Abstract: An image-based georeferencing system comprises an image receiver, an image identification processor, a reference feature determiner, and a feature locator. The image receiver is configured for receiving a first image for use in georeferencing. The image comprises digital image information. The system includes a communicative coupling to a georeferenced images database of images. The image identification processor is configured for identifying a second image from the georeferenced images database that correlates to the first image. The system includes a communicative coupling to a geographic location information system. The reference feature determiner is configured for determining a reference feature common to both the second image and the first image. The feature locator is configured for accessing the geographic information system to identify and obtain geographic location information related to the common reference feature.

Abstract: Cascaded object detection techniques are described. In one or more implementations, cascaded coarse-to-dense object detection techniques are utilized to detect objects in images. In a first stage, coarse features are extracted from an image, and non-object regions are rejected. Then, in one or more subsequent stages, dense features are extracted from the remaining non-rejected regions of the image to detect one or more objects in the image.

Abstract: The present disclosure provides a method and system for realizing interaction in augmented reality. The method includes: collecting a frame image and uploads the frame image; recognizing a template image that matches the frame image and returning the template image; detecting a marker area of the frame image according to the template image; and superposing media data corresponding to the template image on the marker area and displaying the superposed image.

Abstract: An image is obtained. At least one local region is set in the image. Feature patterns are extracted from the local region, and, out of a plurality of bins corresponding to a plurality of patterns which can form the feature patterns, bins that have been determined in accordance with a type of the local region are set as histogram bins used in generating a histogram. A histogram is generated corresponding to the extracted feature patterns using the set histogram bins, and image recognition is performed using the generated histogram.

Abstract: An image processing and recording system and an image processing and recording method thereof are provided. An image processing and recording system includes a recording module, an access module, and an identification module. The recording module stores an image which includes N image blocks, and the N image blocks compose M image tiles. The identification module performs an image recognition procedure to identify a predetermined feature of the N image blocks picked up by the access module and generates N identification results. Each result includes an address of the tile in the image corresponding to the Kth image block, a corresponding address of the Kth image block in the image tile and whether the Kth image block has the predetermined feature. Thus, the access module can pick up the image blocks having the predetermine feature to perform a next image recognition procedure.

Abstract: Provided are an age estimation apparatus, an age estimation method, and an age estimation program capable of obtaining a recognition result closely matching the result perceived by human. An age estimation apparatus 10 for estimating an age of a person on image data includes a dimension compressor 11 for applying dimension compression to the image data to output low dimensional data; and an identification device 12 for estimating an age of a person on the basis of a learning result using a feature amount contained in the low dimensional data, wherein a parameter used for the dimension compression by the dimension compressor 11 and the feature amount used for age estimation by the identification device 12 are set on the basis of a result of an evaluation of a generalization capability using a weighting function that shows a degree of seriousness of an age estimation error for every age, and learning of the identification device 12 is performed on the basis of the weighting function.

Abstract: An image processing device includes an image-modification processing unit and an adjustment unit. The image-modification processing unit executes first image-modification processing wherein pixels are inserted to or deleted from a subject image in a first direction or pixels in the subject image are shifted in the first direction and second image modification processing wherein pixels in the subject image are shifted in a second direction. The adjustment unit adjusts a position of a shift-border along which the pixels are shifted in the second image-modification processing on the basis of a position of each step in an image caused in the first image-modification processing.

Abstract: Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object derived from a video input, wherein each version has a different resolution of said image of said object; computing an appearance score at each of a plurality of regions on the lowest resolution version of said plurality of versions of said image for at least one attribute for said object, wherein said appearance score denotes a probability of the at least one attribute appearing in the region; determining a configuration of the at least one attribute in the lowest resolution version based on at least the appearance score in each of the plurality of regions in the lowest resolution version; and displaying said configuration.

