Abstract: Disclosed is a method for multi-center effect compensation based on a PET/CT intelligent diagnosis system. The method includes the following steps: estimating multi-center effect parameters of a test center B relative to a training center A by implementing a nonparametric mathematical method for data of the training center A and the test center B based on a location-scale model about additive and multiplicative multi-center effect parameters, and using the parameters to compensate the data of the test center B to eliminate a multi-center effect between the test center B and the training center A. According to the present disclosure, the multi-center effect between the training center A and the test center B can be compensated, so that the compensated data of the test center B can be used in the model trained by the training center A, and the generalization ability of the model is indirectly improved.

Abstract: A computer-implemented method includes: (i) receiving location information that represents a physical location of a user; (ii) receiving a first image that has been captured by the user; (iii) in response to receiving the first image, obtaining a second image that has been captured by a camera and that depicts a particular object in an area around the physical location; (iv) determining whether the first image matches the second image; and (v) in response to determining that the first image matches the second image, determining that the user is authentic.

Abstract: Provided is a method and apparatus for eye tracking. An eye tracking method includes detecting an eye area corresponding to an eye of a user in a first frame of an image; determining an attribute of the eye area; selecting an eye tracker from a plurality of different eye trackers, the eye tracker corresponding to the determined attribute of the eye area; and tracking the eye of the user in a second frame of the image based on the selected eye tracker, the second frame being subsequent to the first frame.

Abstract: A contextual local image recognition module of a device retrieves a primary content dataset from a server and then generates and updates a contextual content dataset based on an image captured with the device. The device stores the primary content dataset and the contextual content dataset. The primary content dataset comprises a first set of images and corresponding virtual object models. The contextual content dataset comprises a second set of images and corresponding virtual object models retrieved from the server.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for machine learning for home understanding and notification. In one aspect, a method includes obtaining reference videos from a camera within a premises of a home, determining, from the reference videos, timing of actions in a routine that a particular person performs before leaving the home, determining from a sample video from the camera within the home that the particular person appears to be out of sync in performing a particular action based on the timing of actions in the routine determined from the reference videos, and in response, providing a notification to the particular person.

Abstract: Techniques are provided for deep neural network (DNN) identification of realistic synthetic images generated using a generative adversarial network (GAN). According to an embodiment, a system is described that can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise, a first extraction component that extracts a subset of synthetic images classified as non-real like as opposed to real-like, wherein the subset of synthetic images were generated using a GAN model. The computer executable components can further comprise a training component that employs the subset of synthetic images and real images to train a DNN network model to classify synthetic images generated using the GAN model as either real-like or non-real like.

Abstract: According to an embodiment, an image processing apparatus includes a display unit, an operation unit, a processing unit, a storage unit, and a control unit. The display unit is configured to display an operation screen on which a processing mode and setting information may be selected. The operation unit is configured to receive an operation instruction from the operation screen displayed on the display unit and to transmit a processing job based on the operation instruction. The processing unit is configured to execute a process based on the processing job received from the operation unit. The storage unit is configured to store use history information indicating the processing jobs. The control unit is configured to customize the operation screen according to the use history information stored by the storage unit and cause the display unit to display the customized operation screen.

Abstract: A computer-implemented method of assessing the condition of a real-world object is provided. The computer-implemented method comprises: receiving sensor data depicting the real-world object; authenticating the received sensor data as genuinely depicting the real-world object; and if the authentication is successful, assessing a condition of the real-world object from the sensor data.

Abstract: The method for display may include obtaining an image to be displayed by at least one of the one or more display devices. The image may have a first region. The method may also include acquiring image information to be displayed in a second region that is displayed in the at least one of the one or more display devices. The image information may be related to the image. The method may also include acquiring a display standard associated with the image. The method may also include storing the image to at least one of the one or more storage devices. The method may also include generating a first determination that a display of the second region does not satisfy the display standard when storing the image. The method may also include generating a response based on a result of the first determination.

Abstract: Estimating absolute geospatial accuracy in input images without the use of surveyed control points is disclosed. For example, the absolute geospatial accuracy of a satellite images may be estimated without the use of control points (GCPs). The absolute geospatial accuracy of the input images may be estimated based on a statistical measure of relative accuracies between pairs of overlapping images. The estimation of the absolute geospatial accuracy may include determining a root mean square error of the relative accuracies between pairs of overlapping images. For example, the absolute geospatial accuracy of the input images may be estimated by determining a root mean square error of the shears of respective pairs of overlapping images. The estimated absolute geospatial accuracy may be used to curate GCPs, evaluate a digital elevation map, generate a heatmap, or determine whether the adjust the images until a target absolute geospatial accuracy is met.

Abstract: Computational techniques are applied to video images of polyps to extract features and patterns from different perspectives of a polyp. The extracted features and patterns are synthesized using registration techniques to remove artifacts and noise, thereby generating improved images for the polyp. The generated images of each polyp can be used for training and testing purposes, where a machine learning system separates two types of polyps.

