Abstract: An apparatus and method for video fingerprinting are provided. The method includes, for each frame of a video sequence including a plurality of frames, removing a portion of the frame, dividing a remaining portion of the frame into blocks, dividing each block into sub-blocks, computing a block level feature as a mean of pixels in each sub-block within the block, concatenating all block level features in the frame, and concatenating features of all frames in the video sequence.

Abstract: A method of processing image data including performing a first mapping, of a first image dataset to a first reference, performing a second mapping, of a second image dataset to a second reference, and using the first mapping and the second mapping to correlate at least one position in the first image dataset to at least one position in the second image dataset.

Abstract: An information processing apparatus that calculates information on a position and an orientation of an image capture device relative to an object captured by the image capture device, holds three-dimensional information including a plurality of line segments that constitute the object, acquires an image of the object captured by the image capture device, detects an image feature indicating a line segment from the acquired image, calculates a position and orientation of the image capture device based on correspondence between the image feature indicating the detected line segment and the held line segment, and determines, for each of the held line segments, whether to use the line segment for the calculation of the position and orientation thereafter, based on at least one of a result of detection of the image feature, and information acquired in the calculation of the position and orientation.

Abstract: A method and system for extracting rib centerlines in a 3D volume, such as a 3D computed tomography (CT) volume, is disclosed. Rib centerline voxels are detected in the 3D volume using a learning based detector. Rib centerlines or the whole rib cage are then extracted by matching a template of rib centerlines for the whole rib cage to the 3D volume based on the detected rib centerline voxels. Each of the extracted rib centerlines are then individually refined using an active contour model.

Abstract: A set of silhouette attributes are determined for a class of objects, where each of the silhouette attribute corresponds to a discriminative feature that is not associated with any other silhouette attribute in the set. An image content item depicting an object of the class is analyzed. A discriminative feature is identified for the object. The silhouette attribute associated with the determined discriminative feature is associated with the object as provided in the image content item.

Abstract: Each training image in a collection of training images is associated with a corresponding mask. A set of training images is selected from the collection as being a match for an input image, based at least in part on a comparison of the input image to each training image in the collection. An output mask is determined from the associated masks of the set of training images. One or more boundaries are determined for an object depicted in the input image using the output mask.

Abstract: The classification and segmentation system of the current invention makes use of information from pixels of an image, namely the magnitude of the pixels, to run specific analytics to classify and segment the image pixels into different groups. This invention includes a system for processing an image, the system including an input device, a processor, a memory and a monitor. The input device is configured to receive image data, where the image data includes pixels and each pixel has a magnitude. The memory has instructions stored in it that, when executed by the processor, cause the processor to run calculations. The calculations include: calculating the log-magnitudes from the magnitudes of at least a plurality of the pixels, calculating standard deviations of the log-magnitudes for subsets of the plurality of pixels and compute an integral of the standard deviations over a desired range. The pixels are classified into different groups based on a value of the integral relative to one or more integral values.

Abstract: A code recognition method includes the following steps: a first code-image block is received. Wherein, several first codes are displayed on the first code-image block. The first code-image block is partitioned into several second code-image blocks. Wherein, each of the second code-image blocks displays a second code respectively. Each of the second codes is one of the first codes. Each of the second code-image blocks is recognized as several third codes corresponding to each of the second codes respectively. Some of the neighboring second code-image blocks are combined to form several third code-image blocks. Wherein, each of the third code-image blocks displays a first code set, which comprises some of the second codes. Each of the third code-image blocks is recognized as a second code set corresponding to each of the first code sets respectively. Wherein, each of the second code sets includes the codes selected from the third codes.

Abstract: An MMR system for searching across multiple indexes comprises a plurality of mobile devices, a pre-processing server or MMR gateway, and an MMR matching unit, and may include an MMR publisher. The MMR matching unit receives an image query from the pre-processing server or MMR gateway and sends it to one or more of the recognition units to identify a result including a document, the page and the location on the page. The MMR matching unit includes a segmenter for segmenting received images by content type, a distributor for distributing the images to corresponding content type index tables, and an integrator for integrating recognition results. The result is returned to the mobile device via the pre-processing server or MMR gateway. The present invention also includes a number of novel methods including a method for processing content-type specific image queries and for processing queries across multiple indexes.

Abstract: A radiation therapy device controller identifies a pixel on a straight line connecting a ray source and a sensor array, and calculates a luminance update amount candidate value for each identified pixel based on a ratio of a change amount for the pixel on the straight line indicating the living body to a sum of change amounts from a luminance value of a pixel corresponding to a correlated computed tomography image correlated with a computed tomography image of an update target of a luminance value of the identified pixel. Also, the control device calculates a luminance update amount of each identified pixel using the luminance update amount candidate value of each identified pixel calculated for a plurality of rotation angles, and updates the luminance value of each corresponding pixel of the computed tomography image of the update target using the luminance update amount of each identified pixel.

Abstract: Provided is, for example, a medical image display device which automatically create and display an image suitable for radiographic image interpretation of interosseous tissue or a 3-dimensional image of a vertebral body separated one by one with high precision. A medical image processing device (1) creates a first conversion image (in step (S1)), extracts a first intervertebral disc region from the first conversion image (in step (S2)), and specifies two coordinates (P1, P2) from among the pixels included in the first intervertebral disc region (in step (S3)). Next, the medical image processing device (1) creates a second conversion image (in step (S4)), extracts a second intervertebral disc region (in step (S5)), and specifies two coordinates (Q1, Q2) from the second intervertebral disc region (in step (S6)).

