Abstract: Provided is a method for generating pose transformation data between first and second rigidly mounted digital cameras having non-coincident fields of view. The method includes obtaining a first plurality of images of a first calibration object, obtaining a second plurality of images of the first or a second calibration object, generating first and second object point data, generating first and second calibration data of the first and second digital cameras, determining first pose data between a first frame of reference of the first digital camera and the frame of reference of the first calibration object, determining second pose data between the frame of reference of the second digital camera and the frame of reference of the first or second calibration objects, and calculating the pose transformation data between the pose of the first digital camera and the pose of the second digital camera.

Abstract: Embodiments of the disclosure may be directed to an image processing system configured to receive a medical image of a region of a subject's body taken at a first time and to receive a surface image of an exterior portion of the region of the subject's body taken at the first time. The image processing may also be configured to receive a medical image of the region of the subject's body taken at a second time and to register the medical image taken at the first time, the surface image taken at the first time, and the medical image taken at the second time.

Abstract: Systems and methods are described for segmenting a medical image using a two-stage variational method in which fracture mechanics are used in the second stage to remove fine-scale contact bridges that connect object contours generated in the first stage. The image segmentation can be used to segment objects, such as bone objects, from surrounding tissues in a medical image, such as an image obtained with a computed tomography (“CT”) or other x-ray imaging system.

Abstract: The present document describe monocular machine vision systems and methods for determining locations of target elements when the three dimensional orientation of the monocular machine vision system relative to the target system is unknown. The machine vision system described herein captures and uses information gleaned from the captured target elements to determine the locations of these captured target elements relative to the vision system, or reversely, the location and orientation of the vision system relative to the target elements.

Abstract: Systems and methods for determining a breast region in a medical image are provided. The methods may include obtaining a first image relating to the breast region, determining a first region including a first plurality of pixels in the breast region, determining a second region including a second plurality of pixels relating to an edge of the breast region, and determining the breast region by combining the first region and the second region. The second plurality of pixels may include at least a portion of the first plurality of pixels.

Abstract: Systems and methods are provided for automatic measurement of strains and strain-ratio calculation for sonoelastography.

Abstract: The present disclosure provides a method, an electronic device, and a medium for image fusion. The method includes calculating a fusion coefficient image M based on a first frame image I1 or based on both the first frame image I1 and a second frame image I2; calculating a first gradient D1 of the first frame image I1 and a second gradient D2 of the second frame image I2; calculating a preliminary fusion result J based on the image M, the first gradient D1 and the second gradient D2; and obtaining an output image I3 based on the image M, the first gradient D1, the second gradient D2 and the preliminary fusion result J, wherein brightness of the first frame image I1 is greater than brightness of the second frame image I2, and wherein the image M is used to mark fusion weights of pixels in the first frame image I1.

Abstract: According to one embodiment, a medical information processing apparatus includes processing circuitry. The processing circuitry is configured to acquire information on an accuracy of a trained model that outputs information on a lesion included in data related to a medical image based on inputted data related to the medical image. Further, the processing circuitry is configured to determine a data collection condition for the medical image in a medical image diagnostic apparatus based on the information on the accuracy.

Abstract: A tracker is described which comprises a processor configured to receive captured sensor data depicting an object. The processor is configured to access a rigged polygon mesh model of the object and to compute a plurality of approximate surface normals of a limit surface of the rigged polygon mesh. The processor is configured to compute values of pose parameters of the model by calculating an optimization to fit the model to the captured sensor data where the optimization uses an evaluation function based on the plurality of approximate surface normals.

Abstract: A video analyzer measures and outputs a visual indication of a dynamic range of a video signal. The video analyzer includes a video input to receive the video signal and a cumulative distribution function generator generates a cumulative distribution function curve from a component of the video signal. A feature detector generates one or more feature vectors from the cumulative distribution function curve and a video dynamic range generator produces a visual output indicating a luminance of one or more portions of the video signal.

Abstract: Methods, systems, and computer readable media to detect and model a brain tumor in an electronic image and to predict features of the brain tumor based on the model. The method can include classifying one or more magnetic resonance imaging (MRI) images of a brain into one or more of one or more tumorous images containing an image of a tumor or one or more non-tumorous images, wherein the classification is performed using a deep learning CNN system. The method can also include segmenting a tumor region from one of the one or more tumorous images. The segmenting can include a neighboring Fuzzy C-Means (FCM) process. The method can further include classifying the segmented tumor region into one of four classes of brain tumor types. The segmented tumor region is classified as a particular brain tumor type using the deep learning CNN system. The method can also include reconstructing a 3D model of the tumor region and measuring one or more of a location of the tumor, a shape of the tumor, or a volume of the tumor.

