Abstract: A tone-mapping method for adjusting a contrast of an image includes generating a luminance histogram of the image according to a luminance and a sharpness of the image; performing histogram equalization on the luminance histogram, to generate a luminance mapping function corresponding to the image; performing a weighted operation on the luminance mapping function and a linear function, to generate a weighted luminance mapping function corresponding to the image; generating a tone-mapping look-up table corresponding to the image according to the weighted luminance mapping function; and adjusting the luminance of the image according to the tone-mapping look-up table, so as to adjust the contrast of the image.

Abstract: A noise estimation apparatus for calculating a noise estimation value of a frame of an image is provided. The noise estimation apparatus includes a distribution calculation unit, a variance calculation unit, a distribution curve generation module and a noise estimation unit. The distribution calculation unit generates a pixel distribution according to multiple pixel data of an ith block of the frame and multiple previous pixel data of the ith block of a previous frame. The variance calculation unit combines the pixel data and the previous pixel data to generate a variance value. The curve distribution generation module generates a curve distribution according to the variance value, and compares the pixel distribution with the curve distribution to generate a weighting value. The noise estimation unit outputs the noise estimation value according to the weighting value and the variance value corresponding to each of the blocks of the frame.

Abstract: Nuclear image data generated by a multimodal imaging device, such as a combined position emission tomography (PET)/magnetic resonance (MR) scanner (12, 14), is attenuation-corrected with a combined patient-specific attenuation correction (AC) map and an AC map template (70) for an MR coil (72) that is present in both the nuclear and MR scanning procedures. A template library (46) contains templates for each of a plurality of MR coils and other accessories. Each template is generated on one of two manners. The coil may be imaged inside the PET scanner 14 with the transmission source 16 (e.g., Ge-68 or Cs-137). A transmission image 48 is reconstructed using the known algorithms and may be used as the AC template directly. Alternatively, the template can be generated by creating a global histogram of the transmission image and identifying segments of the coil or other accessory. An average linear attenuation coefficient (LAC) value is determined from the distribution of the histogram.

Abstract: A method of enhancing an image includes: dividing the input image into multiple tiles; and constructing a respective histogram for each respective multiple tile. The method further includes: dividing each respective histogram into multiple portions, in which each portion represents a count of pixels spanning across pixel intensity value bands. The method also includes: constructing a respective cumulative distribution function (CDF) for each of the multiple portions; and transforming each of the multiple portions using the respective CDF. Each histogram may be divided, as an example, into two portions.

Abstract: A method of enhancing an image. This includes the steps of: dividing the image into multiple tiles and constructing a histogram for each tile, wherein the histogram represents a distribution of pixel intensity values in each tile. In addition, the method applies a bias value to the histogram and a plateau value to the histogram. A cumulative histogram is constructed after applying the bias value and the plateau value to the histogram. The method transforms each pixel in the image, by weighing four cumulative histograms, respectively, in four adjacent and closest tiles to the pixel under consideration. The pixel under consideration is modified based on a weighted cumulative histogram.

Abstract: An image processing apparatus includes an input unit for inputting image data, an attribute information generation unit for generating attribute information about each pixel of the image data, a block division unit for dividing the image data into a plurality of blocks of a predetermined size, a histogram generation unit for generating a histogram of colors and the number of pixels of each color existing in a focused block divided by the division unit, and a color replacement unit, if it is not determined that the area having the focused color is a significant area, for replacing a color of a pixel existing within the area having the focused color with a different color so that the color of the area having the focused color becomes the same as the color of another area contacting the area having the focused color and having the different color according to a predetermined condition.

Abstract: There is provided an image processing apparatus which can suppress degradation of an image quality in a recording material save mode processing and obtain an effect of consumption amount reduction of recording material desired by a user at low costs. A recording material consumption amount at the time of applying first color conversion processing unit is predicted corresponding to inputted image data. The setting of a second color conversion processing is changed from a prediction value and a target value of the recording material consumption amount.

Abstract: There is provided a video processing apparatus comprising a motion vector detection unit for detecting data on the motions of objects by using at least two frames, an interpolation frame generation unit for generating interpolation frames in the horizontal/vertical and temporal directions in accordance with the motion vectors obtained by the motion vector detection unit, and an image feature detection unit for detecting the features of motions extended over the at least two frames, wherein the procedures, performed by the image feature detection unit, of generating interpolation frames in the horizontal/vertical and temporal directions are switched over in accordance with the features of motions.