Abstract: A characteristic point extraction section acquires an image captured by an image capture device and extracts characteristic points from the captured image, a vehicle lane boundary point selection section selects vehicle lane boundary points that indicate vehicle lanes from the extracted characteristic points, a distribution determination section determines the distribution of the vehicle lane boundary points, a system noise setting section sets each system noise based on the distribution of vehicle lane boundary points, and a travel path parameter estimation section stably predicts travel path parameters based on the vehicle lane boundary points, past estimation results, and the system noise that has been set.

Abstract: A method and system for automated view planning for cardiac magnetic resonance imaging (MRI) acquisition is disclosed. The method and system automatically generate a full scan prescription using a single 3D MRI volume. The left ventricle (LV) is segmented in the 3D MRI volume. Cardiac landmarks are detected in the automatically prescribed slices. A full scan prescription, including a short axis stack and 2-chamber, 3-chamber, and 4-chamber views, is automatically generated based on cardiac anchors provided by the segmented left ventricle and the detected cardiac landmarks in the 3D MRI volume.

Abstract: An image processing device includes: a coordinate conversion unit (142) which calculates a corresponding sampling coordinate on a color mosaic image corresponding to a pixel position of a color image when a deformation process is performed, according to the pixel position of the color image; a sampling unit (143); a sampling unit (143) which interpolates-generates a pixel value in a sampling coordinate for each of color planes obtained by decomposing the color mosaic image; and a color generation unit (144) which generates a color image by synthesizing interpolation values of the respective color planes. Each pixel value of a color image subjected to a deformation process is obtained as a pixel value of the sampling coordinate from the color mosaic image by interpolation calculation, thereby realizing the color interpolation process for generating a color image from the color mosaic image and a deformation process of the color image by one interpolation calculation.

Abstract: Ulcer detection may include calculating ulcer head scores for image pixels, and calculating ulcer red region scores for pixels, each score correlated to the probability that the pixel color is typical to ulcer heads, ulcer red regions, or a other regions. Ulcer head scores may be compared to an ulcer head threshold level and, based on the results, ulcer head candidates may be obtained. Ulcer red region scores may be compared to a threshold and ulcer red region candidates may be obtained. Ulcer candidates may be formed by creating pairs including an ulcer head candidate and a potential ulcer red region candidate. A grade for ulcer candidates indicating the probability that the ulcer candidate is an ulcer may be used to generate a score for the image, the score indicating the probability that the image includes an ulcer.

Abstract: The present invention refers to a system for the diagnosis of plant anomalies which comprises at least: an acquisition device (1) capable of capturing images in real time of at least one sample of a plant to be diagnosed; a storage unit (2) comprised by a database of digitalized images (7) of samples of plants affected by anomalies and also comprised by a database of technical information (8) related to said anomalies; a human interface device (3) capable of displaying digitalized images of the plant samples; a human control device (4) capable of allowing for an active interaction between a user and the human interface device; and a processing unit (5) operatively associated to the acquisition device (1), to the storage unit (2), to the human interface device (3) and to the human control device (4).

Abstract: A method and system for estimating 3D cardiac motion from a single C-arm angiography scan is disclosed. An initial 3D volume is reconstructed from a plurality of 2D projection images acquired in a single C-arm scan. A static mesh is extracted by segmenting an object in the initial 3D volume. The static mesh is projected to each of the 2D projection images. A cardiac phase is determined for each of the 2D projection images. A deformed mesh is generated for each of a plurality of cardiac phases based on a 2D contour of the object and the projected mesh in each of the 2D projection images of that cardiac phase.

Abstract: Systems and methods for standardizing one or more fluorescence scanning instruments to a reference system by separating the effects of drift and normalization. In an embodiment, a drift image comprising an image of a drift reference slide is captured by a system to be standardized. A drift measurement is calculated using the drift image. A first normalization image comprising an image of a normalization slide is also captured by the system to be standardized. A reference normalization image, also comprising an image of the normalization slide, is captured by a reference system. The first normalization image is compared to the reference normalization image to determine a gamma value and offset value for the system to be standardized.

Abstract: An image processing apparatus includes a correlating unit configured to acquire correlation information that correlates a first three-dimensional image of a target object with a second three-dimensional image of the target object, and a corresponding cross-sectional image generation unit configured to generate a corresponding cross-sectional image of one of the first three-dimensional image and the second three-dimensional image, if a cross section is set on the other of the first three-dimensional image and the second three-dimensional image, based on the correlation information.

Abstract: The present invention relate generally to digital watermarking and data hiding. One claim recites a method including: obtaining first data and second color data, the first color data and the second color data represent data from a color image signal or color video signal; obtaining a digital watermark pattern, the pattern aiding detection of a watermark message; separating the digital watermark pattern into first frequency components and second frequency components; utilizing a programmed electronic processor or electronic processing circuitry, modifying the first color data by hiding the first frequency components therein; and utilizing a programmed electronic processor or electronic processing circuitry, modifying the second color data by hiding the second frequency components therein. Of course, other combinations and claims are provided too.