Abstract: Provided is an image fusing apparatus for fusing a thermal image and a visible image of a subject. The image fusing apparatus includes: a determination processor configured to determine importance of each pixel, based on a luminance value thereof, of the thermal image and the visible image; a pixel coefficient setting processor configured to set a pixel coefficient for each pixel of the thermal image based on the importance of each pixel of the thermal image and the visible image; a thermal image processor configured to generate another thermal image by applying the pixel coefficient to the luminance value of each pixel of the thermal image; and an image fusing processor configured to fuse the other thermal image and the visible image to generate a fused image.

Abstract: This disclosure provides systems, methods, and apparatus for analyzing a video are disclosed. An input video signal can be received and a quality metric associated with the input video signal can be determined. A parameter to be used in a first object tracking process can be selected, based in part on the quality metric associated with the input video signal. A background model can be extracted from the input video signal based on an online median estimate of the intensity values of the pixels in the image frames. The online median estimate can be calculated using a quantile function.

Abstract: A geodetic surveying device has a sighting unit pivotable about two axes. The sighting unit defines a target direction in a coordinate system and has a camera for capturing a camera image substantially in the target direction. The device can display object data that is stored in a database with a respective position reference indicating a position in the coordinate system. The device includes a graphical output unit that displays the camera image and the object data. The device has a filter functionality for the object data, with dynamic filtering based on the current range of view and static filtering based on a user selectable or specifiable selection criterion. The filtered object data is displayed on the output unit with markings representing the object data conjointly with the camera image. The markings are displayed at a respective point in the camera image referenced by the position reference.

Abstract: A method for calibrating a biological instrument is provided. The method comprises the steps of acquiring an image of at least one biological sample array, determining a first region of interest within the image, wherein the first region of interest comprises a first plurality of locations on the at least one biological array; and identifying within the first region of interest, a plurality of image elements associated with each of the first plurality of locations on the at least one biological array.

Abstract: This document describes techniques and apparatuses for area-dependent image enhancement. These techniques are capable of enabling selection, through a touch-enabled mobile-device display, of an area of a photographic image through movement of a spatially-variable implement, such as brush icon moved over the image. Selected areas can be enhanced differently than other areas, such as to apply sharpening to the selected area and blurring to a non-selected area.

Abstract: An image processing apparatus that obtains a synthesized image of a subject viewed from an arbitrary viewpoint includes a calculator, a storage, and a synthesizer. The calculator calculates a correction value for a pixel value of a pixel that partially constitutes the picked-up images on the basis of a brightness of each of the plurality of picked-up images. The storage stores the correction value for each of the pixels. The synthesizer obtains a pixel value of a pixel in the synthesized image that corresponds to the pixel that partially constitutes the picked-up images by correcting a pixel value of the pixel that partially constitutes the picked-up images on the basis of a positional relationship of the pixel in the picked-up images, a correspondence relationship between the picked-up images and the synthesized image, and the correction value, and thereby generates the synthesized image.

Abstract: A method and system for producing a scalar image from a derivative field and a vector image is disclosed. A function class c is selected, where all members of the class c are functions which map each vector of the vector image to a unique scalar value. A function f is selected from the class c which maps the vector image to a scalar image, the derivative of which is closest to the derivative field. The scalar image is generated from the vector image by using f to calculate each scalar value in the scalar image from a corresponding vector in the vector image.

Abstract: Methods of performing two point calibration of a linear-logarithmic image sensor pixel include measuring voltages of a floating diffusion region of the pixel after establishing a plurality of unequal sub-threshold currents through a transfer transistor of the pixel. These sub-threshold currents operate to sequentially increase a voltage of the floating diffusion region to respective voltage levels that enable knee-point (KNPT) voltage and logarithmic sensitivity (LOGS) determination. The methods also include depleting a photodiode within the pixel by driving a cathode of the photodiode with a pull-up current in advance of establishing the sub-threshold currents. The method is photocurrent-independent.

Abstract: A computer-implemented method for detecting a copy of a reference video, comprises segmenting respective ones of multiple frames of the reference video into multiple regions, determining sets of image features appearing in respective ones of the multiple frames, determining a measure for the relative number of image features for a given region across the multiple frames, generating a spatio-temporal signature for the reference video using the determined measures, and comparing the signature for the reference video against a spatio-temporal signature of a query video to determine a likelihood of a match.

