Abstract: A video refocusing system operates in connection with refocusable video data, information, images and/or frames, which may be light field video data, information, images and/or frames, that may be focused and/or refocused after acquisition or recording. A video acquisition device acquires first refocusable light field video data of a scene, stores first refocusable video data representative of the first refocusable light field video data, acquires second refocusable light field video data of the scene after acquiring the first refocusable light field video data, determines a first virtual focus parameter (such as a virtual focus depth) using the second refocusable light field video data, generates first video data using the stored first refocusable video data and the first virtual focus parameter, wherein the first video data includes a focus depth that is different from an optical focus depth of the first refocusable light field video data, and outputs the first video data.

Abstract: A sample set of images is received. Each image in the sample set may be associated with one or more social cues. Correlation of each image in the sample set with an image class is scored based on the one or more social cues associated with the image. Based on the scoring, a training set of images to train a classifier is determined from the sample set. In an embodiment, an extent to which an evaluation set of images correlates with the image class is determined. The determination may comprise ranking a top scoring subset of the evaluation set of images.

Abstract: An object of the present invention is to provide a fitting support device and method which make it possible to reliably select apparel such as clothes that match user's appearance. The fitting support device includes: a color-characteristic processing unit 100 that acquires color characteristic data relating to user's skin color on the basis of captured image data; a body processing unit 101 that colors, on the basis of the color characteristic data, three-dimensional body shape data corresponding to body shape data on a user to thereby create body image data; a color-pattern processing unit 102 that acquires color pattern data corresponding to the color characteristic data, on the basis of clothing data; a wearing processing unit 103 that creates wearing image data on the basis of the body image data and the color pattern data; and a fitting processing unit 104 that creates fitting image data by synthesizing head portion image data on the user and the wearing image data.

Abstract: An image alignment method and apparatus, where the method and apparatus include obtaining image information of two to-be-aligned images, determining, using a cross-correlation measurement model, first coordinate offset according to the image information of the two images, where the first coordinate offset are used to indicate position deviations of to-be-aligned pixels between the two images in the coordinate system, and aligning the two images according to coordinates of pixels in the first image in the coordinate system and the first coordinate offset.

Abstract: The present principles relate to a method and a device for reducing noise in a component of a picture. The method includes obtaining a low-pass filtered component by low-pass filtering the component of the picture, for a current pixel in the component of the picture. For at least one current neighboring pixel of the current pixel, computing a distance, relative to the current neighboring pixel, between the value of the current pixel in the low-pass filtered component and the value of the current neighboring pixel in the low-pass filtered component. When the distances relative to the at least one neighboring pixels of the current pixel are lower than a first threshold, modifying the value of the current pixel in said component of the picture according to a linear combination of the value of the current pixel in the component of the picture and the value of the current pixel in the low-pass filtered component.

Abstract: The present application discloses an image interpolation method for interpolating a pixel and enhancing an edge in an image, comprising detecting an edge position in an image; obtaining edge characteristics associated with the edge position; determining whether an interpolation point is located within an edge region based on the edge characteristics of an array of p×q pixels surrounding the interpolation point, wherein p and q are integers larger than 1; determining edge direction of an interpolation point located within the edge region, wherein the edge direction is normal to gradient direction; classifying the edge direction accordingly to in angle subclasses and n angle classes; wherein each angle class comprises one or more subclasses, m and n are integers, and n?m; selecting a one-dimensional horizontal interpolation kernel based on the angle class; performing a horizontal interpolation using the selected one-dimensional horizontal interpolation kernel; and performing a vertical interpolation using a one

Abstract: Identifying a masked suspect is one of the toughest challenges in biometrics that exist. This is an important problem faced in many law-enforcement applications on almost a daily basis. In such situations, investigators often only have access to the periocular region of a suspect's face and, unfortunately, conventional commercial matchers are unable to process these images in such a way that the suspect can be identified. Herein, a practical method to hallucinate a full frontal face given only a periocular region of a face is presented. This approach reconstructs the entire frontal face based on an image of an individual's periocular region. By using an approach based on a modified sparsifying dictionary learning algorithm, faces can be effectively reconstructed more accurately than with conventional methods. Further, various methods presented herein are open set, and thus can reconstruct faces even if the algorithms are not specifically trained using those faces.

