Abstract: A method of processing a digital image using face detection within the image achieves one or more desired image processing parameters. A group of pixels is identified that correspond to an image of a face within the digital image. Default values are determined of one or more parameters of at least some portion of the digital image. Values are adjusted of the one or more parameters within the digitally-detected image based upon an analysis of the digital image including the image of the face and the default values.

Abstract: Motion information generated by comparing one or more clinical volume data may be used in a variety of applications. Examples of applications described herein include 1) generation of interpolated volume data at a time point somewhere between two received instance of volume data; 2) propagation of geometric information from one instance of volume data to another based on the motion information; and 3) adjustment of volume data to fix one or more features at a same location in a series of rendered instances of volume data. Combinations of these effects may also be implemented.

Abstract: A novel and useful method and system of optimized image compression of digital pathology slide images. The optimized image compression mechanism exploits the special color properties of the stained tissue represented by the digital pathology slides and provides an image compression algorithm having improved rate-distortion performance. Optimized color transforms are pre-computed using training sets of pathology slide image scan data for each stain type. The optimized color transforms are used to compress input slide image scans resulting in more efficient image streaming enabling users to review extremely large digital slide scans from any connected location, such as in a hospital, satellite center, home or on a mobile telephone.

Abstract: In the medical image interpreting apparatus having a pointing device for moving a cursor, medical image, interpretation report, and cursor are displayed on a display screen, and initial movement information and information on the destination of movement of the cursor are linked and stored, via the pointing device when the cursor begins to move, said initial movement information relevant to the initial movement is retrieved to obtain the linked information on the destination of movement and the cursor is moved to the destination of movement indicated in the obtained information on the destination of movement. Due to this, just by slightly moving the cursor, the cursor jumps to the desired destination of movement, therefore, it becomes possible to omit an operation of the pointing device in between.

Abstract: A method for determining absorption coefficients corrected with polychromy artifacts for an object composed of a plurality of material types differentiated with absorption attributes is provided. A plurality of x-ray beam projections of the object are recorded with monochrome x-rays from different positions. The recorded projections are reconstructed to determine a first set of absorption coefficients. The projections are calculated by reprojection. The recorded projections are corrected by the calculated projections. A second set of absorption coefficients corrected with polychromy artifacts is finally determined by reconstructing the corrected projections. A formula-based description of a rule taking account of polychromy is used in the calculation. The rule includes parameters to be determined by the reprojection in the course of the calculation of projections. The method combines steps of conventional methods and is thus more efficient.

Abstract: A plurality of sets of volume data obtained by imaging a subject on different imaging dates or different imaging times are analyzed, to calculate at least one type of index value that represents the state of the subject within each set of volume data. Transition data that represent transitions in the index values are generated for each type of index value, based on the calculated index values. At least one subject map that includes a region in which transitions are detected is generated. Specified data from among the calculated index values and the generated transition data are correlated with regions within each subject map where transitions are detected, and output to a predetermined screen.

Abstract: A target-viewpoint position in a first-medical-image having multiple viewpoints is determined. Information about an anatomical structure and/or a lesion in the first-medical-image is obtained, as first information. Further, information about an anatomical structure and/or a lesion in a finding with respect to at least one second-medical-image of the same examined person as the first-medical-image, the information being related to the first information, is obtained, as second information, from image-reading-report information including the finding. Each of the at least one second-medical-image has multiple viewpoints, and was obtained at different time from the first-medical-image. The image-reading-report information is correlated with an image of a viewpoint position at which the finding was prepared.

Abstract: A computer implemented method of mapping of multiple regional center point trajectory movements of cavity walls is provided in which images are acquired and a region-of-interest is identified in each of the images. The region-of-interest is divided into a plurality of distinct regions and a regional center point for each of the regions is located in the images. For each regional center point, a center point trajectory is determined based on variances in position of the center points from each other in the images. The center point trajectory of each regional center point is decomposed into radial and circumferential components so as to isolate radial component of the center point trajectory for each regional center point in each of the images and radial motion versus time curves are displayed for each regional center point based on the determined radial component for each regional center point in each of the images.

