Showing papers on "Image conversion published in 2008"

Systems and methods for filling occluded information for 2-D to 3-D conversion

Abstract: The present invention is directed to systems and methods for processing 2-D to 3-D image conversion. The system and method includes erode filling when an object has been removed from an image. In one embodiment, a target binary t image mask of the removed object is used for comparison with a binary source mask of the image. In an iterative process, color differences between pixels in the target mask and pixels in the source mask are identified and the pixels in the target mask are changed working from the periphery of the target mask to the center of the mask. Color noise is eliminated in the filled region of the target mask and, if desired, random color noise is added to the filled target mask.

Hallucinating faces from thermal infrared images

Abstract: This paper addresses the face hallucination problem of converting thermal infrared face images into photo-realistic ones. It is a challenging task because the two modalities are of dramatical difference, which makes many developed linear models inapplicable. We propose a learning-based framework synthesizing the normal face from the infrared input. Compared to the previous work, we further exploit the local linearity in not only the image spatial domain but also the image manifolds. We have also developed a measurement of the variance between an input and its prediction, thus we can apply the Markov random field model to the predicted normal face to improve the hallucination result. Experimental results show the advantage of our algorithm over the existing methods. Our algorithm can be readily generalized to solve other multi-modal image conversion problems as well.

An improved contrast enhancing approach for color-to-grayscale mappings

Abstract: Despite the widespread availability of color sensors for image capture, the printing of documents and books are still primarily done in black-and-white for economic reasons. In this case, the included illustrations and photographs are printed in grayscale, with the potential loss of important information encoded in the chrominance channels of these images. We present an efficient contrast enhancement algorithm for color-to-grayscale image conversion that uses both luminance and chrominance information. Our algorithm is about three orders of magnitude faster than previous optimization-based methods, while providing some guarantees on important image properties. More specifically, our approach preserves gray values present in the color image, ensures global consistency, and locally enforces luminance consistency. Our algorithm is completely automatic, scales well with the number of pixels in the image, and can be efficiently implemented on modern GPUs. We also introduce an error metric for evaluating the quality of color-to-grayscale transformations.

Image composition device with image conversion function

Abstract: An image composition apparatus with an image converting function is provided to convert images so as for the image types of two image data to be identical, determine color by image frame represented by corresponding image data to which transparency is applied between the two image data, and compose the two image data while applying transparency to the image data, thereby reducing the number of accesses to a memory and an access time and reducing time required to convert and compose two images. A first image type converter(110) converts the image type of first input image data corresponding to a first image in response to a first control signal, or bypasses the first input image data to output first output image data. A second image type converter(120) converts the image type of second input image data corresponding to a second image in response to a second control signal, or bypasses the second input image data to output second output image data. A color determination unit(130) outputs actual transparency data included into the first input image data in response to a third control signal, or determines color by image frame of the first image based on the first output image data, and selects and outputs one of plural reference transparency data according to a determination result. A composition unit(140) adjusts the transparency of the first output image data on the basis of the actual transparency data or the selected reference transparency data, composes the first output image data and the second output image data, and outputs composition image data to an external device(200). The image type of the first output image data and the image type of the second output image data are identical. The composition unit has an image converting function serially operated as the first and second image type converters are operated.

Systems and methods for 2-d to 3-d conversion using depth access segments to define an object

Abstract: The present invention is directed to systems and methods for controlling 2-D to 3-D image conversion. The system and method includes receiving an image and masking the objects in the image using segmentation layers Each segmentation layer can have weighted values for static and dynamic features. Iterations are used to form the final image which, if desired, can be formed using less than all of the segmentation layers. A final iteration can be run with the weighted values equal for static and dynamic features.

Image processing apparatus, moving image reproducing apparatus, and processing method and program therefor

Abstract: An image processing apparatus includes moving image storage means for storing a taken moving image and conversion information storage means for storing, for each second taken image located after a first taken image, conversion information. The image processing apparatus further includes image holding means for holding a log image including each taken image located before the second taken image and feature quantity extraction means for extracting a feature quantity. The image processing apparatus also includes image conversion means for converting the second taken image, decision means for determining whether or not synthesis of the second taken image and the log image is necessary, and image synthesis means for, if the synthesis of the second taken image and the log image is determined necessary, synthesizing the converted second taken image with the log image.

