Abstract: Methods and systems for lane boundary detection using images are described. A computing device may be configured to receive, from an image-capture device coupled to a vehicle, an image of a road of travel of the vehicle. The computing device may be configured to identify a pixel in the image based on an intensity of the pixel and a comparison of the intensity of the pixel to respective intensities of neighboring pixels. Based on the intensity of the pixel and the comparison, the computing device may be configured to determine a likelihood that the pixel belongs to a portion of the image depicting a lane marker on the road. Based at least on the likelihood, the computing device may be configured to and provide instructions to control the vehicle.

Abstract: Described herein is a method for recognizing a human head in a source image. The method comprises detecting a contour of at least part of a human body in the source image, calculating a depth of the human body in the source image. From the source image, a major radius size and a minor radius size of an ellipse corresponding to a human head at the depth is calculated, and, for at least several of a set of pixels of the detected contour, generating in an accumulator array at least one segment of an ellipse centered on the position of the contour pixel and having the major and minor radius sizes. Positions of local intensity maxima in the accumulator array are selected as corresponding to positions of the human head candidates in the source image.

Abstract: An image recognition device including: a first recognition unit that performs image recognition within an image to find a first object; an obtaining unit that obtains an attribute of the first object found by the first recognition unit; an object specifying unit that refers to object correspondence information showing identifiers of second objects and associating each identifier with an attribute, and specifies an identifier of one of the second objects that is associated with the attribute of the first object; an area specifying unit that refers to area value information showing values that are associated with the identifiers of the second objects and are related to a first area occupied by the first object, and specifies a second area within the image by using a value associated with the identifier of the one of the second objects; and a second recognition unit that performs image recognition within the second area to find the one of the second objects.

Abstract: A medical image diagnostic apparatus of the present invention includes: an image display unit that displays a medical image including a target part of an object; an input unit that inputs feature points of the target part; a contour position estimation unit that estimates a contour position of the target part to generate an initial contour; a contour extraction unit that extracts a contour along the shape of the target part using the feature points and the initial contour; and a control unit that displays a composite image, which is obtained by combining the extracted contour and the medical image, on the image display unit.

Abstract: Techniques for searching in an image for a particular block of pixels that represents a feature are described herein. The techniques may include searching within an expanding search area to find a block of pixels that has a threshold amount of similarity to a block of pixels of a preceding image. Upon finding a block of pixels that satisfies the threshold, the techniques may search in the image along a path of increasing similarity to the block of pixels of the preceding image.

Abstract: A device may obtain a program that includes a logo that is inserted into the program by adding luminance to a set of pixels defining a shape of the logo. The device may generate a luminance map for the program that identifies an amount of luminance added to each pixel included in the set of pixels to insert the logo into the program. The device may determine a selection of the program by a user via a set top box. The device may determine that the set top box is providing the program for display to the user based on the luminance map.

Abstract: A region extraction apparatus includes: a region extraction unit that extracts, from an image data of a process target, a high intensity region having higher intensity than a neighboring region thereof and a low intensity region having lower intensity than a neighboring region thereof; a combination identification unit that identifies a combination of a high intensity region and a low intensity region corresponding to an extraction target region to be extracted based on arrangement positions of the high intensity region and the low intensity region extracted by the region extraction unit; an outer frame determination unit that determines an outer frame corresponding to the combination of the high intensity region and the low intensity region; and a contour extraction unit that extracts a contour of the extraction target region based on image data within the outer frame determined by the outer frame determination unit.

Abstract: An account creating and authenticating method is provided. Firstly, an account is created according to a face image included in a photo. A password corresponding to the face image is also generated by a service system. During an account authenticating method, an image pickup device is used to shoot a face of a login person on the spot. If the service system judges that the shot face image of the login person on the spot complies with a predetermined face image corresponding to an existing account, the login person is allowed to login into the service system and the password is displayed. In a case that the image pickup device is provided, the service system may be authenticated by inputting the password. The method of the present can simplify the process of creating and authenticating the account.