Abstract: A license plate recognition process is described that includes automated image analysis integrated with human review and a definition of a plate grammar of license plate visual elements that are required to prepare a database search index that enables selection of a particular license plate, from a known population of all possible license plates issued for each and every jurisdiction of interest. The plate grammar includes visual elements that may be searched by both automated image analysis and by a human reviewer. The process includes creation of a question that guides a human reviewer into providing required information regarding a selected plate grammar element that is not identified by computerized image analysis. Integration of a manual review process within an automated process as opposed to manual review solely at a failed completion of the automated process is included.

Abstract: Data structure for image-processing data is for creating image-processing data necessary for performing image processing on captured images of multiple workpieces when an articulated robot extracts a workable target workpiece from among multiple supplied workpieces. The data structure includes workpiece shape data for recognizing a target workpiece by pattern matching and tool data configured to check whether there is interference between a tool mounted on the articulated robot and a peripheral workpiece. The data structure is configured such that the combination of the workpiece shape data and the tool data can be rearranged for each workpiece or for each tool.

Abstract: In one embodiment, a medical image processing apparatus includes a memory storing a predetermined program and processing circuitry. The processing circuitry is configured, by executing the predetermined program, to acquire a plurality of images that are obtained by imaging a same object and are different in imaging time, classify tissue property of the object into a plurality of tissue-property classes by analyzing the tissue property of the object based on pixel values of respective regions of the plurality of images, assign the classified tissue-property classes to the respective regions of the plurality of images, and estimate change in disease state of the object from change in the classified tissue-property classes in respectively corresponding regions of the plurality of images.

Abstract: A smart marking system for a surgical video and a method thereof are disclosed. The image recognition is performed for each surgical video to generate object information corresponding to each surgical video. The object information is used as feature data of the surgical video corresponding thereto. After a video to be analyzed is loaded, eigenvalue analysis and statistics are performed according to the video to be analyzed and all the feature data to calculate a similarity rate between the video to be analyzed and each surgical video. A surgical name corresponding to the surgical video with the highest similarity rate is selected to mark as a surgical name corresponding to the video to be analyzed. The video to be analyzed and the surgical name corresponding thereto are stored in a database as the surgical video. Thus, the efficiency of marking the surgical videos is improved.

Abstract: The present disclosure may provide a method for segmenting an image. The method may include obtaining an image and related information. The image may include a tumor region. The method may also include determining a region of interest in the image. The region of interest may include the tumor region. The method may also include performing a first segmentation of the region of interest to obtain a first segmentation result. The first segmentation may include: determining tumor morphology relating to the tumor region; performing a second segmentation of the region of interest to obtain a second segmentation result; and optimizing, based on the tumor morphology, the second segmentation result to obtain the first segmentation result.

Abstract: To make it possible to set a parameter, which is used for detection of a mark attached to a ground marker, according to the feature of the mark. Provided is an information processing apparatus including: an acquisition unit that acquires a captured image; a detection unit that detects a feature of a target object in the captured image; and a determination unit that determines, on the basis of the feature, a parameter used for an assessment of whether or not the target object is a predetermined object.

Abstract: According to an embodiment of the disclosure, a method for providing a parking service by a server configured to provide the parking service comprises obtaining a vehicle image from a closed-circuit television (CCTV) camera installed on each of both sides of each parking section of a parking lot in a direction facing a vehicle entering to capture an inside of the parking section in a direction perpendicular to an parking orientation of the vehicle, extracting a license plate of the vehicle from at least one frame included in the obtained vehicle image and tracking a trajectory of an XY-coordinate point of each vertex of the extracted license plate, detecting a time when the trajectory of the XY-coordinate point changes from a linear trajectory to a non-linear trajectory and grouping at least one frame obtained before the time into an image for the vehicle, and mapping and storing at least one license plate number recognized from the at least one frame grouped as a license plate number of the vehicle.

Abstract: The present disclosure provides systems and methods that include or otherwise leverage use of a facial expression model that is configured to provide a facial expression embedding. In particular, the facial expression model can receive an input image that depicts a face and, in response, provide a facial expression embedding that encodes information descriptive of a facial expression made by the face depicted in the input image. As an example, the facial expression model can be or include a neural network such as a convolutional neural network. The present disclosure also provides a novel and unique triplet training scheme which does not rely upon designation of a particular image as an anchor or reference image.

Abstract: A camera calibration method, a camera calibration apparatus (300), an electronic device and a computer-readable storage medium are provided. The camera calibration method includes the following steps. At (202), a target infrared image and a Red/Green/Blue (RGB) image obtained by capturing the same scene by an infrared camera and an RGB camera are acquired when the image definition is lower than a definition threshold. At (204), feature points in the target infrared image are extracted to obtain a first feature point set, feature points in the RGB image are extracted to obtain a second feature point set, and the first feature point set and the second feature point set are subjected to matching. At (206), a transformation relation between a coordinate system of the infrared camera and a coordinate system of the RGB camera is acquired according to the matched feature points.