Abstract: An image recovery method is disclosed for eliminating an effect of an environmental medium. The image recovery method includes receiving a captured image affected by the environmental medium, defining a respective local window with each pixel located at a center of the respective local window, and under an assumption that original radiance of all pixels within the respective local window in the captured image are identical, performing a minimization calculation for each local window, to obtain a corresponding transmission of each pixel in the captured image.

Abstract: A method and image processing system for removing a visual object from an image, e.g., a moving image, is described. An image is provided in which a visual object to be removed is selected, for which a mask is determined. Pixels outside the mask that are intended to be used for replacing pixels inside the mask are selected, based on a similarity measure, comprising an appearance similarity measure representing the visual similarity between a previously selected pixel for replacing the pixel to be replaced and the pixel to be selected, and a geometry similarity measure, representing the closeness of the pixel to be selected to the pixel among the pixels outside the mask that was previously used for replacing the pixel adjacent to the pixel to be replaced. The pixels inside the mask are replaced by copying the properties of the selected pixels to the respective pixels to be replaced.

Abstract: The luminance information of an image captured by a multi-lens camera system can be improved by selecting a luminance information source for each portion of the captured image. Each lens of the camera system can capture an initial image. For each portion of a final image, a corresponding initial image portion can be selected as the luminance information source. The portions of the final image and initial images can be pixels, groups of pixels, or other image portions. The luminance information from the selected initial image portions is combined to form final image luminance information. Chrominance information can also be selected from the initial images to form final image chrominance information, and the final image chrominance information and the final image luminance information can be combined to form a final image.

Abstract: A method and system for real time luminance correction and detail enhancement of a video image including the steps of extracting a luminance component from a video image, separating the luminance component into an illumination layer and a scene reflectivity layer, the illumination layer having a dynamic range, compressing the dynamic range of the illumination layer to generate a corrected illumination layer, filtering the reflectivity layer to generate an enhanced reflectivity layer; and combining the corrected illumination layer with the enhanced scene reflectivity layer to generate an enhanced luminance image, is provided. A system for real time luminance correction and detail enhancement of a video image is also provided.

Abstract: A method and an apparatus for deblurring an image from a sequence of images are described. The image comprises pixels. A motion estimation stage estimates motion of the pixels of the image. A point spread function modeling stage models point spread functions for the pixels of the image using the motion estimates. A deconvolution stage determines a deblurred estimate of the image using the modeled point spread functions. A feedback loop allows iteratively improving the motion estimates for the pixels until the modeled point spread functions converge.

Abstract: An image processing apparatus includes a gamma correction unit configured to perform gamma correction on linear-scale raw image signals to generate log-scale signals, a demosaicing unit configured to demosaic the log-scale signals generated by the gamma correction unit to generate image signals, and an inverse gamma correction unit configured to perform inverse gamma correction on the image signals generated by the demosaicing unit to generate linear-scale signals.

Abstract: Generation of a plurality of orthomosaic image layers for a geographical area, wherein the layers comprise different spatial resolutions and are radiometrically normalized to facilitate improved radiometric consistency when zooming relative to the geographic area. In applications that facilitate zooming with respect to a geographic area imaged by the orthomosaic layers, radiometric normalization of the orthomosaic image layers may reduce radiometric discontinuities when zooming in, zooming out, and/or panning a displayed portion that is output to the user. The orthomosaic layers may be generated based on one or more orthomosaic image layer or may be developed independently using a source images. In any regard, the radiometric normalization may include generating a normalization function based on image metadata that is calculated and may be independent of the spatial resolution of the image.

Abstract: Methods disclosed permit the identification of frame buffer pixels for trapping. In some embodiments, flags associated with pixels in the frame buffer may be used to provide an indication of pixels for trapping. A bit in a flag associated with a pixel may be set when the pixel is painted, if the luminosity value of the pixel does not exceed a luminosity threshold. In some embodiments, the method discloses a process for updating the value of the bit through the rasterization process. The pixel may be identified as a candidate for trapping based on the value of the at least one bit at trapping time.

Abstract: Some embodiments provide a computer program for performing a color matching operation. The computer program identifies first and second images. Each image includes several pixels. Each pixel includes a luma component value. Based on analysis of the luma component values of the pixels of the first and second images, the computer program determines a set of transforms to modify pixel values of the first image so that the pixel values of the first image are similar to pixel values of the second image. The computer program applies the set of transforms to the first image such that the pixel values of the first image are similar to the pixel values of the second image.