Abstract: A method of labeling pixels in an image in which pixels in the image that represent human skin of one or more people are detected and one or more regions in the image are identified, where each region in the one or more regions includes all or a portion of a human face of a person in the one or people in the image. Pixels that represent each face in the image are identified using the pixels that represent skin and the regions that include faces of the people, thereby identifying a position of each face in the image. From this, a face mask for each face and a rough body map corresponding to each face is determined using the positions of the identified faces. Further still, a torso map corresponding to each face is determined using determined face positions. Then, the extracted face masks and the torso maps are used to refine a skin map. A person or people map is determined using the skin map and the rough body map.

Abstract: One or more systems and/or techniques are provided to identify objects comprised in a compound object without segmenting three-dimensional image data of the potential compound object. Two-dimensional projections of a potential compound object (e.g., Eigen projections) are examined to identify the presence of known objects. The projections are compared to signatures, such as morphological characteristics, of one or more known objects. If it is determined based upon the comparison that there is a high likelihood that the compound object comprises a known object, a portion of the projection is masked, and it is compared again to the signature to determine if this likelihood has increased. If it has, a sub-object of the compound object may be classified based upon characteristics of the known object (e.g., the compound object may be classified as a potential threat item if the known object is a threat item).

Abstract: Techniques for identifying a salient object with respect to its context are described. A process receives an input image that includes a salient object. The process segments the input image into multiple regions and calculates a saliency value for each of the segmented regions based on scale image levels. The process constructs saliency maps based at least in part on the calculated saliency value, and combines the saliency maps to construct a total saliency map. Next, the process connects a set of line segments computed from the input image and utilizes the total saliency map to compute a closed boundary, which forms a shape prior from the closed boundary, and extracts the salient object from the total saliency map and the shape prior.

Abstract: Device for edge detection and quality enhancement in an image which comprises a grouping of identical and locally interconnected elementary processing cells. Each processing cell is characterised in turn by a comparator which carries out in parallel the comparison of each pair of neighbouring pixels. The threshold voltage which establishes the difference in voltage between pixels considered to be part of an edge is determined by means of a temporary adjustment of a control signal. This adjustment, along with that of the filtering control signal, also temporary in nature, are the only ones necessary for configuring the required processing. No external analogue control signals are required making it easier to programme the hardware by the device which is used and reducing the number of digital/analogue converters of the final system.

Abstract: A consecutive thin edge detection system and method for enhancing color filter array image is disclosed in the present invention. The consecutive thin edge detection system includes a consecutive thin edge detector, a color gradient estimator and a direction indicator. The consecutive thin edge detector receives a color pixel array including a plurality of color pixels and alternately sets each color pixel as a target pixel. The consecutive thin edge detector detects a difference value between a plurality of first green pixels and a plurality of second green pixels nearby a target pixel, and determines whether the target pixel comprises a consecutive thin edge feature or not according to the difference value. The plurality of first green pixels are in red pixel rows which comprises a plurality red pixels and the plurality of first green pixels, and the plurality of second green pixels are in a blue pixel row which comprises blue pixels and the plurality of second green pixels.

Abstract: A method of providing a unique identifier for a manufactured part includes defining a boundary area on at least one surface of the manufactured part, recording surface properties within a portion of the boundary area, interpreting the recorded surface properties with a pattern recognition algorithm to create the unique identifier, and storing the unique identifier in a database.

Abstract: Techniques of detecting text in video are disclosed. In some embodiments, a portion of video content can be identified as having text. Text within the identified portion of the video content can be identified. A category for the identified text can be determined. In some embodiments, a determination is made as to whether the video content satisfies at least one predetermined condition, and the portion of video content is identified as having text in response to a determination that the video content satisfies the predetermined condition(s). In some embodiments, the predetermined condition(s) comprises at least one of a minimum level of clarity, a minimum level of contrast, and a minimum level of content stability across multiple frames. In some embodiments, additional information corresponding to the video content is determined based on the identified text and the determined category.