Abstract: The proposed method comprises determining for each point of the signal an environment comprising the first neighbours and calculating for each point of the signal a reconstructibility measurement, or singularity measurement, weighting the contributions of said local environment of the point. The value of the signal at each point is inferred from the values of the signal at the points of the local environment using a reconstruction formula. The singularity measurement includes the difference between the value of the signal at the point and the value estimated by its local environment. A logarithmic transformation is carried out on said singularity measurement with a view to obtaining an independent measurement of the amplitude of the sampled digital signal that varies in a controlled manner under changes in resolution. A system is proposed with means for obtaining said singularity measurement for each point and for carrying out the abovementioned logarithmic transformation and other calculations.

Abstract: Provided is an ultrasonic imaging apparatus including: a time-gain controller (TGC) that compensates an amplitude fading occurring in the process of propagation inside a living body; a scan converter (SC) that constructs image data; a TIC measurement unit that measures a TIC of each pixel; an evaluation index input unit that inputs an index for evaluating hemodynamics on the basis of a TIC; a mapping parameter estimation unit that estimates a mapping parameter comparable to an evaluation index; a TIC image construction unit that constructs a two-dimensional image on the basis of the mapping parameter; and a pixel detection unit that extracts a region corresponding to a color map from a TIC image, and utilizing a TIC measured with each pixel so as to measure a difference in hemodynamics.

Abstract: According to one embodiment, an X-ray computed tomography apparatus includes an X-ray generating unit and an area detector. The reconstruction processing unit reconstructs first and second volume data including an overlap region. The extraction unit extracts first and second slice images from the first and the second volume data respectively. The calculation unit calculates the difference value between a sum of pixel values in the first slice images and the sum of pixel values in the second slice images. The determination unit determines whether the difference value falls within a predetermined range. The combining unit combines the first and second volume data and sets a pixel value in the overlap region to a pixel value of the first volume data, a pixel value of the second volume data, or a value derived from pixel values of the first and second volume data.

Abstract: A method is disclosed for scanning a cyclically moved examination object using a contrast agent within the scope of a preliminary examination by way of a CT scanner, in which measurement data is recorded at a sequence of recording times, and in which a first image is reconstructed at every recording time from the measurement data, from which a time profile of a concentration of the contrast agent is established. In at least one embodiment, the recording times for respectively recording a certain phase of the motion are synchronized with a motion signal from the examination object, wherein a second image with a small time offset with respect to the first image is reconstructed from the measurement data at each recording time, and wherein a motion curve representing a time profile of an intensity of the cyclical motion is established by comparing the first image and the second image at each recording time.

Abstract: According to one embodiment, An X-ray CT apparatus includes acquisition unit, intermediate image generating unit, weighting factor calculating unit, and resultant image generating unit. The intermediate image generating unit generates a first image based on a first projection data set and a second image based on a second projection data set. The first projection data set falls within a first view angle range of projection data acquired by the acquisition unit. The second projection data set falls within a second view angle range of the projection data. The second view angle range is narrower than the first view angle range. The weighting factor calculating unit calculates a weighting factor corresponding to a pixel value difference between the first image and the second image. The resultant image generating unit generates a resultant image associated with weighted addition of the first image and the second image based on the weighting factor.

Abstract: An X-ray imaging system comprises: an imaging unit for irradiating a subject with X ray at different angles while moving an X-ray source in one direction in tomosynthesis imaging, detecting the X ray with which the subject has been irradiated with a flat panel detector to acquire projection data of X-ray images taken at different angles; and an image processor for reconstructing a first X-ray tomographic image using projection data acquired by the imaging unit, the image processor including: a correction decision unit for selecting, according to a given selection condition, one of previously provided different corrections to be performed on the projection data; a first image correction unit for performing correction based upon the correction selected by the correction decision unit on the projection data; and a first image reconstruction unit for reconstructing the first X-ray tomographic image using the corrected projection data.