Automatic Measurement and Recognition of Yarn Snarls by Digital Image and Signal Processing Methods

Abstract: In this paper, a computerized method has been proposed for automatic measurement and recognition of yarn wet snarls from an image of snarled yarn samples captured in a water bath. After image acquisition, image conversion and individual snarled sample extraction, the yarn profile function was extracted from the separated binary image. Fast Fourier Transform and Adaptive Orientated Orthogonal Projective Decomposition were then incorporated into a pattern recognition algorithm of yarn snarl features by treating the yarn profile function as a one-dimensional signal. In addition to the number of yarn snarl turns, the method was also accurate and efficient for the detection of yarn snarl height and width, which are unobtainable by the untwisting method. The effects of various factors on the yarn profile function were numerically examined, including distributions of yarn diameter and snarl, and the level of random noise.

Systems and methods for depth peeling using stereoscopic variables during the rendering of 2-d to 3-d images

Abstract: The present invention is directed to systems and methods for processing 2-D to 3-D image conversion. Rendering of left and right eye images is performed by order independent depth peeling. For each image that is created a number of scene traversals are performed that peel off each depth layer based on a previous traversals depth map. The peeled layers are then blended together and, if desired, unwanted jagged edges can be removed.

Systems and methods for allowing a user to dynamically manipulate stereoscopic parameters

Abstract: The present invention is directed to systems and methods for controlling 2 -D to 3-D image conversion.. In one embodiment, stereo visualization and rendering of the final image is performed by allowing a user to independently select inter-ocular and convergence distances on a frame by frame basis. The user can view the effect of each selected parameter on a real-time basis and may, if desired, use interpolation and select parameters only for key frames.

Systems and methods for 2-D to 3-D image conversion using mask to model, or model to mask, conversion

Abstract: The present invention is directed to systems and methods for controlling 2-D to 3-D image conversion. In one embodiment, a mask is generated from an object model of the image. The mask is then used to from a 2-D mesh which is then converted to a 3-D volume mesh. The 3-D volume mesh is then used to produce 3-D image conversion.

Systems and methods for filling light in frames during 2-d to 3-d image conversion

Abstract: The present invention is directed to systems and methods for processing 2-D to 3-D image conversion. The systems and methods fill in light among image frames when object have been removed or otherwise changed. In one embodiment, light is treated as an object and can be removed during image processing. The light is added back during the rendering process using the created light object. In other embodiments, light from other frames is filled in using weighted averaging of the light depending upon temporal distance from a particular frame and a base frame.

Systems and methods for treating occlusions in 2-d to 3-d image conversion

Abstract: The present invention is directed to systems and methods for processing 2 -D to 3-D images. The system and method includes a procedure for optimizing occlusion and/or texturing by creating tolerances in which such texturing need not occur.

System and method for using feature tracking techniques for the generation of masks in the conversion of two-dimensional images to three-dimensional images

Abstract: The present invention is directed to systems and methods for controlling 2-D to 3-D image conversion and/or generation. The methods and systems use auto-fitting techniques to create a mask based upon tracking features from frame to frame. When features are determined to be missing they are added prior to auto-fitting the mask.

Image data creation device, and image data reproduction device

Abstract: PROBLEM TO BE SOLVED: To provide an image data creation device in which image data for three-dimensional (3D) display have versatility, an image of an arbitrary viewpoint can be efficiently selected and in addition, when encoding an image adjacently coupling a plurality of images, the image can be efficiently encoded, and to provide an image data reproduction device for reproducing the data. SOLUTION: An image signal consisting of continuous frames is inputted to an image creation device one by one frame. A control section 102 specifies presence/absence of reduction, presence/absence of connection, and 2D selection. An image conversion section 101 creates image data of the format specified by the presence/absence of reduction and presence/absence of connection. A 3D information creation section 103 formats the presence/absence of reduction, presence/absence of connection, and 2D selection and creates 3D information required for displaying the image as a 3-dimensional image. A multiplexing section 104 converts the image data and the 3D information into a predetermined format and outputs it outside. COPYRIGHT: (C)2008,JPO&INPIT