Abstract: A system for automatically extracting or isolating structures or areas of interest (e.g., built-up structures such as buildings, houses, shelters, tents; agricultural areas; etc.) from HR/VHR overhead imagery data by way of making as little as a single pass through a hierarchical data structure of input image components (where pixels are grouped into components based on any appropriate definition or measure of dissimilarity between adjacent pixels of the input image) to identify candidate components (e.g., possible structures of interest) free of necessarily having to re-iterate the same operator configured with different threshold parameters for a plurality of values.

Abstract: The present invention provides a method and apparatus for selectively enhancing regions in an image. In one embodiment, a digital image is read from an image source and is converted into a desired image model. One or more regions in the image having intensity values of pixels falling outside a pre-determined optimal intensity range are determined. The one or more regions in the image are then enhanced using a modeled light source of an optimal intensity such that the intensity value of pixels corresponding to the one or more regions in the image fall within the pre-determined optimal intensity range.

Abstract: Disclosed are an apparatus and method for extracting a skin area to block a harmful image. The apparatus includes an image extraction unit, a skin sample area extraction unit, a background sample area extraction unit, a probability density function computation unit, and a skin area extraction unit. The image extraction unit extracts an image from image media. The skin sample area extraction unit extracts a skin sample area of the image based on prior information. The background sample area extraction unit extracts a background sample area of the image based on the prior information. The probability density function computation unit calculates the probability density functions of the skin sample area and the background sample area. The skin area extraction unit extracts a skin area from the image based on the probability density function of the skin sample area and the probability density function of the background sample area.

Abstract: A method of generating a saliency image, which includes: converting an input image into an input image of the first size and an input image of the second size; applying a saliency extraction scheme to the input image of the first size to generate a first saliency image; converting the first saliency image to the second size; extracting an area that satisfies a first condition from the converted first saliency image; determining an area of the input image of the second size that corresponds to the extracted area; and generating a second saliency image by multiplying an image generated by applying the saliency extraction scheme to the determined area, and the converted first saliency image.

Abstract: A computing system for automatically identifying individual regions in a digital image that include a human face, forming combined padded regions and automatically evaluating each of the regions including calculating a fitness score for each of the combined padded regions and ignoring at least one of the combined padded regions whose fitness score is below a known threshold.

Abstract: What is disclosed is a system and method which reconstructs an N-pixel image of a scene such that Q pixel locations associated with identified regions of interest in a scene have a higher image quality when rendered relative to other pixels in the image. Acquisition and adaptive-quality compression are performed simultaneously by semi-synchronously or asynchronously temporally modulating an ordered set of sampling functions used to spatially modulate a pattern of light. The teachings hereof improve compression efficiency of a compressed sensing framework while improving encoding efficiency with respect to traditional compressed sensing techniques.

Abstract: A computer implemented method for modifying a digital image comprises padding two or more face regions in the image and digitally defining at least one combined padded region that includes the two or more face regions. At least one border of the combined padded region is collinear with a border of one of the individual regions. Each of the borders of the at least one combined padded region is selected so as to be collinear with at least one border of one of the individual padded regions.

Abstract: In techniques for image foreground detection, a foreground detection module is implemented to generate varying levels of saliency thresholds from a saliency map of an image that includes foreground regions. The saliency thresholds can be generated based on an adaptive thresholding technique applied to the saliency map of the image and/or based on multi-level segmentation of the saliency map. The foreground detection module applies one or more constraints that distinguish the foreground regions in the image, and detects the foreground regions of the image based on the saliency thresholds and the constraints. Additionally, different ones of the constraints can be applied to detect different ones of the foreground regions, as well as to detect multi-level foreground regions based on the saliency thresholds and the constraints.

Abstract: A video object retrieval method is provided. The method includes dividing an input video into a number of video shots and detecting target-class object occurrences and related-class object occurrences in each video shot. The method also includes pre-processing object bounding box images and performing automatic object extraction. Further, the method includes performing object-level feature extraction and integration and generating visual search results based on similarity scores.