Abstract: Control sections of displays 11 each determine control information Pi used when area-active driving is performed individually and transmit the control information Pi to a multi-display control section 12. The multi-display control section 12 determines control information Ps for the entire device on the basis of the received pieces of control information Pi and transmits the control information Ps to the control sections of the displays 11. All the displays 11 perform area-active driving on the basis of the same control information Ps. In this way, occurrence of a luminance difference or chromaticity difference among display screens of the displays 11 is prevented and the quality of a displayed image is improved.

Abstract: Extracting financial card information with relaxed alignment comprises a method to receive an image of a card, determine one or more edge finder zones in locations of the image, and identify lines in the one or more edge finder zones. The method further identifies one or more quadrilaterals formed by intersections of extrapolations of the identified lines, determines an aspect ratio of the one or more quadrilateral, and compares the determined aspect ratios of the quadrilateral to an expected aspect ratio. The method then identifies a quadrilateral that matches the expected aspect ratio and performs an optical character recognition algorithm on the rectified model. A similar method is performed on multiple cards in an image. The results of the analysis of each of the cards are compared to improve accuracy of the data.

Abstract: A blurring process is performed on an addition area including a point light source area detected in an image to be processed so that the nearer to the circumference of the addition area, the higher the luminance value while an addition coefficient is being increased according to a distance from the center.

Abstract: Image denoising techniques are described. In one or more implementations, a denoising result is computed by a computing device for a patch of an image. One or more partitions are located by the computing device that correspond to the denoising result and a denoising operator is obtained by the computing device that corresponds to the located one or more partitions. The obtained denoising operator is applied by the computing device to the image.

Abstract: The present disclosure provides for path rendering including receiving, with a graphics processing unit (GPU), data indicative of a path segment of a path to be rendered. The systems and methods render the path segment by performing a fill of the path segment, which includes tessellating the path segment into a first plurality of primitives including a triangle per primitive, storing a first plurality of primitives in a stencil buffer, and drawing a bounding box of the path segment and rendering the bounding box with a stencil test enabled. The systems and methods also stroke the path segment, including tessellating the path into a second plurality of primitives, re-tessellating the second plurality of primitives, cutting the second plurality of primitives according to a dash pattern, creating a cap at a location of a cut, and creating a triangulation of a stroke and rasterizing the stroke based on the triangulation.

Abstract: Easy-to-learn, efficient, and/or unambiguous methods for controlling rotation and/or other manipulation of multi-dimensional (for example, 2D and/or 3D) images and/or objects are disclosed. The systems and methods may be used for any type of image display/manipulation on a wide variety of computer systems and coupled displays including personal computers with monitors, phones, tablets, and televisions. In general, a user may select a particular rotation plane (for example, rotation only in x axis) by placement of a cursor, or touch of a finger, over a certain portion of the image such that subsequent movements of the mouse result in only rotations in the particular plane, and unwanted rotations and/or other manipulations in other planes do not occur. In this way, the user can more precisely control rotations of the 3D image and/or object.

Abstract: An image processing device, which uses a dictionary which stores data of two or over sets which associate a blurred patch of a blurred image generated by blurring a predetermined image with a restoration patch of the predetermined image. The device includes a processor that processes instructions to generate a tentative restored image from the restoration patch selected based on values indicating similarities between plural input patches generated by dividing an inputted input image and the blurred patch. The processor also processes the instructions to generate a tentative patch by dividing the tentative restored image. The processor further processes the instructions to generate a restored image from the restoration patch selected based on a sum of the value indicating the similarity between the input patch and the blurred patch and a value indicating the similarity between the tentative patch and the restoration patch.

Abstract: The present invention relates to a histogram equalization apparatus using histogram compression, and the objective of the present invention is to provide an equalization apparatus which highly compresses a histogram of an input image having a brightness level with a high frequency and lowly compresses the histogram having a brightness level with relatively a lower frequency thereby maintaining the characteristics of the input image, while refraining excessive changes in brightness, and enhancing the contrast more effectively by controlling the strength of a compression ratio according to the characteristics of the input image.