Abstract: A method for increasing enhancing local contrast in a thermal image for a class of objects having a thermal characteristic is provided. The method including providing thermal image data representing a first thermal image, where the first thermal image is acquired by an absolute calibrated thermal imaging system, redistributing the thermal image data having a first intensity distribution into a second intensity distribution using a predetermined redistribution function, where the predetermined redistribution function is based on the thermal characteristic, such that the local contrast is enhanced for the class of objects, outputting the redistributed thermal image data as the thermal image. An apparatus for enhancing local contrast in a thermal image for a class of objects having a thermal characteristic is further provided.

Abstract: A biological image processing device includes: a memory; and a processor coupled to the memory and the processor configured to execute a process, the process comprising: extracting at least one line from contours of a palm and principal lines of the palm shown in an image of the palm; extracting pixels of the line extracted by the extracting of at least one line; setting a local region for each of the pixels, each local region including each corresponding one of the pixels; calculating, for each local region, local orientations of the line extracted by the extracting of at least one line, in accordance with gradient intensities related to respective orientations of each corresponding local region; and calculating an orientation of the palm in accordance with a statistical amount of the respective local orientations.

Abstract: A method for operating a scanning microscope and for determining point spread functions, with which sample images are recorded with the scanning microscope. The method includes scanning a sample with at least one illuminating light beam; recording at least one sample image with a detector device during a scan by the illuminating light beam; and comprising the point spread function, with which a sample image is recorded, from the at least one sample image. A detector device having receiving elements is used, where the distance between the receiving elements is smaller than a diffraction disk that generates a sample point on the detector device. Detector signals, generated by means of the receiving elements, are read out for each of the different positions of the illuminating light beam on the sample, as a result of which the scanning of the sample allows the detector signals, which are read out, to generate a plurality of sample images.

Abstract: An image processing method includes at least the following steps: partitioning a picture into a plurality of slices, wherein each slice row in the picture includes at least one slice; generating a compressed picture by encoding each of the slices; and controlling at least one of start of transmission of encoded data of a slice row and end of the transmission of encoded data of the slice row according to a transmission synchronization event.

Abstract: A resolution estimating device is achieved which is capable of adequately estimating the resolution of the original image of any received image signal. A resolution estimating device (1000) includes a proximity-degree acquiring unit (1), an accumulation unit (2), a frequency transform unit (3), and a spectrum analyzing unit (4). The proximity-degree acquiring unit (1) acquires the proximity degree value of each target pixel. The accumulation unit (2) accumulates the proximity degrees of the target pixels, for example, in the vertical direction on the image, and obtains a one-dimensional data sequence of the accumulated proximity degree values. The frequency transform unit (3) performs a frequency transform on the one-dimensional data sequence of the accumulated proximity degree values obtained by the accumulation unit (2), and obtains a one-dimensional frequency-component data sequence which is a one-dimensional data sequence for frequency regions.

Abstract: In one embodiment, a method includes identifying a shared visual concept in visual-media items based on shared visual features in images of the visual-media items; extracting, for each of the visual-media items, n-grams from communications associated with the visual-media item; generating, in a d-dimensional space, an embedding for each of the visual-media items at a location based on the visual concepts included in the visual-media item; generating, in the d-dimensional space, an embedding for each of the extracted n-grams at a location based on a frequency of occurrence of the n-gram in the communications associated with the visual-media items; and associating, with the shared visual concept, the extracted n-grams that have embeddings within a threshold area of the embeddings for the identified visual-media items.