Abstract: A multidimensional histogram is used to characterize an image (or object), and is used to identify candidate matches with one or more reference images (or objects). An exemplary implementation employs hue information for two of the dimensions, and a second derivative function based on luminance for a third dimension. The simplicity and speed of the detailed arrangements make them well suited for use with cell phones and other mobile devices, which can use the technology for image/object recognition, e.g., in visual search applications.

Abstract: An image processing device separates an original image signal into a plurality of components including a first component serving as a skeleton component and a second component obtained after the first component is separated from the original image signal, obtains a signal level of the first component or the original image signal, sets a tone conversion coefficient to be applied during tone conversion based on the signal level of the first component or the original image signal, performs tone conversion processing on the first component using the tone conversion coefficient, obtains the signal level of the first component, sets a noise reduction processing parameter on the basis of the signal level of the first component, and reduces a noise of the second component using the noise reduction processing parameter and the tone conversion coefficient.

Abstract: Systems and methods for optimizing bilateral filtering operation, by segmenting an image based on predetermined ranges of colors, and reiteratively blurring the image based on each color. In one aspect, colors associated with pixels that are located in such compartment are substantially similar. A blurring procedure(s) can subsequently be applied to each compartment, wherein pixels on the image that have more color similarity to a color of the compartment are weighted more, as compared to pixels that have less color similarity to the color of such compartment.

Abstract: A method of measuring a step height of a device using a scanning electron microscope (SEM), the method may include providing a device which comprises a first region and a second region, wherein a step is formed between the first region and the second region, obtaining a SEM image of the device by photographing the device using a SEM, wherein the SEM image comprises a first SEM image region for the first region and a second SEM image region for the second region, converting the SEM image into a gray-level histogram and calculating a first peak value related to the first SEM image region and a second peak value related to the second SEM image region, wherein the first peak value and the second peak value are repeatedly calculated by varying a focal length of the SEM, and determining a height of the step by analyzing a trend of changes in the first peak value according to changes in the focal length and a trend of changes in the second peak value according to the changes in the focal length.

Abstract: A technique is provided for enhancing the background of an original document image. In the case of a black-and-white image, the background color of the original document image is detected, the desired enhanced background color of the original document image is determined from a background pixel value Pb that is in the center of the background color range, and the original document image is enhanced to the desired enhanced background color. However, if the background of the original document image is in color, the technique further includes obtaining color image histograms of red, blue and green colors of the original document image, smoothing the histograms, and comparing the histograms to determine if they have the same shape.

Abstract: The present invention generates a color template design to format a presentation. According to one aspect, a plurality of template designs are provided on a visual display. A selection of one of the plurality of template designs is received from a user. A plurality of source images that are separate from the plurality of template designs are provided on the visual display. A selection of a color from one of the plurality of source images is received from the user. Colors of the selected template design are automatically adjusted to match the selected the color from the source image. The selected template design may include framing, mat, background, and foreground portions, at least one of which is adjusted. After automatically adjusting the colors, the selected template design may be displayed and/or stored for use as a template.

Abstract: A highly accurate reproduction of visual intensity and contrast rather than the conventional 8-bit color depth is more and more used, motivating the development of an enhanced dynamic range called high bit-depth. A method for encoding a first, low bit-depth image of M bit RGB pixels and a second, high bit-depth video image of N bit RGB pixels, M<N, both having same spatial resolution, comprises generating a first transfer function based on color histograms of the first and the second video image, generating a second transfer function based on the first transfer function, applying the second transfer function to the first video image, wherein a transformed first video image is generated, calculating and encoding the residual, encoding the first video image and transmitting the encoded first video image, the second transfer function and the encoded difference.

Abstract: Provided are a method and apparatus for processing a digital image signal, and a recording medium having recorded thereon the method, in which an image including a subject is generated, a subject region is formed by detecting the subject from the image, the subject region is divided into at least two regions, histograms for the at least two regions are generated, respectively, and it is determined whether a light direction is side lighting by analyzing the histograms for the at least two regions.