Abstract: A composite repair system and method for assisting in the repair of a cured composite part in which a damaged portion has been cut out and removed, exposing a plurality of composite plies and their cut edges, which are then taper sanded to expose a plurality of taper-sanded surfaces and their corresponding ply boundaries. The ply boundaries may be traced by a user with a marking device. The composite repair system may comprise an image capturing device to obtain an image of the traced ply boundaries and a computing device for processing creating a map of the traced ply boundaries based on the image. The map may be used to manufacture filler plies having peripheral edges shaped to correspond with the ply boundaries for replacing the damaged portion of the composite part.

Abstract: An image processing apparatus including a first image processing unit and a second image processing unit. The first image processing unit is configured to calculate a parameter for image processing based on a first image, but not based on a second image, and execute the image processing on the first image using the parameter. The second image processing unit is configured to execute the image processing on the second image using the parameter.

Abstract: An image processing apparatus and method for generating high-sensitive, high-brightness color images are disclosed. A second image having a wider band and higher-sensitivity than those of a first image which includes color information may be acquired, wherein the first and second images are images captured from a scene. A first transformed image having high brightness may be generated by performing binning on the first image, and edge information being a high-frequency component may be extracted from the second image. A high-brightness, high-sensitive color image may be generated using the first transformed image and the edge information.

Abstract: A method and apparatus for image processing to avoid counting shelf edge promotional labels when counting product labels. Shelf edges are identified by detecting shelf edge content in a captured image by comparing the image to reference images of shelf edge content. Detected occurrences of shelf edge content are demarcated using a geometric pattern having corners at coordinates corresponding to positions around the identified shelf edge content. Corresponding corners are grouped into clusters, and the clusters are analyzed to define the upper and lower bounds of a shelf region in the image.

Abstract: Implementations relate to relate to rectification of distortion in an image. In some implementations, a method includes extracting edgelets from an image, each edgelet defined by a location of a pixel having an edge depicted in the image and defined by a direction of the edge. The method finds at least one vanishing point in the image based on intersections of pairs of the edges of the edgelets. Each vanishing point is selected based on a plurality of the edgelets in the image having edges approximately aligned with the vanishing point. Found vanishing points are used to transform the image to reduce image distortion.

Abstract: An image processing method capable of appropriately increasing a resolution of an input image in which an edge direction that is a direction along an edge included in the input image is identified; a shape of an application region that is a region including at least a part of the edge is determined according to the identified edge direction; an image similar to an image within the application region having the determined shape is searched for; and an output image is generated by performing a resolution conversion process on the input image using the similar image so that the input image includes high-frequency components.

Abstract: Disclosed are methods and apparatuses for searching images. An image is received and a first search path is defined for the image. The first search path may be a straight line, horizontal, and/or near the bottom of the image, and/or may begin at one edge and move toward the other. A transition is defined for the image, distinguishing a feature to be found. The image is searched for the transition along the first search path. When the transition is detected, the image is searched along a second search path that follows the transition. The apparatus includes an image sensor and a processor. The sensor is adapted to obtain images. The processor is adapted to define a first search path and a transition for the image, to search for the transition along the first search path, and to search along a second search path upon detecting the transition, following the transition.

Abstract: A method for selectively applying a reflectance modifying agent (RMA) to an area of skin, the method comprising receiving an image of the area of skin, identifying, using the image, a nominated point within the area of skin, determining an actual reflectance of the nominated point, applying an edge protection technique based on the image to generate one or more outputs, determining a desired reflectance of the nominated point based on the one or more outputs, calculating an amount of RMA to be applied based on the output, and determining whether to apply the RMA to the area of skin based on the amount of RMA.

Abstract: An image recognition method and an image recognition system can be applied to fetal ultrasound images. The image recognition method includes: (a) adjusting the image with a filter operator to decrease noise and to homogenize an image expression level of the pixel units within an individual object structure; (b) analyzing the image by a statistic information function, determining a foreground object pixel unit and a background pixel unit according to a max information entropy state of the statistic information function; and (c) searching by a profile setting value and recognizing a target object image among the foreground object pixel unit. The image recognition method can not only increase the efficiency of identifying the object of interests within the image and measuring the object of interests, but also improve the precision of measurements of the object of interests.