Abstract: An imaging apparatus according to the present invention is an imaging apparatus performing live-view display when not performing the focus adjustment, and also when performing the focus adjustment, and includes: a focus adjustment brightness value calculation section comparing a first brightness value in the photometric area for the live-view display with a second brightness value in the photometric area for the focus adjustment, correcting the first brightness value according to a comparison result, and calculating a brightness value for obtaining the image data for the focus adjustment; an imaging section obtaining the image data by performing exposure using the brightness value calculated by the focus adjustment brightness value calculation section; a focus adjustment section performing the focus adjustment using the image data obtained by the imaging section, and a display section performing the live-view display using the image data obtained by the imaging section.

Abstract: A method of selecting image data representative of a subject from an image data set comprises determining regions of image data, wherein each region of image data consists of a respective plurality of connected voxels, and selecting at least one region as being representative of the subject based upon at least one of the size and shape of the region.

Abstract: To generate a color image exhibiting few blocked-up colors or little color saturation. It is provided a image processing apparatus for processing an original image that is picked up, comprising: an image input part for inputting N original images having different exposure levels, where N is an integer of two or more, which are obtained by picking up images of the same subject in one of a simultaneous manner and a time-series manner; and a composite processing part for generating M output images, where M is an integer of one or more and less than N, by composing the N original images. The composite processing part compares color component signals in each corresponding pixel position with each other between the N original images, and sets the color component signal that produces a higher chroma as a color component signal in each pixel position of the output image.

Abstract: An image reading device includes: a CCD for reading an image on a document to output an image signal; a light source for switchingly emitting visible light and non-visible light; and lighting control means for controlling lighting periods of the light source. The lighting control means is adapted to perform control such that a first light source lighting period for applying non-visible light is longer than a second light source lighting period for applying visible light. The image reading device also includes splitting means for splitting the image signals outputted from the CCD into an image signal upon application of visible light and an image signal upon application of non-visible light.

Abstract: Depth maps are generated from two or more of images captured with a conventional digital camera from the same viewpoint using different configuration settings, which may be arbitrarily selected for each image. The configuration settings may include aperture and focus settings and/or other configuration settings capable of introducing blur into an image. The depth of a selected image patch is evaluated over a set of discrete depth hypotheses using a depth likelihood function modeled to analyze corresponding images patches convolved with blur kernels using a flat prior in the frequency domain. In this way, the depth likelihood function may be evaluated without first reconstructing an all-in-focus image. Blur kernels used in the depth likelihood function and are identified from a mapping of depths and configuration settings to the blur kernels. This mapping is determined from calibration data for the digital camera used to capture the two or more images.

Abstract: An apparatus generates an image coding signal comprising for each image a first pixelized picture and a second pixelized picture having a luminance component and a chroma component. The apparatus comprises a first picture processor (203, 211) which includes image encoding data for an encoded first image in the first pixelized picture. A second picture processor (205, 207, 209, 211) includes dynamic range extension data in the second pixelized picture. The dynamic range extension data may be dynamic range extension data included in a chroma component of the second pixelized picture for generating an increased dynamic range image on the basis of the encoded first image. The compensation data may e.g. be compensation data for correcting another LDR-to-HDR transform, e.g. a prefixed global gamma transformation.

Abstract: To make available a HDR image encoding mechanism with strongly improved usability, we describe an image encoding unit (301) arranged to encode a high dynamic range image (IM_HDR-in) comprising: —an LDR selector (311) for identifying a low dynamic range of luminances (R_Norml_LDR) or corresponding range of luma code values (R_LDR) within the total range of luminances (Range_HDR) covered by the high dynamic range image; —a HDR selector for selecting at least one complementary range (R_above) within the total range of luminances (Range_HDR), comprising mostly luminances not covered by the low dynamic range of luminances (R_Norml_LDR); —a code mapping unit (315) arranged to encode in a first image (Im_1*), having a luma component comprising N bit code words, pixel luminances of the high dynamic range image (IM_HDR-in) falling within the low dynamic range of luminances (R_Norml_LDR) to code values (Y_out) according to a first mapping (CMAP_L), and pixel luminances of the high dynamic range image (IM_HDR-in) fallin

Abstract: Described is system for image de-hazing for real-time video processing. A video comprising image frames is received as input. In determining an atmospheric veil value to use, the system leverages temporal correlations or specific scene constraints to determine whether to use a new atmospheric veil value or a previously determined atmospheric veil value. A global atmospheric light value is estimated as an average of a set of the brightest pixels in an upper region of an image frame. A de-hazed image is generated from the current image frame using either the previously determined atmospheric veil value or the new atmospheric veil value and the global atmospheric light value.