Abstract: A method and system for extracting a visual descriptor using a feature selection are provided. The system includes an image input unit configured to receive an image, a candidate feature point group detecting unit configured to detect a point having a local maximum or minimum of local region filtering in scale-space images as being included in a candidate feature point group, a feature point selecting unit configured to calculate an importance for each candidate feature point, depending on its characteristics, select the candidate feature point as a feature point when its importance is greater than the predetermined threshold value, a dominant orientation calculating unit configured to calculate a dominant orientation of the selected feature point and a visual descriptor extracting unit configured to extract a patch for each feature point, according to its scale, location and dominant orientation, and extract a visual descriptor from the patch.

Abstract: Implementations relate to an image cache used for replacing portions of images. In some implementations, a method includes examining a received image and detecting a subject depicted in a subject portion of the received image. The method determines a likelihood that the subject portion will be used as a replacement to be inserted in place of one or more corresponding subject portions in future images examined at a later time. The subject portion, or a reference thereto, is stored in an image cache in response to the determined likelihood being greater than a predetermined threshold. The image cache is available to be searched for the subject portion and other portions of images to replace corresponding portions of future images.

Abstract: In techniques for iterative saliency map estimation, a salient regions module applies a saliency estimation technique to compute a saliency map of an image that includes image regions. A salient image region of the image is determined from the saliency map, and an image region that corresponds to the salient image region is removed from the image. The salient regions module then iteratively determines subsequent salient image regions of the image utilizing the saliency estimation technique to recompute the saliency map of the image with the image region removed, and removes the image regions that correspond to the subsequent salient image regions from the image. The salient image regions of the image are iteratively determined until no salient image regions are detected in the image, and a salient features map is generated that includes each of the salient image regions determined iteratively and combined to generate the final saliency map.

Abstract: Systems and methods for improving visual object recognition by analyzing query images are disclosed. In one example, a visual object recognition module may determine query images matching objects of a training corpus utilized by the module. Matched query images may be added to the training corpus as training images of a matched object to expand the recognition of the object by the module. In another example, relevant candidate image corpora from a pool of image data may be automatically selected by matching the candidate image corpora against user query images. Selected image corpora may be added to a training corpus to improve recognition coverage. In yet another example, objects unknown to a visual object recognition module may be discovered by clustering query images. Clusters of similar query images may be annotated and added into a training corpus to improve recognition coverage.

Abstract: Respective models of visual weight in images are determined. An image query is generated from a determined visual weight distribution. At least one of the images is retrieved from a database based on comparisons of the image query with respective ones of the visual weight models.

Abstract: An image processing device configured to detect a salient region from an image has a pixel small-region image generating unit that generates a pixel small-region image using, as a unit, a pixel small region made of pixels adjacent to one another and whose luminance values or chromaticity are similar, from the image, a prior probability calculator that calculates prior probability of likelihood of the salient region for each of the pixels of the image, a region generating unit that generates a salient-region-containing region having high possibility of containing a salient region on the basis of a corner point extracted from the image, and a likelihood calculator.

Abstract: A hardware coprocessor architecture calculates the Difference-of-Gaussian (DoG) pyramid of an input image and extracts from this the interest points to be used in several image detection algorithms. Advantages of the architecture include the possibility to process the image by stripes, namely by blocks having one dimension coincident with the input image width, in the absence of an input frame buffer and the possibility to avoid RAM memory. The coprocessor is suitable to be tightly coupled with raw image sources like sensors.

Abstract: A document management apparatus includes a reception unit, an operation information extraction unit, a memory, an executability determination unit, and an operation execution unit. The reception unit receives an operation request for an electronic document from an operator. The operation information extraction unit extracts operation information related to the operation request. The memory stores operation history information which is an accumulation of previous operation information which is operation information related to previous operation requests previously made for electronic documents. The executability determination unit reads the operation history information from the memory to determine whether or not an operation pertaining to the operation request is executable on the basis of the operation information and the operation history information.

