1299 results about "Image object" patented technology

An imaging apparatus and related method comprising a source that projects a beam of radiation in a first trajectory; a detector located a distance from the source and positioned to receive the beam of radiation in the first trajectory; an imaging area between the source and the detector, the radiation beam from the source passing through a portion of the imaging area before it is received at the detector; a detector positioner that translates the detector to a second position in a first direction that is substantially normal to the first trajectory; and a beam positioner that alters the trajectory of the radiation beam to direct the beam onto the detector located at the second position. The radiation source can be an x-ray cone-beam source, and the detector can be a two-dimensional flat-panel detector array. The invention can be used to image objects larger than the field-of-view of the detector by translating the detector array to multiple positions, and obtaining images at each position, resulting in an effectively large field-of-view using only a single detector array having a relatively small size. A beam positioner permits the trajectory of the beam to follow the path of the translating detector, which permits safer and more efficient dose utilization, as generally only the region of the target object that is within the field-of-view of the detector at any given time will be exposed to potentially harmful radiation.

The invention discloses an RGB-D image object detection and semantic segmentation method based on a deep convolution network, which belongs to the field of depth learning and machine vision. According to the method provided by the technical scheme of the invention, Faster-RCNN is used to replace the original slow RCNN; Faster-RCNN uses GPU, which is fast in the aspect of feature extracting, and at the same time generates a regional scheme in the network; the whole training process is training from end to end; FCN is used to carry out RGB-D image semantic segmentation; FCN uses a GPU and the deep convolution network to rapidly extract the deep features of an image; deconvolution is used to fuse deep features and shallow features of the image convolution; and the local semantic information of the image is integrated into the global semantic information.

A structure to generate x-rays has a plurality of stationary and individually electrically addressable field emissive electron sources with a substrate composed of a field emissive material, such as carbon nanotubes. Electrically switching the field emissive electron sources at a predetermined frequency field emits electrons in a programmable sequence toward an incidence point on a target. The generated x-rays correspond in frequency and in position to that of the field emissive electron source. The large-area target and array or matrix of emitters can image objects from different positions and/or angles without moving the object or the structure and can produce a three dimensional image. The x-ray system is suitable for a variety of applications including industrial inspection/quality control, analytical instrumentation, security systems such as airport security inspection systems, and medical imaging, such as computed tomography.

During a process of migrating a source system into a standardized virtual environment, virtual machine instances of the source system executing in a hypervisor are snapshotted as virtual machine images in an operational repository of the hypervisor. The virtual machine images in the operational repository are short-term snapshots. From time to time during the migration process, long-term snapshots of the source system are created by checking given ones of the virtual machine images from the hypervisor operational repository into an image library as image objects.

A method for determining a translation of a three-dimensional pre-operative image data set to obtain a registration of the three-dimensional image data with a patient positioned in a projection imaging system. In one embodiment the user identifies an initial three-dimensional organ center from projections and extreme contour landmark points of the object on a set of projections. A set of contour points for the image object in each of a plurality of three-dimensional cross-section planes; is obtained and the points projecting nearest to the user-identified landmark points are selected. A three-dimensional grid having a predetermined number of intervals at a predetermined interval spacing centered at the user-identified organ center is defined. The three-dimensional image data contour points as centered onto each grid point are projected for evaluation and selection of the grid point leading to contour points projecting nearest to the user-identified landmark points. This selection leads to the iterative definition of a series of improved estimated three-dimensional organ centers, and associated translation vectors. Registration of a three dimensional image data to the patient positioned in a projection imaging system will allow, among other things, overlay of a visual representation of a pre-operative image object onto a projection image plane that can serve as a visual tool and a surgical navigation aid. In particular, the position and orientation of a medical device can be shown with respect to the three-dimensional image data and thus enable quicker, safer, and less invasive navigation of the medical device to and within an organ of interest.

A visual aid system, device and method is provided. The visual aid system may include an imaging unit to capture images of a user's surroundings, a knowledge database to store object recognition information for a plurality of image objects, an object recognition module to match and identify an object imaged in one or more captured images with an object in the knowledge database, and an output device to output a non-visual indication of the identified object.

Selective encryption for object data such that objects having copyrights to-be-protected are encrypted. There are provided a plurality of data compression devices for compressing respective object data respectively corresponding to a plurality of objects which compose a scene, a multiplexor for multiplexing scene description data and compressed object data to produce a multiplexed bit stream MB, a scrambler for encrypting (scrambling) individual streams corresponding to the objects having copyrights to-be-protected in the multiplexed bit stream MB, to produce an encrypted bit stream SB, for outputting the encrypted bit stream SB to a data storage medium or a data transmission medium.

A device for imaging an object, such as for breast imaging, includes a gantry frame having mounted thereon an x-ray source, a source grating, a holder or other place for the object to be imaged, a phase grating, an analyzer grating, and an x-ray detector. The device images objects by differential-phase-contrast cone-beam computed tomography. A hybrid system includes sources and detectors for both conventional and differential-phase-contrast computed tomography.

