Abstract: A method and system for recognizing and selecting a portion of an image. The method and system employs user-controlled region growing to select a region within an image. The user manipulates a user input device to interactively increase or decrease the number of iterations performed by a region growing routine. The progress of the growth of the region is displayed to the user on a display. In the case of a three dimensional image, the user may select sectional or volume views of the image within which to monitor the growth of the region. Once the user determines an appropriately sized region has been grown, the remainder of the image is scalpelled away and the selected region is displayed on the display. Alternatively, the region is scalpelled away and the remainder of the image is displayed on the display.

Abstract: Systems and methods for encoding and decoding document images are disclosed. Document images are segmented into multiple layers according to a mask. The multiple layers are non-binary. The respective layers can then be processed and compressed separately in order to achieve better compression of the document image overall. A mask is generated from a document image. The mask is generated so as to reduce an estimate of compression for the combined size of the mask and multiple layers of the document image. The mask is then employed to segment the document image into the multiple layers. The mask determines or allocates pixels of the document image into respective layers. The mask and the multiple layers are processed and encoded separately so as to improve compression of the document image overall and to improve the speed of so doing. The multiple layers are non-binary images and can, for example, comprise a foreground image and a background image.

Abstract: Apparatus and a method are disclosed for automatically identifying and validating a document, for validating the identity of a bearer of a document, for verifying that the bearer has authorization to participate in an activity represented by the document, and for comparing information on the document against information databases to determine if there are known concerns about the document or its bearer. A document type is narrowed by initially determining the size of the document, and is then identified from amongst a group of documents by looking for colors or other characteristics at specific locations on the document only until the document is identified. The order in which document locations are looked at is dependent upon a history of the types of documents that have been identified.

Abstract: A system and method facilitating document image compression utilizing a mask separating a foreground of a document image from a background is provided. The invention includes a pixel energy analyzer adapted to partition regions into a foreground and background. The invention further provides for a merge region component adapted to attempt to merge regions if the merged region would not exceed a threshold energy. Merged regions are partitioned into a new foreground and new background. Thereafter, a mask storage component stores the partitioning information in a binary mask.

Abstract: A fingerprint sensing system includes an image sensor, a rate sensor and a sensor circuit. The image sensor includes a linear array of capacitive sensors for capacitive sensing of ridge peaks and ridge valleys of a fingerprint on a swiped finger. The rate sensor senses the speed of the finger as it is swiped across the image sensor. The sensor circuit supplies image drive signals to the image sensor and detects image signals in response to the drive signals. The sensor circuit supplies rate drive signals to the rate sensor and detects rate signals in response to the rate drive signals. The sensor circuit further coordinates the image signals and the rate signals to provide a fingerprint image. The image sensor may be configured as an image pickup plate and multiple image drive plates formed on a substrate, such as a flexible printed circuit board or other flexible substrate which may conform to the shape of the finger.

Abstract: The present invention provides a circuit pattern edge inspection method of finding out a failure in a fabricating process and image distortion in an observing apparatus by analyzing, by a non-destructive inspection, the shape of an edge of a line of a fine pattern in which characteristics of the material, process, and an exposure optical system in a semiconductor fabricating process appear, and performing analysis quantitatively. The method includes a step of detecting a set of edge points indicative of positions of edges of the pattern in a two-dimensional plane by a threshold method; a step of obtaining an approximation line for the set of edge points detected; and a step of obtaining an edge roughness shape and a characteristic by calculating the difference between the set of the edge points and the approximation line. A plurality of values are used as thresholds used for the threshold method.

Abstract: A method for quantization of a color histogram bin value of an image or video, and more particularly, a method for non-uniform quantization of a color histogram bin value of an image (or video) according to the frequency of color occurrence is provided. The methods effectively represent the characteristics of a color histogram of an image in comparison to conventional art, and improve the performance of image retrieval when an image (video) retrieval search is conducted.

Abstract: A method for personalizing an image-based physical manifestation to conform with user preferences for image processing. In one implementation, the method includes identifying an image for processing, identifying user preferences for image processing and processing the image including manipulating image data for the image in accordance with the user preferences.