Abstract: A video display control device includes a video signal processing section that corrects a video signal and outputs a video signal after correction to a display, and a backlight controlling section that controls a light emission amount of a backlight. A control data generating section allocates to a low gradation region of the video signal a high gradation region dynamic range of the video signal in which a video signal corresponding to a black band region is excluded. The backlight controlling section controls a light emission luminance of the backlight so as to cancel out an increase or a decrease in the mean luminance of the video displayed on a screen.

Abstract: Techniques are described for compensating for distortion effects caused by projecting images to a surface that is non-perpendicular to a raster-scanning laser projector. Pixel size is modulated such that smaller pixels are projected to farther portions of the surface, and larger pixels are projected to nearer portions. Pixels within a raster scan line may have their lengths modulated through variation of a frequency of light source that generates the pixels, or through adjustment of a scan speed along the line. Pixel heights may be adjusted by modulating the distance between scan lines. Scan speed and distance between scan lines may be modified by controlling micromirrors incorporated into the laser projector for directing the light projection.

Abstract: In one example embodiment, a method of operating an image data processing circuit which controls an operation of an organic light-emitting diode (OLED) display includes transforming at least one first RGB value into at least one luminance value and at least one chroma value. The method further includes adjusting the at least one luminance value and the at least one chroma value based on at least one first control value. The method further includes generating at least one second RGB value based on the at least one adjusted luminance value and the at least one adjusted chroma value. The method further includes outputting the second RGB values to the OLED display.

Abstract: The present invention relates to an image information encoding and decoding method and a device for same. One embodiment of an image information encoding method according to the present invention, as an image information encoding method according to another embodiment of the present invention, includes the steps of: generating a restore block; applying a deblocking filter on the restore block; applying a Sample Adaptive Offset (SAO) on the restore block having the deblocking filter applied thereon; and transmitting information on the SAO application. During the applying of the SAO, the SAO is applied to chroma pixels, and during the transmitting of the information, in addition to information on whether the SAO is applied on the chroma pixels, at least one of area information, division information on the SAO coverage area, SAO type information, and SAO offset information is transmitted.

Abstract: Lens flare mitigation techniques determine which pixels in images of a sequence of images are likely to be pixels affected by lens flare. Once the lens flare areas of the images are determined, unwanted lens flare effects may be mitigated by various approaches, including reducing border artifacts along a seam between successive images, discarding entire images of the sequence that contain lens flare areas, and using tone-mapping to reduce the visibility of lens flare.

Abstract: Systems, apparatus, articles, and methods are described including operations to generate a weighted look-up-table based at least in part on individual pixel input values within an active block region and on a plurality of contrast compensation functions. A second level compensation may be performed for a center pixel block of the active region based at least in part on the weighted look-up-table.

Abstract: Technologies are generally described for methods and systems effective to reduce glare in augmented reality. In some examples, a method for producing a modified image of an object may include receiving first image data. The first image data may correspond to a first light reflected from the object through a clear filter. The method may further include receiving second image data. The second image data may correspond to a second light reflected from the object through a polarized filter. The method may further include combining the first image data and the second image data to generate modified image data. The method may further include producing the modified image of the object based on the modified image data. The method may further include rendering the modified image on an augmented reality display. The modified image may be different from the first image and different from the second image.

Abstract: A lighting correction filter for selectively correcting lighting in computer animation is disclosed. The lighting correction filter can select a computer-generated object having one or more lighting attributes. The selected object can be a portion of an object, an entire object, a portion of a computer-generated scene, or an entire scene. The filter can then set lighting correction values for the lighting attributes of the selected object. The lighting correction values can be color values, exposure values, or both. The filter can apply the lighting correction values to the selected object's lighting attributes to effect a lighting correction in the object prior to rendering.

Abstract: A method for applying a filter to data to improve data quality and/or reduce file size. In one example, a region of interest of an image is identified. A histogram is generated of pixel intensity values in the region of interest. The histogram is iteratively updated to focus (zoom) in on the highest peak in the histogram. A Gaussian curve is fitted to the updated histogram. A bilateral filter is applied to the images, where parameters of the bilateral filter are based on the parameters of the Gaussian curve.