Abstract: The present invention provides a method and apparatus to enhance the image contrast of a digital image device, while simultaneously compensating for image intensity inhomogeneity, regardless of the source, correcting intensity inhomogeneities, and producing a more uniform image appearance. Also, the image is enhanced through increased contrast, e.g., tissue contrast in a medical image. In the method, the error between the histogram of the spatially-weighted original image and a specified histogram is minimized. The specified histogram may be selected to increase contrast for accentuation, e.g., on localized regions of interest. The weighting is preferably achieved by two-dimensional interpolation of a sparse grid of control points overlaying the image. A sparse grid is used rather than a dense one to compensate for slowly-varying image non-uniformity.

Abstract: An electronic apparatus and method obtains an original image, converts the original image into gray level to determine a gray level distribution of the original image, and defines a fuzzy region and a flat region and a fuzzy region according to the gray level distribution and a binary threshold. The electronic apparatus and method compares the pixel gray values in the fuzzy region with pixel gray values in the flat region to re-define the pixel gray values in the fuzzy region according to the comparison and a formula, and binarizes the original image to output an binarized image.

Abstract: Methods, apparatus and articles of manufacture for detecting objects in images using color histograms are disclosed. An example method disclosed herein comprises segmenting an image into sets of subregions, different sets having at least one of different subregion sizes or different subregion offsets relative to one another, determining a first comparison metric quantifying comparison of a first subregion with the object based on differences between bin values of a second color histogram corresponding to the object and adjusted bin values of a first color histogram corresponding to the first subregion, determining a second comparison metric quantifying comparison of a second subregion with the object, and comparing the first and second comparison metrics with a threshold to identify at least one of the subregions as being associated with a possible location of the object in the image.

Abstract: A system and method includes reception of a first image data value of a digital image, determination of a first index based on the first image data value, determination of a value stored in a first array of a first shared memory at the first index, and determination of whether the value stored in the first array of the first shared memory at the first index is equal to the first image data value. If the value stored in the first array of the first shared memory at the first index is equal to the first image data value, 1 is added to a count value stored in a second array of the first shared memory at the first index. If the value stored in the first array of the first shared memory at the first index is not equal to the first image data value a count value stored in a second shared memory in association with the first image data value is updated.

Abstract: Methods of collapsing volume data to a lower dimensional representation of the volume data are provided. The methods include collapsing volume data to a lower dimensional representation of the volume data using histogram projection. Related systems and computer program products are also provided.

Abstract: An image processing device (100) includes: a luminance distribution information preparation section (110) for preparing a luminance histogram in which each luminance range serves as a class, by counting the number of pixels belonging to each luminance range; a weight correction section (120) for generating, for each luminance range, a weighting value which is proportional to a corresponding class value; and an image processing section (140) for correcting a luminance value of each pixel so that a difference between a maximum luminance value and a minimum luminance value in the luminance range is determined by an increasing function with respect to both (i) a frequency of the luminance range and (ii) a weighting value of the luminance range.

Abstract: Processes such as image matching can be improved by utilizing a Polar Accumulated Signed Gradient (PASG), a feature descriptor vector that utilizes polar coordinates. Such an approach is efficient because it avoids the costly image rotation and resampling of conventional processes. Further, the gradients can be sampled over different regions in order to achieve effective weighting without analyzing all gradients and applying a weighting factor. Such efficiencies enable image matching to be performed on devices with limited computing capacity, such as smart phones and tablet computers.

Abstract: A method for toning mapping high dynamic range (HDR) video for display in low dynamic range display comprises accessing the HDR video; producing a luminance information for the individual frames; partitioning different consecutive groups of frames into segments responsive to the luminance information; classifying the segments into static luminance segments and transient luminance segments; producing a tone mapping parameter set for the static luminance segments; producing a tone mapping parameter set for at least one of the transient luminance segments responsive to the tone mapping parameter set of an adjacent static luminance segment; and tone mapping the static luminance segments and transient luminance segments according to the respective tone mapping parameter sets.

