided. The method includes: providing at least two different illumination systems; acquiring, by at least one detector, at least two pieces of image information of the object, each piece of image information being acquired under illumination of a corresponding one of the illumination systems; obtaining at least two pieces of surface defect information of the object by analyzing the acquired at least two pieces of image information using a computer and storing at least one of the obtained at least two pieces of surface defect information by the computer; and combining, by the computer, all of the at least two pieces of surface defect information to de-duplicate the at least two pieces of surface defect information and obtain a piece of combined surface defect information.

Abstract: An apparatus includes an acquisition unit that acquires a first image based on a first parameter, and a second image based on a second parameter, a segmentation unit that segments each of the first and second images into a plurality of segments, an acquisition unit that acquires feature quantities from each of the plurality of segments formed by segmenting the first and second images, respectively, a calculation unit that calculates a reliability of each of the plurality of segments of the first image based on the feature quantities acquired from the first image, a classification unit that classifies the plurality of segments of the first image into a first field having a relatively high reliability and a second field having a relatively low reliability, and a determination unit that determines categories for the first and second fields based on the feature quantities acquired from the first and second images.

Abstract: Techniques for de-aliasing depth ambiguities included within infrared phase depth images are described herein. An illuminator emits reference light towards a target object. Some of this light is reflected back and detected. A phase image is generated based on phase differences between the reference light and the reflected light. The phase differences represent changes in depth within overlapping sinusoidal periods of the reference and reflected light. The phase image also includes ambiguities because multiple different depths within the phase image share the same phase difference value, even though these depths actually correspond to different real-world depths. The phase image is fed as input to a machine learning (“ML”) component, which is configured to de-alias the ambiguities by determining, for each pixel in the phase image, a corresponding de-aliasing interval. A depth map is generated based on the phase image and any de-aliasing intervals generated by the ML component.

Abstract: An apparatus for automatic target recognition with reinforcement learning is provided. The apparatus receives an image of a scene and performs an automatic target recognition on the image to detect objects in the image as candidate targets. The apparatus divides the candidate targets into subsets of candidate targets and performs a verification of the automatic target recognition to identify true targets in the image. In the verification, the apparatus solicits user input to manually identify some true targets in the image. The verification is performed according to a reinforcement learning process to minimize a total verification time.

Abstract: Systems and associated methods relate to classification of documents according to their spectral frequency signatures using a deep neural network (DNN) and other forms of spectral analysis. In an illustrative example, a DNN may be trained using a set of predetermined patterns. A trained DNN may, during runtime, receive documents as inputs, where each document has been converted into a spectral format according to a (2D) Fourier transform. Some exemplary methods may extract periodicity/frequency information from the documents based on the spectral signature of each document. A clustering algorithm may be used in clustering/classification of documents, as well as searching for documents similar to a target document(s). A variety of implementations may save significant time to users in organizing, searching, and identifying documents in the areas of mergers and acquisitions, litigation, e-discovery, due diligence, governance, and investigatory activities, for example.

Abstract: Systems and methods for generating synthetic video are disclosed. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include generating a static background image and determining the location of a reference edge. The operations may include determining a perspective of an observation point. The operations may include generating synthetic difference images that include respective synthetic object movement edges. The operations may include determining a location of the respective synthetic object movement edge and generating adjusted difference images corresponding to the individual synthetic difference images. Adjusted difference images may be based on synthetic difference images, locations of the respective synthetic object movement edges, the perspective of the observation point, and the location of the reference edge.

Abstract: To precisely identify a state of an athlete who is present in a swimming pool, a processor used in a device for identifying a state of an athlete or a method for identifying a state of an athlete refers to a result of performing processing of detecting the athlete in a video image obtained by imaging the athlete who is present in the swimming pool and identifies an advancing direction of the athlete as a direction that is different from the previous advancing direction on the basis of a result of the detection of the athlete after the athlete is present in a region on the side of an end of the swimming pool. In this manner, it is possible to more accurately identify the advancing direction of the athlete and to thereby precisely identify the state of the athlete who is present in the swimming pool.

Abstract: Exemplary quantitative susceptibility mapping methods, systems and computer-accessible medium can be provided to generate images of tissue magnetism property from complex magnetic resonance imaging data using the Bayesian inference approach, which minimizes a cost function consisting of a data fidelity term and two regularization terms. The data fidelity term is constructed directly from the complex magnetic resonance imaging data. The first prior is constructed from matching structures or information content in known morphology. The second prior is constructed from a region having an approximately homogenous and known susceptibility value and a characteristic feature on anatomic images. The quantitative susceptibility map can be determined by minimizing the cost function. Thus, according to the exemplary embodiment, system, method and computer-accessible medium can be provided for determining magnetic susceptibility information associated with at least one structure.