Abstract: A PSF cost function used for determining a PSF kernel (438) of at least a portion of an image (16) includes (i) a first fidelity term having a first direction derivative, (ii) a first fidelity term weight for the first fidelity term, (iii) a second fidelity term having a second direction derivative, and (iv) a second fidelity term weight for the second fidelity term. Another PSF cost function for determining a PSF kernel (638) includes (i) a first fidelity term with a first derivative in a dominant edge direction (d), and (ii) a second fidelity term having a second derivative in a perpendicular direction(p) to the dominant edge direction.

Abstract: An error of an outline point due to a brightness fluctuation cannot be corrected by a simple method such as a method of adding a certain amount of offset. However, in recent years as the miniaturization of the pattern represented by a resist pattern has progressed, it has been difficult to appropriately determine a region that serves as a reference. An outline of the resist pattern is extracted from an image of the resist pattern obtained by a charged particle beam apparatus in consideration of influence of the brightness fluctuation. That is, a plurality of brightness profiles in the vicinity of edge points configuring the outline are obtained and an evaluation value of a shape of the brightness profile in the vicinity of a specific edge is obtained based on the plurality of brightness profiles, and the outline of a specific edge point is corrected, based on the evaluation value.

Abstract: A driver assistance system for a vehicle includes an imaging device disposed at an exterior portion of a vehicle. With the imaging device disposed at the exterior portion of the vehicle, the imaging device has a field of view at least one of rearward of the vehicle and sideward of the vehicle. A control utilizes edge detection in processing image data captured by the imaging device. Responsive at least in part to processing of captured image data by the control, the control determines that an object is present in the field of view of the imaging device. The control is operable to determine that the imaging device is misaligned. The control, responsive to a determination of misalignment of the imaging array sensor, is operable to at least partially compensate for the determined misalignment of the imaging device.

Abstract: Embodiments herein provide an ultrahigh sensitive optical microangiography (OMAG) system that provides high sensitivity to slow flow information, such as that found in blood flow in capillaries, while also providing a relatively low data acquisition time. The system performs a plurality of fast scans (i.e., B-scans) on a fast scan axis, where each fast scan includes a plurality of A-scans. At the same time, the system performs a slow scan (i.e., C-scan), on a slow scan axis, where the slow scan includes the plurality of fast scans. A detector receives the spectral interference signal from the sample to produce a three dimensional (3D) data set. An imaging algorithm is then applied to the 3D data set in the slow scan axis to produce at least one image of the sample. In some embodiments, the imaging algorithm may separate flow information from structural information of the sample.

Abstract: In an image processing device, the control device identifies a background color of the image. The control device classifies each of the pixels into either one of a background color pixel group or a non-background color pixel group. The control device determines whether a partial region of the image having the non-background pixel is a chromatic color region or an achromatic color region, without using pixel values corresponding to pixels classified into the background color pixel group. The control device determines that the image is chromatic color image when it is determined that the partial region is the chromatic color region. The control device determines that the image is achromatic color image when it is determined that the partial region is the achromatic color region.

Abstract: A computing device and a method joints point clouds of an object into a coordinate system. The computing device calculates edge points of each image, and calculates a curvature scale space (CSS) corner of each image according to the edge points of each image. The computing device calculates a sub-pixel corner of each image according to the CSS corner of each image, and matches a sub-pixel corner of each image to obtain common corners. The computing device calculates a transmitting matrix using the common corners, and transmits all point clouds in the coordinate system using the transmitting matrix.

Abstract: A computer-implemented method for creating an ordered set of boundary data by transforming data from remotely sensed imagery of shorelines is provided. A feature data set and an edge data set are transformed into a set of 3-point boundary segments having a specific head and tail point and the segments are ordered from tail to head in a clockwise or counterclockwise manner relative to the water. Once the 3-point segments are created they are easily linked together into larger segments. These large multi-point segments in turn are linked together to create a closed loop in a predetermined direction, for example, but not limited to, the shorelines for rivers or coastal areas.