Abstract: Methods and systems are provided to reduce noise in thermal images. In one example, a method includes receiving an image frame comprising a plurality of pixels arranged in a plurality of rows and columns. The pixels comprise thermal image data associated with a scene and noise introduced by an infrared imaging device. The image frame may be processed to determine a plurality of column correction terms, each associated with a corresponding one of the columns and determined based on relative relationships between the pixels of the corresponding column and the pixels of a neighborhood of columns. In another example, the image frame may be processed to determine a plurality of non-uniformity correction terms, each associated with a corresponding one of the pixels and determined based on relative relationships between the corresponding one of the pixels and associated neighborhood pixels within a selected distance.

Abstract: An electronic device is provided, which includes a light sensor, an algorithm engine, an adjustment engine, and a display. The light sensor detects an ambient brightness around the electronic device. The algorithm engine is coupled to the light sensor. The algorithm engine determines at least one adjustment function according to the ambient brightness. The adjustment engine is coupled to the algorithm engine. The adjustment engine adjusts the luminance component of each pixel of an image according to the at least one adjustment function to enhance the brightness and/or the contrast of the image. The display is coupled to the adjustment engine for displaying the adjusted image.

Abstract: An apparatus and a method for extracting a background luminance map of an image, and a de-shading apparatus and method. The apparatus includes: a luminance extracting unit, configured to extract luminance values everywhere in the image to obtain a luminance map; a separating unit, configured to separate background from foreground of the image based on the luminance map, to obtain an initial background luminance map; a top and bottom luminance obtaining unit, configured to extract top and bottom luminance of the initial background luminance map, and in the case of a part of the top and/or bottom luminance being missing, to supplement the missing part utilizing existing data of the top and/or bottom luminance to obtain complete top and bottom luminance; and an interpolation unit, configured to perform interpolation on the whole image based on the complete top and bottom luminance, to obtain the background luminance map of the image.

Abstract: Method for analyzing seismic data representing a subsurface region for presence of a hydrocarbon system or a particular play. Seismic attributes are computed, the attributes being selected to relate to the classical elements of a hydrocarbon system, namely reservoir, seal, trap, source, maturation, and migration. Preferably, the attributes are computed along structural fabrics (1) of the subsurface region, and are smoothed over at least tens or hundreds of data voxels. The resulting geologic attributes (2) are used to analyze the data for elements of the hydrocarbon system and/or recognition of specific plays, and for ranking and annotating partitioned regions (3) of the data volume based on size, quality, and confidence in the prospectivity prediction (5). A catalog (8) of hydrocarbon trap configurations may be created and used to identify potential presence of hydrocarbon traps and/or aid in scoring (4) and ranking partitioned regions as hydrocarbon prospects.

Abstract: An imaging apparatus having a function of detecting a face from an image signal on which a focusing frame is superimposed is configured so that a face selected to be a main object can continue being selected to be a main object even if a focusing frame is displayed as superimposed on the face. A central processing unit moves a position of a focusing frame to be displayed by a display unit to a position corresponding to a detected object if a ratio of a size of the detected object to a size of the focusing frame displayed on the display unit is greater than or equal to a predetermined threshold, and does not move the position of the focusing frame to be displayed by the display unit to a position corresponding to the detected object if the ratio is less than the threshold.

Abstract: There is provided a method of processing a digital image including: (a) obtaining a plurality of images; (b) converting the plurality of images into histograms; (c) setting one of the plurality of images as a reference image and another of the plurality of images as a comparison target image; (d) adjusting a distribution of the histogram of the reference image to match a distribution of the histogram of the comparison target image to produce an adjusted reference image; (e) comparing a difference between the adjusted reference image and the comparison target image to produce a masking image; (f) applying the masking image to the comparison target image to produce an adjusted comparison target image; and (g) combining the reference image and the adjusted comparison target image to produce a high dynamic range (HDR) image. Accordingly, even if there is a complex motion on a subject, a clear image without an image overlap or a ghost effect may be obtained when producing the HDR image.

Abstract: A method for shadow detection in an image comprising multiple color channels is disclosed wherein said image is compared with a background image. Said image and said background image comprises the same multiple color channels, have an exposure of a common background and are divided into a plurality of corresponding evaluation areas. For each combination of two color channels, a shadow region is defined in the two-dimensional coordinate system spanned by the two color channels. For each image evaluation area to be evaluated and for each combination of two color channels, the method comprises checking if a difference value between a first value pair defining values of said two color channels in the image evaluation area and a second value pair defining the values of said two color channels in the corresponding background evaluation area falls within said shadow region in said coordinate system.