Abstract: A method of producing a magnetic resonance (MR) image of a region of interest is provided. The method includes the steps of: acquiring an initial MR image of the region of interest, the initial MR image mapping values of an MR-sensitive, physical property at positions over the region; determining a corresponding map of the estimated uncertainties in the values of the MR-sensitive, physical property over the region; and calculating a weighted MR image of the region, the weighted MR image mapping values of a function which combines, at each position of the initial image, the respective value of the MR-sensitive, physical property and the respective estimated uncertainty, the function applying a higher weighting to positions with relatively low estimated uncertainties than to positions with relatively high estimated uncertainties.

Abstract: A method for performing client-side content inference may include (1) receiving a request to upload, from a client-side device to a server-side device, a content item that includes a first sequence of bytes and a second sequence of bytes, (2) identifying a model configured to output a classification for sequences of bytes, (3) using, at the client-side device, the model to derive a first classification for the first sequence, (4) using, at the client-side device, the model to derive a second classification for the second sequence, and (5) uploading, in response to the request, the content item to the server-side device by (a) uploading the first sequence, (b) uploading the first classification substantially contemporaneous with uploading the first sequence, (c) uploading the second sequence, and (d) uploading the second classification substantially contemporaneous with uploading the second sequence. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A method, information processing apparatus, and a non-transitory computer-readable storage medium are provided. In the method, a location of an edge of an eye in a first image of a face is determined. An area of the first image based on the determined location is determined. The area of the first image is divided into first and second subareas based on pixel values of the area of the first image. The first subarea includes the pixel values of a first range and the second subarea includes the pixel values of a second range, and an average pixel difference of the first and second ranges is greater than a threshold. The location of the pupil is determined based on a location of one of the first and second subareas when the average pixel difference of the first and second ranges is greater than the threshold.

Abstract: Devices, systems, and methods obtain a region of an image; generate known-object scores for the region using known-object detectors, wherein each known-object detector of the known-object detectors detects objects in a respective object class; determine a likelihood that the region includes a complete object; and determine a likelihood that the region includes an unknown object based on the likelihood that the region includes a complete object and on the known-object scores.

Abstract: Systems and methods for counting objects in images based on each object's approximate location in the images. An image is passed to a segmentation module. The segmentation module segments the image into at least one object blob. Each object blob is an indication of a single object. The object blobs are counted by a counting module. In some embodiments, the segmentation module segments the image by classifying each image pixel and grouping nearby pixels of the same class together. In some embodiments, the segmentation module comprises a neural network that is trained to group pixels based on a set of training images. A plurality of the training images contain at least one point marker corresponding to a single training object. The segmentation module learns to group pixels into training object blobs that each contain a single point marker. Each training object blob is thus an indication of a single object.

Abstract: Systems and methods may utilize a predictive analysis model to analyze a contract or other document. A system may parse a document and/or a repository of information associated with the document. The system may identify one or more terms in the document and corresponding terms in the repository. The system may determine a difference parameter between a first term extracted from the document and a second term extracted from the repository. The system may determine whether the difference between the first term and the second term, represented by the difference parameter, is likely to be acceptable to the user using a predictive analysis model. The system may report a validation parameter indicating a level of acceptability associated with the difference. User feedback on the accuracy of the predictive analysis model is used to train, modify, and improve the predictive analysis model.

Abstract: Methods and systems are provided for automatically selecting a target area to project content thereon. For example, a projection device receives content to be projected and content attributes of the content. The projection device also captures images of candidate areas and determines candidate area characteristics based on the captured images. The projection device generates a respective quality-of-projection indicator based on the content attributes and the candidate area characteristics. The projection device selects the candidate area with the highest quality-of-projection indicator as the target area on which the content is to be projected.

Abstract: A method of operating a real time locating system (RTLS) includes: obtaining object gesture pattern data for an RTLS tagged object, in response to a gesture pattern motion of the RTLS tagged object; receiving camera gesture pattern data from a video camera, in response to the gesture pattern motion of the RTLS tagged object; determining that the object gesture pattern data matches the camera gesture pattern data; and sending the RTLS coordinates of the RTLS tagged object to a monitoring device, in response to the object gesture pattern data matching the camera gesture pattern data.

Abstract: Techniques are discussed for determining a velocity of an object in an environment from a sequence of images (e.g., two or more). A first image of the sequence is transformed to align the object with an image center. Additional images in the sequence are transformed by the same amount to form a sequence of transformed images. Such sequence is input into a machine learned model trained to output a scaled velocity of the object (a relative object velocity (ROV)) according to the transformed coordinate system. The ROV is then converted to the camera coordinate system by applying an inverse of the transformation. Using a depth associated with the object and the ROV of the object in the camera coordinate frame, an actual velocity of the object in the environment is determined relative to the camera.