Abstract: A method of removing fog from the images/videos independent of the density or amount of the fog and free of user intervention and a system for carrying out such method of fog removal from images/videos are disclosed. The removal of fog from images and video involve airlight estimation and airlight map refinement based restoration of foggy images and videos. Advantageously, removal of fog from images and videos of this invention would require less execution time and yet achieve high perceptual image quality with reduced noise and enhanced contrast. The proposed method is adapted for RGB Colour model and advantageously also for HSI colour model involving reduced computational requirements and be user friendly and supposed to have wide application and use.

Abstract: A method for determining an estimated clutter level of an input digital image based on an inequality index. The inequality index is determined by partitioning the input digital image into small sub-images and analyzing the sub-images to determine a set of image features. The image features are associated with a set of designated reference features, and the inequality index is determined based on the statistical variation of the reference features. The inequality index is compared to a predefined threshold to classify the input digital image as a rich-content image or a low-content image. For rich-content images, the estimated clutter level is determined responsive to a set of scene content features relating to spatial structures or semantic content of the input digital image is determined by analyzing the input digital image. For low-content images, the estimated clutter level is determined responsive to an overall luminance level.

Abstract: Disclosed is a method for identifying lawn grass which includes capturing an image of the terrain in front of a mower, segmenting the image into neighborhoods, calculating at least two image statistics for each of the neighborhoods, generating a binary representation of each image statistic. The binary representation of each image statistic is generated by comparing the calculated image statistic values to predetermined image statistic values for grass. The method further includes weighting each of the binary representations of each image statistic, and summing corresponding neighborhoods for all image statistics. A binary threshold is applied to each of the summed neighborhoods to generate a binary map representing grass containing areas and non-grass containing areas.

Abstract: The adaptive contrast enhancer uses an adaptive histogram equalization-based approach to improve contrast in a video signal. For each video frame, the histogram of the pixel luminance values is calculated. The calculated histogram is divided into three regions that are equalized independently of the other. The equalized values are averaged with the original pixel values with a weighting factor that depends on the shape of the histogram. The weighting factors can be also chosen differently for the three regions to enhance the darker regions more than the brighter ones. The statistics calculated from one frame are used to enhance the next frame such that frame buffers are not required. Many of the calculations are done in the inactive time between two frames.

Abstract: Provided are an image brightness control device and an image brightness control method for improving the definition of brightness of the entire image and/or improving the definition of brightness of local areas using local brightness information. The image brightness controlling device includes: a preprocessing unit acquiring an offset table for controlling a dynamic range corresponding to an image range of an input image using brightness values of color data of the input image; and a tone mapping unit mapping the offset table onto the color data. It is possible to improve the definition of brightness so as to correspond to the characteristic of the input image, by automatically considering how to reflect a distribution characteristic of an image.

Abstract: A picture quality controlling device (10) that controls a picture quality for an image signal which is input including: a histogram generation unit (14) generating a histogram for at least one of brightness, chromaticity, color, and frequency information pieces from an image contained in the image signal; a threshold value comparing unit (17) comparing the histogram with a threshold value previously set for the histogram in order to determine whether control of the picture quality for the image signal is necessary; and a picture quality controlling unit (18) extracting a histogram pattern corresponding to the histogram from a reference table including plural predetermined histogram patterns, and controlling the picture quality based on a controlled parameter corresponding to the extracted histogram pattern if the control is determined to be necessary based on a result obtained by the threshold value comparing unit.

Abstract: A method is provided for training and using an object classifier to identify a class object from a captured image. A plurality of still images is obtained from training data and a feature generation technique is applied to the plurality of still images for identifying candidate features from each respective image. A subset of features is selected from the candidate features using a similarity comparison technique. Identifying candidate features and selecting a subset of features is iteratively repeated a predetermined number of times for generating a trained object classifier. An image is captured from an image capture device. Features are classified in the captured image using the trained object classifier. A determination is made whether the image contains a class object based on the trained object classifier associating an identified feature in the image with the class object.

Abstract: Methods and apparatus for color grading stereoscopic and autostereoscopic (multi-view) view video content are provided. Video content for one view is adjusted so that a histogram of the adjusted video data is more similar to a target histogram than the original, unadjusted video content for the one view. The adjusted video content is automatically color graded based on a color grading of video content for another view. The target histogram may be calculated for the video content for the other view.