Abstract: The X-ray imaging system includes an imager in which projection data of X-ray images taken at different angles is acquired in tomosynthesis imaging, a first image reconstruction unit in which the acquired projection data of the X-ray images is used to reconstruct an X-ray tomographic image, an abnormal pixel data identification unit which refers to a defective pixel map in which information on defective pixels due to a flat panel detector and its peripheral circuit has been stored, to identify, from among pixel data of the reconstructed X-ray tomographic image, pixel data of abnormal pixels corresponding to the defective pixels, and a first image correction unit which corrects the identified pixel data of the abnormal pixels of the X-ray tomographic image to output a first X-ray tomographic image.

Abstract: An X-ray imaging system includes an imager in which a subject is irradiated with X-ray at different angles while moving an X-ray source in one direction and the X-ray with which the subject has been irradiated is detected with a flat panel detector to acquire projection data of X-ray images taken at the different angles in tomosynthesis imaging, and an image processor in which an X-ray tomographic image is reconstructed not by using abnormal pixel data corresponding to defective pixels but by using only pixel data corresponding to normal pixels from among pixel data making up the projection data of the X-ray images acquired by the imager by reference to a defective pixel map in which information on the defective pixels due to the flat panel detector and its peripheral circuit has been stored.

Abstract: A binary image reconstruction method is provided to identify metal objects in a computer tomography (CT) image. The method includes providing a suitably programmed computer, providing a CT image, where the CT image includes intensity data, and the suitably programmed computer is used to determine a first range of attenuation coefficient values and a second range of attenuation coefficient values in the intensity data, where when a difference between the first range of attenuation coefficient values and the second range of attenuation coefficient values is less than a pre-determined gradient threshold value, a boundary of a metal object in the CT image is determined.

Abstract: A method is provided for visualization of hollow organs of a patient. An x-ray image dataset of the hollow organ is recorded and registered. A number of individual x-ray images are recorded during a movement of an instrument with a data capture unit through the hollow organ, with each individual x-ray image featuring time information. Datasets of a data capture unit of an instrument is recorded during the movement of the instrument, with each dataset featuring time information. Position of the instrument is determined based on the individual x-ray images by an image recognition algorithm. The datasets of the data capture unit and the position of the instrument is spatially assigned based on the time information of the datasets of the data capture unit and the individual x-ray images. The datasets of the data capture unit is jointly displayed with the x-ray image dataset.

Abstract: Recording a plurality of lesion area extraction processing data generated in advance according to a plurality of types of lesion areas, recording a radiology which includes a character string having a lesion description character and being related to position information of a lesion area in the medical image, determining lesion area extraction processing data used for the extraction from the plurality of lesion area extraction processing data based on the lesion description character provided in the radiology report, and performing the extraction using the determined lesion area extraction processing data and the position information of the lesion area related to the character string.

Abstract: The present disclosure concerns a method and system for assessing image quality of sub-images used to form a composite image using an algorithm developed by applying statistical correlation techniques to historical data on features of sub-images which were manually evaluated by experts and using those assessment to make decisions about the further processing of the sub-images which are being assessed. The method and system find particular value in the processing of sub-images generated while there is relative motion between the specimen under examination and the objective lens of a microscope such as when the microscope stage follows a planned traverse in the focal plane and a digital image is created at intervals correlated to the motion of the stage so that a region of interest in the specimen under examination is covered by the sub-images.

Abstract: Disclosed is an image processing apparatus, method and computer-readable medium of a robot which efficiently manage a moving image acquired by the robot and reinforce security to prevent image leakage. In order to restore an object region within an original image photographed by the robot, a low-resolution image is generated using object password information and the original image to generate image information, and the image information is transmitted to a server over a network. The server detects the object password information and the low-resolution information from the image information and restores a high-resolution object image using the object password information and the low-resolution image.

Abstract: Methods and/or systems for modeling 3-dimensional objects (for example, human faces). In certain example embodiments, methods and/or systems usable for computer animation or static manipulation or modification of modeled images (e.g., faces), image processing, or for facial (or other object) recognition methods and/or systems.

Abstract: A method for estimating the aesthetic quality of an input digital image comprising using a digital image processor for performing the following: determining one or more vanishing point(s) associated with the input digital image by automatically analyzing the digital image; computing a compositional model from at least the positions of the vanishing point(s); and producing an aesthetic quality parameter for the input digital image responsive to the compositional model, wherein the aesthetic quality parameter is an estimate for the aesthetic quality of the input digital image.

Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method for learning object recognition in an image is provided. According to a feature of the present invention, the method comprises the steps of providing a training set of standard images, calculating intrinsic images corresponding to the standard images and building a classifier as a function of the intrinsic images.

Abstract: Embodiments described herein facilitate or enhance the implementation of image recognition processes which can perform recognition on images to identify objects and/or faces by class or by people.

Abstract: Described herein is a framework for automatically classifying a structure in digital image data are described herein. In one implementation, a first set of features is extracted from digital image data, and used to learn a discriminative model. The discriminative model may be associated with at least one conditional probability of a class label given an image data observation Based on the conditional probability, at least one likelihood measure of the structure co-occurring with another structure in the same sub-volume of the digital image data is determined. A second set of features may then be extracted from the likelihood measure.

Abstract: Tools disclosed herein comprise progressive, paint stroke based region recognition and selection tools. Using these tools, a user may partially paint a region of interest directly on an image (by using a paint brush or other similar tool). Unlike conventional selection tools, a user is not required to paint the entire region pixel-by-pixel. Rather the desired region is automatically and intelligently recognized based on the partial selection. This is accomplished via a progressive selection algorithm. In addition, these tools provide the ability to quickly execute such region selections on multi-megapixel images.

Abstract: Implementations of the present invention involve methods and systems for converting a 2-D image to a stereoscopic 3-D image by segmenting one or more portions of the 2-D image based on one or more pixel color ranges. Further, a matte may be created that takes the shape of the segmented region such that several stereoscopic effects may be applied to the segmented region. In addition, ink lines that are contained within the segmented region may be removed to further define the corresponding matte. Implementations of the present disclosure also include a interface that provides the above functionality to a user for ease of segmentation and region selection. By utilizing the segmentation process, a 2-D image may be converted to a corresponding stereoscopic 3-D image with a perceived depth. Further, this process may be applied to each image of an animated feature film to convert the film from 2-D to 3-D.

Abstract: An image processing apparatus that separates image data in an N-dimensional first signal format (3<N) into image data in a second signal format is provided. The second signal format is used in an image output apparatus. The apparatus comprises an input unit for acquiring input image data in the first signal format; a conversion unit for converting the input image data in the first signal format into image data in an M-dimensional third signal format (3<M?N); and a color separation unit for separating the converted image data in the third signal format into image data in the second signal format, using an M-dimensional color separation LUT. With respect to a pixel distribution, a correlation between each component of the third signal format data is lower than a correlation between each component of the first signal format data.

Abstract: To adjust colors in an input image (II) to colors of a reference image (RI), matching reference points (RP) are provided in the input image (II) and the reference image (RI), dominant colors of the matching reference points (RP) are determined (10, 20), and the colors in the input image (II) are transformed (30, 40) based on the dominant colors of the matching reference C points to obtain an output image (OI).

Abstract: A film scanning method is provided. When the film is judged as a negative film, the scanning device sets the scan exposure time for the film according to the base background color of the film. The negative film is scanned for the scan exposure time, wherein, the film passes through the scanning device at one time so as to complete the above judge of the film type and scanning of the film. The film scanning method automatically completes the recognition of film type, performs accurate scanning based on the scan exposure time, expands the dynamic range and reduces noise impacts, so as to obtain a scanned image with higher accuracy.

Abstract: Systems for refinement of a segmentation of an image using spray-paint markup are disclosed, with methods and processes for making and using the same. Spray-paint markup allows for easy markup of errors in a segmentation. The markup's data may be correlated or harmonized with the representation of the segmentation, such that it may be applied to the segmentation. The markup's data is utilized to refine the segmentation errors. To assist in the refinement process, the resolutions may be scaled down so as to exert less computation burden during the process.

Abstract: The present invention has disclosed a process of image segmentation, which comprises applying edge detection to an image to obtain an edge image and preprocessing the image; oversegmentating the preprocessed image to obtain the plurality of initial partitions; constructing k-NN Graph for the oversegmented image based on the similarity between the initial partitions; and using k-NN Graph to merge the initial partitions. With the present invention, the merging process can be accelerated and the segmentation accuracy can be improved.