Abstract: An X-ray image processing apparatus for performing image processing for frames successively obtained by an X-ray sensor acquires a first analysis value and a second analysis value by analyzing each of the successively obtained frames, and calculates, as a first statistic and a second statistic, statistics in a time direction of the first analysis values and the second analysis values of the successively obtained frames. Based on the calculated first and second statistics, the X-ray image processing apparatus determines whether to correct the first analysis value. If it is determined to correct the first analysis value, the X-ray image processing apparatus corrects the first analysis value based on the first statistic.

Abstract: The present invention relates to an image object category recognition method and device. The recognition method comprises an off-line autonomous learning process of a computer, which mainly comprises the following steps: image feature extracting, cluster analyzing and acquisition of an average image of object categories. In addition, the method of the present invention also comprises an on-line automatic category recognition process. The present invention can significantly reduce the amount of computation, reduce computation errors and improve the recognition accuracy significantly in the recognition process.

Abstract: A method and system for assigning colors to an image or part thereof, the method comprising: selecting a sequence of colors for assignment to the image or part thereof; determining a minimum intensity IMIN within the image or part thereof; determining a maximum intensity IMAX within the image or part thereof; and determining relative intensity values RIV(i) for each pixel or voxel i according to; (I) where I(i) is an intensity of pixel or voxel /, and ƒ is a preselected function (such as to re-arrange the normalized values); and assigning colors to at least some pixels in the image or part thereof based on the relative intensity values and an order of each of the colors in the sequence.

Abstract: Provided are an image processing system, an image processing method, and a program capable of suitably performing the association of a person appearing in a picture in accordance with a highly reliable user input. This image processing system includes: an input unit for receiving an input of pictures captured by multiple video cameras; a person-to-be-tracked registration unit capable of registering one or more persons appearing in the pictures input from the input unit; a moving image display unit for displaying, on a display device, the pictures input by the input unit, and a UI generation unit capable of registering that the person appearing in the displayed pictures and the person registered by the person-to-be-tracked registration unit are the same person, or not the same person.

Abstract: An object is to ensure clear and easy quantification of the textures such as metallic texture and shiny texture of pearl pigment and to rationalize comparison inspection between an inspection object and a reference object. A coloring inspection apparatus 1 includes a camera 2 that is configured to have three spectral sensitivities (S1(?), S2(?), S3(?)) linearly and equivalently converted to a CIE XYZ color matching function, an arithmetic processing unit 3 that is configured to obtain and compute coloring data by conversion of an image which has three spectral sensitivities and is obtained by the camera 2 into tristimulus values X, Y and Z in a CIE XYZ color system, and lighting units 6 that are configured to illuminate an automobile 5 as an example of measuring object. The coloring inspection apparatus 1 computes a color distribution consistency index that represents a ratio of overlap of two xyz chromaticity histogram distributions of an inspection object Q and a reference object R, so as to inspect color.

Abstract: The invention relates to a device and a method for determining the weight of product (2), in particular a pharmaceutical product, which is located in a container (3). The device comprises at least one x-ray source (28), which produces a radiation path (18), for passing radiation through the container (3), and a sensor (14), which detects the radiation of the container (3) through which radiation is passed in the form of an image (12), wherein an evaluating apparatus (14), is provided, which divides the image (12) of the container (3) through which radiation is passed into at least one evaluation region (21) in which there is no product (2).

Abstract: Methods for characterizing two-dimensional concept drawings are disclosed. The concept drawings comprise cross-sections intersecting at cross-hairs. The method comprises: determining, for each cross-section: a plane on which the cross-section is located, the plane having a normal vector in a three-dimensional coordinate system; and, for each cross-hair on the cross-section, a tangent vector in the three-dimensional coordinate system which is tangent to the cross-section at the cross-hair. For each cross-hair comprising ith and jth intersecting cross-sections, one or more constraints are satisfied, the constraints comprising: the normal vector ni of the plane on which the ith cross-section is located is at least approximately orthogonal to the normal vector nj of the plane on which the jth cross-section is located; and the tangent vector tij to the ith cross-section at the cross-hair is at least approximately orthogonal to the tangent vector tji to the jth cross-section at the cross-hair.