Abstract: The invention relates to a method for temporal video registration of a target video with a master video comprising steps of automatic selection a plurality of key frames for target video and a plurality of key frames for master video; sparse registration of a plurality of key frames for target video with a plurality of key frames for master video; dense registration of frames of target video with frames of master video belonging to a temporal segment including registered key frames.

Abstract: Videos are received and indexed based on fingerprints generated for the videos, using lookup keys which correspond to sub portions of the reference fingerprints. Specifically, a set of lookup keys is selected such that the number of reference fingerprints such that the clumping associated with the associated each of the lookup keys is minimized. Clumping occurs when a number of reference identifiers associated with a lookup key exceeds a maximum value.

Abstract: Methods, storage mediums, and systems for image data processing are provided. Embodiments for the methods, storage mediums, and systems include configurations to perform one or more of the following steps: background signal measurement, particle identification using classification dye emission and cluster rejection, inter-image alignment, inter-image particle correlation, fluorescence integration of reporter emission, and image plane normalization.

Abstract: An image processing apparatus of the present invention includes: a blank document determination section determining whether or not input image data is image data of a blank document, regardless of a process mode set for setting a process with respect to the input image data; a storage device storing the input image data in association with a determination result made by the blank document determination section; and a control section (i) reading out the input image data from the storage device and (ii) excluding the input image data determined as image data of a blank document by the blank document determination section, from images to be displayed by the image display device, when the image display device carries out a preview display of the input image data. This configuration makes it possible to carry out a preview display in which a blank document (blank page document) is skipped, without reading the document again.

Abstract: Methods, apparatus and systems for determining a power spectral density (PSD) of a signal, in which modulation of the signal is employed to facilitate determination of one or more PSD values over a wide range of frequencies. In some implementations, the signal may represent a wide-sense stationary random process. In one example, the signal is measured/sampled during a plurality of measurement windows, during which an intensity of the signal is modulated at one or more modulation frequencies. A variance of a set of quantities determined from the signal samples is calculated and used to determine respective values of the power spectral density (PSD) for the signal at the one or more modulation frequencies. The one or more modulation frequencies may be chosen in excess of the Nyquist frequency of the sampling process, such that the signal may be characterized for one or more frequencies above the Nyquist limit.

Abstract: A video processor includes a video stream translation module configured to generate a translated luminance value for a pixel of a current frame of a video data stream. The translated luminance value is based on a first luminance value for the pixel and a first translation matrix for the current frame of the video data stream. The video processor includes a filter configured to generate an output luminance value for the pixel based on the translated luminance value and a target translated luminance value for the pixel. The output luminance value may be based on a weighted average of the translated luminance value and the target translated luminance value using a first weighting factor. The video processor may include a first weighting factor generator configured to generate the first weighting factor based on luminance values of the current frame of the video stream.

Abstract: Three-dimensional (3D) glasses, a method for driving 3D glasses, and a system for providing a 3D image are provided. The 3D glasses driving method includes detecting a first pattern corresponding to a left eye image and a second pattern corresponding to a right eye image from a 3D display apparatus, converting the first pattern into a first histogram and the second pattern into a second histogram, comparing the converted first and second histograms with first and second optimal histograms, and adjusting an opening or a closing of a left eye glasses part and a right eye glasses part of the 3D glasses based on the comparison.

Abstract: There are provided an apparatus and a method for estimating edge areas of pixels in a digital image to thereby prevent an edge sharpening algorithm from being applied to non-edge area of the digital image. Therefore, the apparatus can accurately determine whether each pixel is in an edge area or in a non-edge area, by generating a binary mask obtained by using a luminance difference average between each pixel and each of neighboring pixels in the digital image. Moreover, the determination of an edge-area or a non-edge area may be applied to various digital images, by adjusting a level of edge-area determination.

Abstract: A method for providing an output image based on an input image, the method comprising determining a location of an output pixel with respect to an input image, determining values of elements of a filter array such that the effective width of the filter array depends on the density of exposed input pixels within the input image, and determining the value of the output pixel by performing a sum-of-products operation between non-zero values of the elements of the filter array and the values of input pixels of the input image located at respective positions, when the filter array is superimposed on the input image such that the center of the filter array corresponds to the location of the output pixel.