Image processing apparatus, image processing method and computer program

Abstract: An image processing apparatus includes an image conversion section that receives an input of a face image to be identified, executes an image conversion on the input face image, and performs a normalization processing into an image. The image conversion section obtains a face image from a first memory storing the face image to be normalization processed, performs the normalization processing by an image conversion and stores the face image after the normalization processing into a second memory. The image processing apparatus includes a calculation section that calculates a conversion parameter for calculating a corresponding point in the first memory to each pixel position in the second memory. The conversion parameter defines one of an image contraction processing, an image rotation processing, or an image translation processing to be performed when the face image stored in the first memory is converted into the face image stored in the second memory.

Image processing device, dynamic image reproduction device, and processing method and program used in the devices

Abstract: To easily understand the contents of a moving image taken by an image taking apparatus. An image conversion block 150 converts a taken image on the basis of conversion information. A transparency conversion block 160 converts the transparency in the converted taken image. A image synthesis block 170 synthesizes the taken image with the transparency converted with a log image and holds a resultant new log image in an image memory 180. An index image extraction block 190 extracts a new index image from among the converted taken images on the basis of the coordinate position and size of an index image in an image taking space. A selection block 270 selects an index image on the basis of the position of a selected representative image when the position of a panorama image displayed on a display block 292 is selected. A display control block 291 displays a panorama image on the display block 292 and displays the selected index image, overlapped on the panorama image.

Image processing apparatus, image processing method and computer program

Abstract: PROBLEM TO BE SOLVED: To provide an image processing apparatus, an image processing method and a computer program that display on a display device an image of the surroundings of a vehicle captured by imaging devices mounted on the vehicle. SOLUTION: A vehicle state determination part 11 determines a vehicle state according to detection signals from various sensors 80. A camera boundary control part 12 determines a boundary position angle to be used when an image processing part 6 combines four two-dimensional image data to generate one three-dimensional image data, according to the vehicle state determined by the vehicle state determination part 11. An image viewpoint control part 13 determines a viewpoint position angle to be used when the image processing part 6 generates projection image data from the three-dimensional image data, according to the vehicle state determined by the vehicle state determination part 11. The image processing part 6 generates projection image data from image data captured by cameras 71-74 by means of the determined boundary position angle and viewpoint position angle and of three-dimensional image conversion data 4a, and outputs it to a display device 90. COPYRIGHT: (C)2010,JPO&INPIT

Device of detecting position of polyhedral body and method for detection

Abstract: PROBLEM TO BE SOLVED: To provide a device of detecting a position of a three-dimensional object capable of precisely recognizing a position and an attitude of an object even when the object has a glossy face, a face without a pattern or a black face, and to provide a method for detection. SOLUTION: Model images of respective faces forming an object to be a measuring target are stored in a model image storage section. An image capturing device captures images of the measuring target as multi-viewpoint images. The imaged three-dimensional information is stored in an image information storage section. A plane face extracting section extracts a plane face from the stored three-dimensional image information. A normal line image conversion section converts the extracted plane face into a normal line image by using a first conversion matrix. A model correspondence image conversion section performs pattern matching between the converted normal line image and each of model images and determines a correspondence model image so as to convert the determined model image into a model correspondence image on the basis of a second conversion matrix. The position and the attitude of the target are recognized on the basis of the operated first and second conversion matrixes. COPYRIGHT: (C)2010,JPO&INPIT

Systems and methods for image capture, generation, and presentation

Abstract: A system for displaying an anamorphic image on a viewing surface comprises a screen having a viewing surface and an image source configured to display the anamorphic image on the viewing surface such that an image viewed on the viewing surface appears undistorted from a viewing point. In addition, the system may also include a reflective lens having a convex exterior surface and a refractive lens having a plurality of surfaces to redirect light toward an image capture device. Further, the system may include an image conversion module for converting a non-anamorphic image into the anamorphic image suitable for displaying on the viewing surface and a selected portion of the anamorphic image into at least one non-anamorphic image.