Abstract: A computer-implemented method and apparatus are described for automatically selecting a region in a blurred image for blur kernel estimation. The method may include accessing a blurred image and defining a size for each of a plurality of regions in the image. Thereafter, metrics for at least two of the plurality of regions are determined, wherein the metrics are based on a number of edge orientations within each region. A region is selected from the plurality of regions based on the determined metrics, and a blur kernel for deblurring the blurred image is then estimated for the selected region. The blurred image is then deblurred using the blur kernel.

Abstract: A computer-implemented method and apparatus are described for deblurring an image. The method may include accessing the image that has at least one blurred region and, automatically, without user input, determining a first value for a first size for a blur kernel for the at least one blurred region. Thereafter, automatically, without user input, a second value for a second size for the blur kernel is determined for the at least one blurred region. A suggested size for the blur kernel is then determined based on the first value and the second value.

Abstract: The current application is directed to a method and system for automatically determining the sense orientation of regions of scanned-document images that include symbols and characters of languages that are not written as simple sequential strings of alphabetic characters. In one implementation, the sense-orientation method and system to which the current application is directed employs a relatively small set of orientation-marker characters that occur frequently in printed text and that lack rotational symmetry.

Abstract: An automated and extensible system for analysis and retrieval of images based on region-of-interest (ROI) analysis of one or more true objects depicted by an image is provided. The system uses a database that is a relational or analytical database containing searchable vectors that represent the images stored in a repository. Entries in the database are created by an image locator and ROI classifier working together to locate images within the repository and extract relevant information to be stored in the ROI database. The ROI classifier analyzes objects in an image to arrive at actual features of the true object. Graphical searches are performed by the collaborative workings of an image retrieval module, an image search requestor and an ROI query module. The image search requestor is an abstraction layer that translates user or agent search requests into the language understood by the ROI query.

Abstract: Feature extraction, coding and pooling, are important components on many contemporary object recognition paradigms. This method explores pooling techniques that encode the second-order statistics of local descriptors inside a region. To achieve this effect, it introduces multiplicative second-order analogues of average and max pooling that together with appropriate non-linearities that lead to exceptional performance on free-form region recognition, without any type of feature coding. Instead of coding, it was found that enriching local descriptors with additional image information leads to large performance gains, especially in conjunction with the proposed pooling methodology. Thus, second-order pooling over free-form regions produces results superior to those of the winning systems in the Pascal VOC 2011 semantic segmentation challenge, with models that are 20,000 times faster.

Abstract: An aerial image is received. A portion of the aerial image is identified that represents an area of interest that includes a vehicle. The portion of the aerial image is analyzed to generate an identification of one or more objects in the area of interest related to a route of the vehicle.

Abstract: A surveillance camera obscures human features when people are present to preserve privacy.

Abstract: Devices, systems, apparatuses, methods, and other embodiments associated with bit resolution enhancement are described. In one embodiment, an apparatus includes logic configured to produce a high-resolution pixel from a low-resolution pixel. The apparatus includes logic configured to classify the high-resolution pixel as being in a smooth region of an image based on at least one of a gradient value and a variance value associated with the low-resolution pixel. The apparatus includes logic configured to selectively re-classify the high-resolution pixel as not being in the smooth region of the image based on a set of neighboring high-resolution pixels associated with high-resolution pixel. The apparatus includes logic configured to selectively filter the high-resolution pixel based on whether the high-resolution pixel remains classified as being in the smooth region of the image.

Abstract: A computer implemented method for modifying a digital image comprising identifying two or more individual regions in the digital image that each include a human face, and digitally defining at least one combined region that includes the two or more individual regions wherein at least one border of the at least one combined region is collinear with a border of one of the individual regions.

Abstract: An information processing apparatus sets a plurality of reference locations of data in information as one reference location pattern and acquires a feature amount obtained from a value of data of one of the plurality of pieces of reference information in one reference location pattern for each of a plurality of reference location patterns and the plurality of pieces of reference information. The apparatus extracts data included in the input information according to each of the plurality of reference location patterns, selects the reference location pattern for classification of the input information from the plurality of reference location patterns based on a value of data included in the extracted input information, and executes classification of the input information by using the feature amount in the selected reference location pattern and data included in the input information at a reference location indicated by the reference location pattern.