Abstract: A system for extraction and verification of handwritten signatures from arbitrary documents. The system comprises one or more computing devices configured to: receive a digital image of a document; perform a dilating transformation via convolution matrix on the digital image to obtain a modified image; determine a plurality of regions of connected markings in the digital image; based at least in part on a pixel density or proximity to an anchor substring of each region, determine whether any region contains any handwritten signature; extract first image data of the region containing a handwritten signature from the digital image; retrieve second image data of a confirmed example signature for a purported signer of the handwritten signature; and based on a comparison of the first image data with the second image data, forward a determination of whether the first image data and second image data are similar.

Abstract: Embodiments may: select a set of training images; extract a first set of features from each training image of the set of training images to generate a first feature tensor for each training image; extract a second set of features from each training image to generate a second feature tensor for each training image; reduce a dimensionality of each first feature tensor to generate a first modified feature tensor for each training image; reduce a dimensionality of each second feature tensor to generate a second modified feature tensor for each training image; construct a first generative model representing the first set of features and a second generative model representing the second set of features of the set of training images; identify a first candidate image; and apply a regression algorithm to the first candidate image and each of the first generative model and the second generative model to determine whether the first candidate image is similar to the set of training images.

Abstract: Provided in the present disclosure are an insect identification method and system. The system comprises a client and a server, and the client is connected to the server. The method comprises: the client acquires an image photograph that is captured by a target user and that contains an insect to be identified, acquires an insect region in the image photograph, slices the insect region to obtain an insect image, and sends the insect image to the server; the server identifies the insect image by invoking an insect species identification model deployed in the server, and sends the identification result to the client; and the client pushes the identification result to the target user. By applying the solution provided in the present disclosure, the problem in the prior art in which insect identification is very difficult and has low accuracy may be solved.

Abstract: A method and a system for extracting information from a table in a document is provided. The method includes: receiving a document that includes information that is arranged in a table; determining three sets of coordinates that respectively relate to lines, words, and characters included in the document; extracting a list of lines based on the first set of coordinates; reconstructing the rows of the table based on list of lines and the second set of coordinates; reconstructing the columns of the table based on the reconstructed rows and the third set of coordinates; and outputting a reconstruction of the table. The three sets of coordinates are expressible in an hOCR format that is based on an open standard for representation of scanned information that is obtainable by using an optical character recognition (OCR) technique.

Abstract: The present disclosure describes a method for occupancy class prediction, such as for occupancy class detection in a vehicle. In aspects, the method includes determining, for a plurality of points of time, measurement data related to an area and determining, for a plurality of points of time, occlusion values based on the measurement data. The method further includes selecting, for a present point of time, one of a plurality of modes for occupancy class prediction based on the occlusion values for at least one of the present point of time and a previous point of time and/or based on one of the plurality of modes for occupancy class prediction selected for the previous point of time. The method additionally includes determining, for the present point of time, one of a plurality of predetermined occupancy classes of the area based on the selected mode for the present point of time.

Abstract: An apparatus, method and computer program is described comprising the following: receiving telemetry and/or motion vector data and distance data from a distance sensor of the drone or unmanned aerial vehicle (32); determining a segment of interest dependent on said telemetry data and/or motion vector data; processing said distance data to determine whether an obstacle falls within said segment of interest (34); receiving imaging data; and providing imaging data analysis in the event that an obstacle is determined to fall within said segment of interest (36).

Abstract: An apparatus comprises a sensor comprising a left camera and a right camera. A processor is coupled to the sensor. The processor is configured to produce an image and disparity data for the image, and search for a vertical object within the image using the disparity data. The processor is also configured to determine whether the vertical object is a bale of material using the image, and compute an orientation of the bale relative to the sensor using the disparity data. The sensor and processor can be mounted for use on an autonomous bale mover comprising an integral power system, a ground-drive system, a bale loading system, and a bale carrying system.

Abstract: A medical system includes an instrument, a display system, and a processing unit. The instrument includes an instrument shape sensor. The processing unit includes one or more processors. The processing unit is configured to, receive an anatomic model of a patient anatomy, receive shape sensor data from the instrument shape sensor while the instrument is positioned within the patient anatomy and registered to the anatomic model, determine a preferred fluoroscopic image plane for display on the display system based on the received shape sensor data and the area of interest, and provide an indication on the display system to guide positioning of a fluoroscopy system to obtain a fluoroscopic image in the preferred fluoroscopic image plane. An area of interest is identified in the anatomic model.

Abstract: An event-based sensor having a sensing part that produces events asynchronously. The output signal includes information relating to at least some of the produced events. The method comprises: estimating a rate of production of events by the sensing part; while the estimated rate is less than a threshold, transmitting the signal having a variable rate; and when the estimated rate is above the threshold, transmitting the signal including information relating to only some of the produced events, such that a rate of events for which information is included in the signal remains within the threshold.