Abstract: A method for sharpening a captured image includes the steps of (i) identifying a plurality of edge pixels in the captured image, (ii) reviewing the plurality of edge pixels to identify one or more line pixels, and one or more non-line pixels in the captured image (354), and (iii) sharpening the captured image utilizing a first level of overshoot control for the non-line pixels (362), and utilizing a second level of overshoot control for the line pixels (360) The method also includes the steps of (i) identifying an intensity value for each of a plurality of neighboring pixels that are positioned near a selected pixel in a predetermined pixel window that have the highest intensity values and the lowest intensity values.

Abstract: Techniques to improve image fusing operations using intensity mapping functions (IMFs) are described. In one approach, when a reference image's pixel values are within its' IMF's useful range, they may be used to generate predicted secondary image pixel values. When the reference image's pixel values are not within the IMF's useful range, actual values from a captured secondary image may be used directly or processed further to generate predicted secondary image pixel values. The predicted and actual pixel values may be used to construct predicted secondary images that may be fused. In another approach, the consistency between pixel pairs may be used to generate consistency-based weighting factors that may be used during image fusion operations.

Abstract: Machine vision based obstacle avoidance system is provided. The system utilizes a CCD camera to capture an image. A normalized image and dynamic masking is used in object detection.

Abstract: An automatic brightness adjusting method and apparatus for image signal processor (ISP) is provided. The image processing apparatus may include a histogram generating unit, a cumulative distribution function calculator, and a histogram equalization (HE) unit. The histogram generating unit may generate a histogram of brightness values of pixels in an input image. The cumulative distribution function calculator may generate a cumulative distribution function and an inverse cumulative distribution function, based on the generated histogram. The HE unit may generate a conversion function based on the cumulative distribution function and the inverse cumulative distribution function, and may apply HE to the input image based on the conversion function so as to generate an output image.

Abstract: The image correction processing device (100) disclosed in the description is configured by integrating a first external terminal (CAMDI) [7:0] to which digital input image data is inputted from outside of the device, an image correction processing circuit (200) applying predetermined image correction processing on the digital input image to create digital output image data, a second external terminal (CAMDO) [7:0] outputting the digital output image data to the outside of the device, an encoder circuit (300) converting the digital output image data to analog composite video-type output image data, and a third external terminal (VOUT) outputting the analog composite video-type data to the outside of the device.

Abstract: A method for evaluating video quality of a video stream comprising the steps of a) calculating, for at least a first frame of a series of frames from said video stream, a true value of at least one video quality-related parameter associated to said first frame; b) calculating a predicted value of said video quality-related parameter for at least a second frame from said series of frames based on said true value associated to said first frame; c) calculating a true value of said video quality-related parameter associated to said second frame; and d) judging the video quality of said second frame based on a difference between true and predicted values of the at least one video quality-related parameter associated to said second frame.

Abstract: Disclosed is a method and a device for denoising a video based on non-local means, which is capable of making self-adaptive adjustment in response to illumination variance of the frame in the video.

Abstract: A pixel processing method includes: selecting a first plurality of color component values of a first plurality of pixels within a pixel block in a buffering device, performing a first color component process upon a first target pixel in the first plurality of pixels to determine a first target color component value of the first target pixel; and selecting a second plurality of color component values of a second plurality of pixels within the pixel block at the same time as the first color component process is performed, and performing a second color component process upon a second target pixel in the second plurality of pixels according to the second plurality of color component values to determine at least one underdetermined target color component value of the second target pixel, wherein the second target pixel has been processed by the first color component process.

Abstract: Color management which converts source device colors into counterpart colors in a destination device color space. Device independent source and destination device gamut boundaries are obtained. A color image is generated in the source device color space. The color image is transformed into an image in a device independent color space. A gamut boundary for the device independent image is generated, based on the content of the device independent image. The source device gamut boundary is shrunk in a hue symmetric manner, such that color hues do not change, until it touches the image gamut boundary. Colors of the device independent image are mapped onto a gamut of the destination device by invoking a compression-type gamut mapping algorithm that uses the modified source device gamut boundary and the destination device gamut boundary to perform gamut mapping. The gamut mapped colors are converted into colors in destination device dependent color space.