Abstract: High-resolution, common-path interferometric imaging systems and methods are described, wherein a light source generates and directs light toward a sample. An optical imaging system collects the resultant substantially scattered component and substantially unscattered component. A variable phase shifting system is used to adjust the relative phase of the scattered and unscattered light components. The interfered components are sensed by an image sensing system. The process is repeated multiple times with different phase shifts to form corresponding multiple electronic signals representative of raw sample images. The raw sample images are then processed by a signal processor to form a processed image, where each image pixel has an amplitude and a phase. This picture can be displayed directly using some combination of brightness and color to represent amplitude and phase.

Abstract: A handwriting compound system is provided. The system includes a handwriting recognition module that receives a proper number of letters from a user, detects a distance between phonemes/syllables, and shapes and locations of the phonemes/syllables, and recognizes the user's handwriting. The system also includes a point designating module, a reference point setting module and a handwriting transforming module. The point designating module designates a particular one of the subdivided positions in each phoneme recognized by the handwriting recognition module. The reference point setting module sets a reference point, serving as reference for the alteration of a phoneme/syllable, inside or outside the user's input phoneme/syllable recognized by the handwriting recognition module. The handwriting transforming module designates x and y coordinates of a first point with respect to the reference point.

Abstract: A method for comparing a plurality of photographers by assessing the aesthetic quality of a set of digital images captured by each photographer comprising: providing a set of digital images captured by each of a plurality of photographers; using a processor to determine an aesthetic quality parameter for each digital image in each of the sets of digital images, wherein the aesthetic quality parameter is an estimate for the aesthetic quality of the digital image; determining an aesthetic quality distribution for each photographer responsive to the aesthetic quality parameters computed for each of the digital images in the photographer's set of digital images; and providing a comparison between the aesthetic quality distributions of the photographers.

Abstract: An image processing method of locating and recognizing barcodes in an image frame is applicable to an image processing apparatus. The method is to define plural scan tracks on the sample image frame, and the image processing apparatus searches for the section(s) possibly having the barcode, along each scan track. If the section(s) possibly having the barcode found on two neighboring scan tracks by the image processing apparatus is located at an approximate horizontal axis position, the image processing apparatus determines that a quadrilateral area defined by the two sections possibly having the barcode is an area possibly having the barcode. Therefore, the image processing apparatus can quickly locate and recognize the barcode area in the image frame.

Abstract: An image processing apparatus analyzes an image of a document to thereby extract a heading region from the image. The image processing apparatus detects candidates for the heading region from the image, and defines a predetermined range in the image as a range to be processed. The apparatus further groups the candidates in the range to be processed, based on a feature quantity corresponding to a feature in terms of style of a character string. The apparatus selects a representative group from the resultant groups, and divides the range to be processed, at the position of a candidate belonging to the representative group. The apparatus newly defines each of the portions generated by the division as a range to be processed.

Abstract: A method for determining a frontal face pose by using the symmetry of a face including detecting a face region in an image, detecting an eye region in the detected face region, normalizing the face region, analyzing the symmetry in the normalized face region, and determining whether a face pose is a frontal face pose based on an analysis of the symmetry.

Abstract: Embodiments described herein facilitate or enhance the implementation of image recognition processes which can perform recognition on images to identify objects and/or faces by class or by people.

Abstract: A method of adaptive local image similarity measurement based on the L1 distance measure is described. A relationship between distance measures is used to estimate appropriate thresholds for various patch sizes. The choice of patch size depends on the degradations contained in the image and the application. The relation between the similarity measures is established using the distribution of L1 distances for various patch sizes. For larger degradations, similarity measure with a bigger patch size is employed. For lesser imperfections, a smaller patch size produces acceptable results. To keep the computational overhead manageable, the smallest patch size that gives the desired image quality is employed.