Abstract: Machines, systems and methods for character recognition disambiguation are provided. The method comprises selecting a first set of characters that match a first visual profile based on results of a character recognition process applied to target content; selecting a subset of the first set based on criteria associated with at least one of confidence level with which characters grouped in the subset are recognized or fragmentation associated with the characters grouped in the subset; and disambiguating recognition results for the characters grouped in the subset by displaying the characters along with context information, wherein reviewing two or more of the characters on a display screen along with context information associated with said two or more characters allows a human operator to select one or more suspect characters from among the two or more characters.

Abstract: A system of stereo imagers, including image processing units and methods of blurring an image, is presented. The image is received from an image sensor. For each pixel of the image, a depth filter component is determined based on a focal area of the image and a depth map associated with the image. For each pixel of the image, a trilateral filter is generated that includes a spatial filter component, a range filter component and the depth filter component. The respective trilateral filter is applied to corresponding pixels of the image to blur the image outside of the focal area. A refocus area or position may be determined by imaging geometry or may be selected manually via a user interface.

Abstract: An image processing apparatus includes a smoothing processing unit which performs smoothing processing, a thinning processing unit which performs thinning processing, an edge direction determination unit which determines an edge direction with respect to each pixel of the image data and a blending processing unit which decides a pixel value of each pixel of when the thinning processing and the smoothing processing are realized at same time. In the image processing apparatus, the blending processing unit decides a pixel value of a target pixel of when the thinning processing and the smoothing processing are realized at the same time depending on a combination of whether the thinning processing is performed or not and whether the smoothing processing is performed or not on the target pixel.

Abstract: Provided is an image processing device for associating images with objects appearing in the images, while reducing burden on the user. The image processing device: stores, for each of events, a photographic attribute indicating a photographic condition predicted to be met with respect to an image photographed in the event; stores an object predicted to appear in an image photographed in the event; extracts from a collection of photographed images a photographic attribute that is common among a predetermined number of photographed images in the collection, based on pieces of photography-related information of the respective photographed images; specifies an object stored for an event corresponding to the extracted photographic attribute; and conducts a process on the collection of photographed images to associate each photographed image containing the specified object with the object.

Abstract: An imaging system includes an identification module, a determination module, and a display module. The identification module is configured to identify one or more first scanning parameters and one or more first display parameters corresponding to a first image, and to identify one or more second scanning parameters corresponding to scanning information acquired during a second scan. The determination module is configured to determine, based on the one or more first scanning parameters and the one or more second scanning parameters, one or more second display parameters so that the scanning information acquired during the second scan may be used to provide a second image appearing more similar to the first image. The display module is configured to use the one or more second display parameters to provide the second image configured to be displayed to a viewer.

Abstract: A method of creating a video sequence. The method comprises setting at least one repetitive reminder in a schedule managed by a handheld device having an image sensor, alarming a user according to the at least one repetitive reminder, capturing a sequence of images using the image sensor, automatically identifying a facial image depicting a face in a preset area in the sequence of images, automatically selecting the facial image, in response to the identification, and adding the facial image to a facial video sequence.

Abstract: Methods, systems, and computer program products for parsing objects in a video are provided herein. A method includes producing a plurality of versions of an image of an object, wherein each version has a different resolution of said image of said object, and computing an appearance score at each of a plurality of regions on the lowest resolution version for at least one attribute for said object. Such a method also includes analyzing one or more other versions to compute a resolution context score for each of the plurality of regions in the lowest resolution version, and determining a configuration of the at least one semantic attribute in the lowest resolution version based on the appearance score and the resolution context score.