Systems and methods are provided for automated diagnosis and grading of tissue images based on morphometric data extracted from the images by a computer. The morphometric data may include image-level morphometric data such as fractal dimension data, fractal code data, wavelet data, and/or color channel histogram data. The morphometric data may also include object-level morphometric data such as color, structural, and/or textural properties of segmented image objects (e.g., stroma, nuclei, red blood cells, etc.).

A location mark detecting method of a robot cleaner capable of accurately detecting location marks from an image captured by an upwardly looking camera. The location mark detecting method comprises the steps of obtaining from the image object marks to be compared with the reference location marks, determining whether shapes of the object marks are identical to those of the reference location marks, determining whether a distance separating the object marks is identical to that between the reference location marks if it is determined that the shapes are identical, determining whether a surrounding image of the object marks is identical to that of the reference location marks if it is determined that the distances are identical, and identifying the object marks as the location marks if it is determined that the surrounding images are identical. A robot cleaner capable of wirelessly communicating with an external device comprises a driving unit, an upwardly-looking camera for capturing an image of a ceiling above an area to be cleaned on which location marks are disposed, and a control unit for detecting the location marks from the image captured by the upwardly-looking camera, the control unit commanding the driving unit utilizing information of the current location to perform a work command.

A method and apparatus are provided for removing noise from a first digital representation of data images and noise images of a document, including digitally scanning the document so as to produce the first digital representation of all the images of the document, including the data images and the noise images. After de-skewing the image representation, objects are built from a reduced-resolution representation of the scanned representation. Objects identified as picture objects are included in a mask which is logically ANDed with the de-skewed representation of the scanned document. All objects are added to an object list and initially marked as noise. Objects identified as text objects or geometric objects are marked as data objects. Objects identified as picture objects are included in a mask which is logically ANDed with the de-skewed representation to eliminate all other objects. Objects marked as data objects are added to that representation to provide the de-skewed, de-speckled representation of the scanned document.

A method and apparatus for automated document layout creation is disclosed. In one embodiment, the method comprises receiving a first layout of document image objects and creating a second layout of document image objects subject to placement constraints corresponding to placement of document image objects, at least one of the placement constraints being based on object content in one or more of the document image objects.

A video system that performs TV signal decoding, deinterlacing, and de-motion-blurring for progressive scan flat panel display is introduced. The system embeds a frame buffer and a scaler for conducting format and resolution conversions for display panels of different sizes. The output of the scaler is sent to a de-motion-blur processor for reducing the blurriness due to the motion of image objects and the slow response time of flat panel display devices. The de-motion-blur processor gets the motion and noise indication signal from scaler or the pre-frame-buffer video processor. Based on the motion and noise information and the information of temporal difference, the de-motion-blur processor performs over driving for the display panel interface and improves the rising and falling response time of the flat panel display. The decoding, deinterlacing, and de-motion-blur processing share the same frame buffer controller so the entire system can be optimized in cost and performance.

An automatic image annotation method for weakly supervised semantic segmentation. The object border is located by an image object detection method, and the semantic label is given. The object border and the semantic label are regarded as a kind of weak supervised semantic label of image level. By using traditional image segmentation method, the whole object region is segmented out, and the segmentation template for training classification network is generated. Then, the segmentation template is used as a supervisory signal to train the classification network. Finally, the trained classification network is used to segment the test image semantically. The technical proposal of the invention utilizes an object detection method to obtain a border and a semantic tag of an object in an image, utilizes a traditional image segmentation method to segment an object region, and combines the semantic tag to serve as a training sample for weak supervision semantic segmentation. The method to automatically generate training samples for weak supervised semantic segmentation, solves the problem of time-consuming and laborious manual labeling of a large number of images.

Methods for image processing for detecting and recognizing an image object include detecting an image object using pose-specific object detectors, and performing fusion of the outputs from the pose-specific object detectors. The image object is recognized using pose-specific object recognizers that use outputs from the pose-specific object detectors and the fused output of the pose-specific object detectors; and by performing fusion of the outputs of the pose-specific object recognizers to recognize the image object.

This invention provides an information output apparatus which outputs tactile information or the like corresponding to the surface state of an object as three-dimensional information together with image information, and allows the user to easily discriminate the surface material or the like of an image object in the image information.

A hybrid display unit of the information display apparatus of this invention has a structure formed by overlaying, e.g., a display panel used to display an image, and an unevenness output element group used to output the unevenness level of that image, and voltage values to be applied to respective unevenness output elements of the unevenness output element group are determined on the basis of, e.g., unevenness information stored in a memory. Therefore, material differences (smooth or rough touch) of images displayed on the display panel can be felt by touching unevenness output by the unevenness output elements.

Provided are three-dimensional air touch feedback apparatus and method for a mobile apparatus. The present invention provides an air touch feedback apparatus, including: a display unit which outputs a 3D floating image; a touch detecting unit which is disposed at a side edge of a display unit and includes a plurality of sensors to detect a body of a user and receives position information on at least one image object of the 3D floating image from the display unit to determine an air touch position where the body of the user is in contact with the image object; and a feedback providing unit which receives air touch position information from the touch detecting unit and radiates an ultrasonic wave to the air touch position at the side edge of the display unit.