Abstract: A computer implemented that, in various aspects, transforms a grayscale image into an OCR image by applying a combination of steps to the grayscale image is disclosed herein. The grayscale image may include one or more alphanumeric characters. The grayscale image may includes visual content displayed upon a computer screen, so that the grayscale image may have a resolution generally equivalent to a screen resolution of the computer screen prior to application of the combination of steps thereto. The resultant OCR image, in various implementations, is of sufficient resolution and quality that an OCR engine can generally recognize alphanumeric characters imbedded within the OCR image.

Abstract: A pattern detection apparatus inputs an image of an object including repetitive patterns, estimates a period of the repetitive patterns in the input object, and generates a reference image based on images divided by the estimated period. Then, the pattern detection apparatus compares the reference image and the image of the object, and detects the positions of individual patterns in the repetitive patterns based on the comparison result.

Abstract: The identification of known normal structures within an image is preferably accomplished using an appearance model. Specifically, an active appearance model, which encapsulates a complete model of the shape and global texture variations of an object from a collection of samples, is utilized to define normal structures within an image by restricting training samples supplied to the active appearance model during a training phase to those that do not contain abnormal structures. Accordingly, the trained appearance model represents only normal variations in the object of interest. When another image with abnormalities is presented to the system, the appearance model cannot synthesize the abnormal structures which show up as errors in a residual image. Accordingly, the errors in the residual image represent potential abnormalities.

Abstract: A data processing device using an image as a data source includes an image capturing unit, a display unit, image recognition modules, a storage unit, a processor, and an input unit. The image capturing unit obtains an original image frame to be displayed on the display unit. The image recognition modules respectively recognize different types of targets in the original image frame, so as to obtain target data of each target. The storage unit stores the original image frame, the target data, and an application program. The processor executes the application program, controls the image recognition modules, and marks the successfully recognized target in the original image frame. The input unit is adopted by a user to select the successfully recognized target in the original image frame, so that the processor transmits the target data of the recognition target to the application program.

Abstract: A computer implemented method for monitoring use of a computer and related systems and compositions of matter are disclosed. In various aspects, the methods may include the step of capturing an image of a monitored region of a computer screen of a computer, and the step of extracting image text from the image.

Abstract: A data managing apparatus having a word extracting portion that extracts one or a plurality of words from document data and a correlating portion that correlates the words extracted by the word extracting portion with related data related to the document data, includes a frequency storage portion having information about a frequency of each of the words stored thereon for each word; an infrequently-appearing word selecting portion that selects an infrequently-appearing word having the frequency lower than a given threshold value predetermined among the words extracted by the word extracting portion based on the information stored in the frequency storage portion; and a frequency updating portion that updates the information about frequency stored in the frequency storage portion in accordance with extraction by the word extracting portion or correlation by the correlating portion, the correlating portion correlating the infrequently-appearing word selected by the infrequently-appearing word selecting portion

Abstract: Methods, systems, and compositions of matter are disclosed herein for the compression of digital image(s) and for the expansion of digital images so compressed. In various aspects, the digital images may be compressed and the compressed images expanded substantially without loss of information.

Abstract: An image processing apparatus has a storage unit for storing uncompressed data, a compression processing unit for performing lossless compression and lossy compression on the uncompressed data, a memory controller for reading the uncompressed data from the storage unit and writing compressed data compressed by the compression processing unit and a control unit for controlling transfer of the uncompressed data stored in the storage unit to the compression processing unit, wherein the compression processing unit has one DMA and simultaneously executes the lossless compression and the lossy compression, and wherein the control unit uses the DMA to successively transfer a rectangular region, constituted by a predetermined number of pixels in a main scanning line direction and a predetermined number of pixels in a sub-scanning line direction, of the uncompressed data from the storage unit to the compression processing unit for each rectangular region, and after uncompressed data on a main scanning line is transfer

Abstract: The disclosure relates to adjusting intensities of images. The method includes receiving information identifying of a plurality of regions within an image; receiving an intensity adjustment of at least one of the plurality of regions; adjusting the intensities of the at least one plurality of regions based on the received intensity adjustment; interconnecting at least two of the plurality of regions by applying a two-dimensional method; generating intensity adjustments for at least one pixel outside the plurality of regions based on the received intensity adjustment of at least one of the plurality of regions and the interconnection of at least two of the plurality of regions; and applying the generated intensity adjustments to the image.