Abstract: Disclosed are a component recognizing apparatus and a component recognizing method. The component recognizing apparatus includes: an image preprocessing unit configured to extract component edges from an input component image by using a plurality of edge detecting techniques, and detect a component region by using the extracted component edges; a feature extracting unit configured to extract a component feature from the detected component region, and create a feature vector by using the component feature; and a component recognizing unit configured to input the created feature vector to an artificial neural network which has learned in advance to recognize a component category through a plurality of component image samples, and recognize the component category according to a result.

Abstract: Methods and apparatus to methods and apparatus to identify images in print advertisements are disclosed. An example method comprises computing a first image feature vector for a first presented image, comparing the first image feature vector to a second image feature vector, and when the first image feature vector matches the second image feature vector, storing printed-media information associated with the first presented image in a database record associated with the second image feature vector.

Abstract: In the present invention, when a solid object is recognized in the direction of movement of an own vehicle, in a system which carries out driving support of a vehicle, turning control of the vehicle is carried out in order to avoid a collision with the solid object. However, the execution of the turning control is permitted, in cases where a distance between the position of the own vehicle under turning control and the position of the solid object in an entire range of a turning control zone continuous between a predetermined control starting point at which the turning control of the own vehicle is started and a predetermined control ending point at which the turning control ends becomes equal to or less than a predetermined avoidance distance at which it is determined to avoid the collision with the solid object.

Abstract: Techniques and apparatus for automatic upright adjustment of digital images. An automatic upright adjustment technique is described that may provide an automated approach for straightening up slanted features in an input image to improve its perceptual quality. This correction may be referred to as upright adjustment. A set of criteria based on human perception may be used in the upright adjustment. A reprojection technique that implements an optimization framework is described that yields an optimal homography for adjustment based on the criteria and adjusts the image according to new camera parameters generated by the optimization. An optimization-based camera calibration technique is described that simultaneously estimates vanishing lines and points as well as camera parameters for an image; the calibration technique may, for example, be used to generate estimates of camera parameters and vanishing points and lines that are input to the reprojection technique.

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: 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: Methods and systems for processing an image to facilitate automated object recognition are disclosed. More particularly, an image is processed based on a perceptual grouping for the image (e.g., derived via segmentation, derived via contour detection, etc.) and a geometric-configuration model for the image (e.g., a bounding box model, a constellation, a k-fan, etc.).

Abstract: A method of processing image data includes a plurality of different processes performed based on edge information generated as a result of performing a preset process from among the plurality of different processes. Therefore, the time for processing the image data is reduced, and image quality is enhanced.

Abstract: The objective is to provide a finger shape estimating device that can estimate the image most similar to a finger image quickly and with high precision, and that can facilitate construction of a database.

Abstract: An image processing apparatus detects boundaries from an image; extracts straight-line segments from the boundaries; detects a region where differences between pixel values of near pixels located across the segments are larger than, or at least a predetermined first value; classifies the segments in the region into four sides of quadrangles; detects colors or densities in outer areas of the four sides; selects combinations that differences between the colors or the densities corresponding to the segments in the combinations are no more than, or smaller than a predetermined second value, from the combinations of the four sides that possibly form the quadrangles; detects coordinates of four vertexes obtained when the segments in the combinations are extended, and a combination that an area of a quadrangle formed by the corresponding four coordinates satisfies a predetermined condition; and corrects the quadrangle formed by the combination to a rectangle.

Abstract: An image feature extraction device according to an embodiment includes a gradient image calculator generates intensity gradient data with respect to two different directions based on intensity data of image data; and a gradient count unit calculates a covariance matrix for each partial area obtained by dividing the image data based on the intensity gradient data. The image feature extraction device according to the embodiment further includes a feature data output unit calculates two parameters related to a major axis and a minor axis of an ellipse expressed by the covariance matrix, quantizes a range of the logarithms of the parameters for each of the partial area using a predetermined division number, and outputs a feature vector which contains a value only at a dimension corresponding to the quantized range different from the other dimensions.