Operation supporting system, image processing device, and deviation detecting method

Abstract: PROBLEM TO BE SOLVED: To provide an operation supporting system, an image processing device, and a deviation detecting method which more accurately determine whether deviation occurs in a position or a direction of a vehicle mounted camera or not in the operation supporting system which composes projected images which are projected on a plane of photographed images using a plurality of vehicle mounted cameras SOLUTION: The operation supporting system of the invention is provided with a first vehicle mounted camera which acquires a first image, a second vehicle mounted camera which acquires a second image, and an image conversion unit which converts the first image and the second image to a first projection image and a second projection image projected on the plane It is also provided with a solid object determination unit which determines whether there is a solid object in an overlapping region or not in a state that directions of the first vehicle mounted camera and the second vehicle mounted camera are different, and they have the overlapping region which overlaps mutually; a difference calculating unit which calculates the difference between an image in the overlapping region in the first projection image and an image in the overlapping region in the second projection image in a case that there is no solid state object; and a detection unit which detects that deviation occurs in the vehicle mounted cameras in a case that the difference is more than a threshold value COPYRIGHT: (C)2008,JPO&INPIT

Radiation image conversion panel, its manufacturing method, and x-ray radiographic system

Abstract: Disclosed are a radiation image conversion panel, which provides high luminance, an image without white or black defects, an image free from cracks and an image with reduced unevenness, and its manufacturing method. Also disclosed is an X-ray radiographic system employing the radiation image conversion panel. The radiation image conversion panel of the invention comprises a substrate and provided thereon, a reflection layer, a phosphor layer and a protective layer in that order, wherein the phosphor layer is composed of a phosphor crystal in the form of column, and the reflection layer is formed by vapor phase deposition of two or more kinds of metals.

Distance image processing device and method, distance image regenerating device and method, and program

Abstract: PROBLEM TO BE SOLVED: To efficiently reduce the amount of data of an image file of a distance image. SOLUTION: Imaging sections 21A, 21B acquire standard images and reference images for calculating distance values including depth information and positional information representing a three-dimensional shape of a subject, by imaging the subject. A distance image formation section 31 calculates distance values from the standard images and the reference images. A distance image conversion section 32 performs quantization concerning depth information within a predetermined range by quantization numbers larger than those for depth information outside the predetermined range, a distance image encoding section 33 encodes a distance image having distance values including quantized positional information as the pixel value of each pixel, and a compression/extension processing section 24 creates an image file of the encoded distance image. COPYRIGHT: (C)2009,JPO&INPIT

Methods of bitonal image conversion for modern and classic documents

Abstract: Bitonal conversion is a basic preprocessing step in Automatic Content Analysis, a very active research area in the past years. The information retrieval process is performed usually on black and white documents in order to increase efficiency and use simplified investigation techniques. This paper presents a number of new modern conversion algorithms which are aimed at becoming an alternative to current approaches used in the industry. The proposed methods are suitable for both scanned images and documents in electronic format. Firstly, an algorithm consisting of a contrast enhancement step, followed by a conversion based on adaptive levelling of the document is presented. Then a new multi-threshold technique is suggested as a solution for noise interferences, a common feature of scanned books and newspapers. Finally, three more approaches adapted to the particular properties of electronic documents are introduced. Experimental results are given in order to verify the effectiveness of the proposed algorithms.

Display system for vehicle and navigation system

Abstract: PROBLEM TO BE SOLVED: To provide a current position display system for displaying one's own vehicle and surrounding situations in an easy-to-understand way. SOLUTION: The current position display system is for sending the original image of a predetermined imaging range to a vehicle from a road side device having an imaging means. The vehicle has a position detecting means 14a for detecting the position of the vehicle; a road map storage means 15 for storing a road map; a road map display means 14d for extracting the road map including the position from the map storage means and displaying the map on a display device, along with a mark indicating the position of the vehicle; an image conversion means 14b for converting the original image into a plane image with a viewpoint approximately perpendicular to a road surface; and an image superposing means 14c for superposing the plane image on the imaging range on the road map and superposing the mark on the vehicle imaged in the plane image. COPYRIGHT: (C)2008,JPO&INPIT