Abstract: A dictionary data registration apparatus includes a dictionary configured to be registered a local feature amount for each region of an image with respect to each of a plurality of categories, an extraction unit configured to extract the local feature amount from a plurality of regions of an input image, a selection unit configured to select a plurality of the local feature amounts for each region according to a distribution of the local feature amounts extracted by the extraction unit from a plurality of regions of a plurality of pieces of input images which belongs to the category with respect to each of the plurality of categories, and a registration unit configured to register the selected plurality of local feature amounts on the dictionary as a local feature amount for each region with respect to the category.

Abstract: A method (100) and system (300) is described for processing video data comprising a plurality of images. The method (100) comprising obtaining (104, 106), for each of the plurality of images, a segmentation in a plurality of regions and a set of keypoints, and tracking (108) at least one region between a first image and a subsequent image resulting in a matched region in the subsequent image taking into account a matching between keypoints in the first image and the subsequent image. The latter results in accurate tracking of regions. Furthermore the method may optionally also perform label propagation taking into account keypoint tracking.

Abstract: Embodiments disclose systems and methods that aid in screening, diagnosis and/or monitoring of medical conditions. The systems and methods may allow, for example, for automated identification and localization of lesions and other anatomical structures from medical data obtained from medical imaging devices, computation of image-based biomarkers including quantification of dynamics of lesions, and/or integration with telemedicine services, programs, or software.

Abstract: One exemplary embodiment involves identifying feature matches between each of a plurality of object images and a test image, each feature matches between a feature of a respective object image and a matching feature of the test image, wherein there is a spatial relationship between each respective object image feature and a test image feature, and wherein the object depicted in the test image comprises a plurality of attributes. Additionally, the embodiment involves estimating, for each attribute in the test image, an attribute value based at least in part on information stored in a metadata associated with each of the object images.

Abstract: Methods, apparatus, and articles of manufacture to measure geographical features using an image of a geographical location are disclosed. An example method includes dividing, with a processor, an image of a geographic area of interest into a plurality of geographical zones, the geographical zones being representative of different geographical areas having approximately equal physical areas, measuring, with the processor, a geographical feature represented in the image for corresponding ones of the plurality of geographical zones, storing descriptions for the geographical zones in a computer memory, and storing values representative of the geographical feature of the geographical zones.

Abstract: An image processing apparatus includes a subject area detector and a subject area determinator. The subject area detector is configured to perform subject detection processing to detect a subject area from an input image. The subject area determinator is configured to determine a final subject area by majority decision processing that is based on the subject areas detected in the subject detection processing performed a plurality of times.

Abstract: There are provided a person recognition apparatus, method, and a non-transitory computer readable recording medium which can perform accurate person recognition according to a time dependent face change. A sorting section sorts a plurality of images by shooting date and time. A group division section divides the plurality of images into a plurality of groups according to a predetermined shooting date and time range. A face recognition section extracts feature amounts by face recognition for each group. An in-group person determination section determines a person having a similarity of a predetermined reference threshold value or higher as the same person and integrates the feature amounts relevant to the person for each group. An inter-group person recognition section recognizes persons having a similarity of a predetermined recognition threshold value or higher as the same person between two groups based on the feature amounts integrated in adjacent groups.

Abstract: An image processor generates a Super-Resolution (SR) frame by upscaling. A Human Visual Preference Model (HVPM) helps detect random texture regions, where visual artifacts and errors are tolerated to allow for more image details, and immaculate regions having flat areas, corners, or regular structures, where details may be sacrificed to prevent annoying visual artifacts that seem to stand out more. A regularity or isotropic measurement is generated for each input pixel. More regular and less anisotropic regions are mapped as immaculate regions. Higher weights for blurring, smoothing, or blending from a single frame source are assigned for immaculate regions to reduce the likelihood of generated artifacts. In the random texture regions, multiple frames are used as sources for blending, and sharpening is increased to enhance details, but more artifacts are likely. These artifacts are more easily tolerated by humans in the random texture regions than in the regular-structure immaculate regions.