Abstract: A denoising apparatus comprising an image input unit which receives pixel data including color information of pixels included in a correction target image, a denoising unit which denoises the pixel data by a weight based averaging method, wherein the weight is set to a maximum value when a difference value between a correction target block and a comparison target block in the correction target image is zero, decreases linearly to zero as the difference value increases until it reaches a threshold value, and is set to zero when the difference value is greater than or equal to the threshold value, and an image output unit which outputs the pixel data processed by the denoising unit. The denoising unit assigns a corrected weight value to at least a guaranteed number of comparison target blocks for an impulse block, where an impulse block is a correction target block for which the number of non-zero weight valued comparison target blocks is less than a predetermined guaranteed number.

Abstract: An image measurement apparatus includes: an imager section, an obtainment section, an outline detection section, a setting section, and a measurement section. The imager section takes an image of a subject to be measured. The obtainment section obtains a taken image of the subject taken by the imager section. The outline detection section detects, by a Hough transformation, outline of a graphic included in the image obtained by the obtainment section. The setting section sets an edge detection tool on the outline detected by the outline detection section. The measurement section measures, by the edge detection tool set by the setting section, graphic information concerning the graphic.

Abstract: A structure descriptor for an m×n pixel block of an image may be determined. The m×n pixel block may contain a primary pixel having a primary pixel value and a plurality of secondary pixels having respective secondary pixel values. The structure descriptor may include a plurality of structure indicators each associated with a respective secondary pixel. The respective structure indicators may be based on the primary pixel value and the respective secondary pixel value of the associated secondary pixel. Based on the structure descriptor, a structure value for the m×n pixel block may be determined. Based on the structure value, image processing may be applied to the m×n pixel block.

Abstract: A method is provided for enhancing edge detection for edges of irregular surfaces in a machine vision inspection system. The inspection system comprises an edge feature video tool configured to determine profile data for an edge feature based on a plurality of differently focused images. An edge-referenced alignment compensation is provided related to substantially minimizing a respective offset amount of the edge feature at respective locations along a directional filtering direction used for directionally filtering the plurality of differently focused images prior to determining the profile data for the edge feature. In some embodiments, the plurality of differently focused images may be directionally filtered using a directional filtering sub region (DFS) defined relative to a point corresponding to a PFF basis pixel location in each of the plurality of images, each DFS having a relatively longer dimension along the directional filtering direction.

Abstract: Provided are an image composition apparatus for composing color images with black-and-white images including infrared components, and an image composition method thereof. The image composition method includes generating a first image signal with color information and a second image signal including infrared components without color information, dividing the first image signal into a brightness signal and a color signal, composing the brightness signal of the first image signal with a brightness signal of the second image signal to generate a composed brightness signal, and composing the composed brightness signal with the color signal of the first image signal to generate a color image.

Abstract: The disclosure relates to a system and method having a common interface to manage and integrate secure information traversing a network with disparate domains. The system and method are capable of rapidly taking external data sources (for example, systems, databases, streams, repositories, websites, etc.) and fusing them under a mediated meta-data layer that allows for data mining, manual and automated analysis and various visualization capabilities in a single application. The system allow for the capability of using data sources, and making secure and appropriate visualization and interoperability functions available in a single portal or interface.

Abstract: A method for creating image products includes the following steps. Image data and positional data corresponding to the image data are captured and processed to create geo-referenced images. Edge detection procedures are performed on the geo-referenced images to identify edges and produce geo-referenced, edge-detected images. The geo-referenced, edge-detected images are saved in a database. A user interface to view and interact with the geo-referenced image is also provided such that the user can consistently select the same Points of Interest between multiple interactions and multiple users.

Abstract: Disclosed is a pupil detection device capable improving the pupil detection accuracy even if a detection target image is a low-resolution image. In a pupil detection device (100), an eye area actual size calculation unit (102) acquires an actual scale value of an eye area, a pupil state prediction unit (103) calculates an actual scale prediction value of a pupil diameter, a necessary resolution estimation unit (105) calculates a target value of resolution on the basis of the calculated actual scale prediction value, an eye area image normalization unit (107) calculates a scale-up/scale-down factor on the basis of the calculated target value of resolution and the actual scale value of the eye area, and normalizes the image of the eye area on the basis of the calculated scale-up/scale-down factor, and a pupil detection unit (108) detects a pupil image from the normalized eye area image.