Object detection device using image processing

Abstract: PROBLEM TO BE SOLVED: To detect an object surely even in the case of a photographed image wherein the road surface is tilted caused by tilt of the road surface or rolling movement of a camera by traveling of a vehicle. SOLUTION: This object detection device is equipped with a parallax image generation part for generating a parallax image from each image by two cameras arranged side by side in parallel with the ground; a parallax image conversion part for converting the parallax image into a virtual parallax image from a viewpoint installed virtually so that the two cameras are in contact with the ground; a correction information calculation part for approximating by a straight line, a part where the density of values showing a stereo parallax in an image acquired by projecting the virtual parallax image onto a U-V plane is higher than a threshold, calculating a roll angle to the ground of the cameras from tilt of a straight line, and correcting the parallax image by utilizing the roll angle; a road surface estimation part for estimating the road surface in the corrected parallax image as a straight line from an image acquired by projecting the corrected parallax image onto a V-d plane; and an object detection part for detecting an object in contact with the road surface in the corrected parallax image, existing over the road surface, based on the stereo parallax of each pixel in the corrected parallax image. COPYRIGHT: (C)2009,JPO&INPIT

Driving support device and driving support method for vehicle

Abstract: PROBLEM TO BE SOLVED: To visually and surely recognize an object as obstacle SOLUTION: This driving support device is provided with an irradiation device 12 for defining the road surface as an imaging area F1 as a reference, in a state where an any object as an obstacle does not exist within the field angle of an imaging device 11 and for emitting irradiation rays of light, by defining a location beyond the road surface as the reference as an irradiation location IR; an image processor 13 for performing the image conversion processing of an image photographed by the imaging device 11 for generating a visual point conversion image photographed from a virtual visual point that is different from that of the imaging device 11; and an image display device 14 for displaying the visual point converted image COPYRIGHT: (C)2008,JPO&INPIT

Video monitoring device

Abstract: PROBLEM TO BE SOLVED: To provide a video monitoring device which detects monitoring target regions with perspective as two images having a duplicate region and dissolves the perspective on a synthetic screen while creating a composite image which can display two of the image information thereon without omission and displaying the composite image on a display partSOLUTION: A video monitoring device 100 is provided with an image processing portion 4 consisting of: a depth side image conversion portion 4b to determine the arrangement of a depth side image, taken by a monitoring camera 3b and being captured and reduced, on a composite image; a near side image conversion portion 4a to capture a near side image taken by the monitoring camera 3a, divide the image into areas which are an overlapping part where the near side image overlaps with the depth side image and a non-overlapping part where the near side image does not overlap with the depth side image, enlarge the overlapping part, and reduce the non-overlapping part; and an image composition processing portion 4c to obtain a composite image by capturing the converted near side and depth side images and disposing the images in an overlapped manner in which a size and a position of a subject are conformed

Image output apparatus, image output method and image output program product

Abstract: An image output apparatus is provided with an image conversion unit for converting image data into an output image of intermediate gradation using a line screen for forming pixel points in stripes, an element angle storing unit for storing the angle information of line segments of the image data, a jaggy judging unit for judging whether or not jaggies will appear on the outline of the output image based on the angle information of the line segments stored in the element angle storing unit, and a screen angle setting unit for substantially changing the screen angle of the line screen if jaggies are judged to appear by the jaggy judging unit.

Image conversion apparatus, image conversion program storage medium, and image display system

Abstract: The image conversion apparatus includes: an image data acquiring section that acquires print image data for a print system, the print image data indicating a print image to be printed by the print system; a data conversion section that converts the print image data to display image data for a display system such that the print image is reproduced by the display system; a degree specification accepting section that accepts a specification operation that specifies a degree of visible color difference between the print image and a reproduced image, the degree of difference generated by a comparison environment that compares colors therebetween; and a conversion adjusting section that adjusts data conversion by the data conversion section based on a degree specified by the specification operation so that the color of the print image and the color of the reproduced image are seen as an identical color.