Abstract: A retouching method for enhancing an appearance of a face located in a digital image involves acquiring a digital image containing one or more faces and detecting a location of facial feature points in the faces, where the facial feature points include points identifying salient features such as skin, eyes, eyebrows, nose, mouth, and hair. The location of the facial feature points are used to segment the face into different regions such as skin, eyes, eyebrows, nose, mouth, neck and hair regions. Facially relevant characteristics of the different regions are determined and, based on these facially relevant characteristics, an ensemble of enhancement filters are selected, each customized especially for a particular region, and the default parameters for the enhancement filters are selected. The enhancement filters are then executed on the particular regions, thereby producing an enhanced digital image from the digital image.

Abstract: A method and system for estimating the quality of video data without gaining access to the source data, are configured to perform a Fast Fourier Transform (FFT) from at least some of the pixel values of the image in at least the horizontal direction, and at most, in the horizontal and vertical directions for the luminance and chrominance components. An average FFT is used to calculate kurtosis and skewness, then an image-quality metric is determined by calculating an offset from the kurtosis and skewness outputs.

Abstract: An image condition is judged based on a mean value and a standard deviation of a feature quantity of an image, and image correction information in the image condition is created based on the mean value and the standard deviation, to thereby correct the image, based on the created image correction information. In this manner, parameters for the image correction processing are determined automatically and highly accurately corresponding to the feature quantity of the image, and the image correction processing is performed based on the parameters. Therefore, the image quality can be improved, while considerably reducing the labor of the operator who performs the image processing.

Abstract: A method for extracting feature information from product images using multivariate image analysis based on Principal Component Analysis (PCA) which is used to develop predictive models for feature content and distribution on the imaged product. The imaging system is used to monitor product quality variables in an on-line manufacturing environment. It may also be integrated into a closed-loop feedback control system in automated systems.

Abstract: Transforming optical images of a portion including a normal conductor pattern having a surface roughness, a portion subjected to an inspection, and a reference portion to images of electric charges and picking up these as electric signals by an image pick-up device, rendering the optical image including the normal conductor pattern having the surface roughness to a pixel signal by the image pick-up device, controlling a light volume of the optical image so that the pixel signal is saturated or immediately before the saturation, picking up a pixel signal of the portion to be inspected under this light volume, obtaining a differential signal from a pixel signal picked up from the reference portion, and judging an existence of defect from the differential signal, so as to detect defects such as a hiatus of conductor, a short circuit, and a deposition of an extraneous matter on a wafer, on which the normal conductor pattern having the roughened surface, with a high accuracy in processes of forming films and etchi

Abstract: A method and system for performing three-dimensional pattern recognition by use of digital holography is disclosed. The complex amplitude distribution generated by an object is recorded by phase-shifting interferometry. The digital hologram contains information about the objects shape, location, and orientation. This information allows one to perform multi-dimensional pattern-recognition methods with a high degree of discrimination and to measure three-dimensional orientation changes.

Abstract: A biometric sensing device includes sensing arrays for sensing a biological surface swiped across the sensing arrays in an arbitrary direction. This device allows for simultaneously sensing different features of a biological surface where the features have the smallest distinguishable features of different size. Using the technique of interleaving partial images, the resolution of the biometric sensing device is increased. Therefore, a small and robust biometric sensing device is provided, which allows for sensing high resolution images.

Abstract: A batch processing method for enhancing an appearance of a face located in a digital image, where the image is one of a large number of images that are being processed through a batch process, comprises the steps of: (a) providing a script file that identifies one or more original digital images that have been selected for enhancement, wherein the script file includes an instruction for the location of each original digital image; (b) using the instructions in the script file, acquiring an original digital image containing one or more faces; (c) detecting a location of facial feature points in the one or more faces, said facial feature points including points identifying salient features including one or more of skin, eyes, eyebrows, nose, mouth, and hair; (d) using the location of the facial feature points to segment the face into different regions, said different regions including one or more of skin, eyes, eyebrows, nose, mouth, neck and hair regions; (e) determining one or more facially relevant character

Abstract: The image reading apparatus for photoelectrically reading an original image includes an image reading device and a detection device. The image reading device has first reading unit for reading a visible image carried by the original image and a second reading unit for reading a reference image in a wavelength different from that used to read the visible image. The detection device acquires correlative pixel distribution information between a visible image signal and a reference image signal using the visible image and the reference image having been read by the image reading device and detects an image defect caused by a foreign particle deposited on the original image and a flaw of an original using the information. The apparatus can detect the image defect of the film with pinpoint accuracy without erroneous detection without depending upon a type of the film and a state of the image, and output in excellent productivity an image of high quality whose image defect has been preferably corrected.

Abstract: An image collecting system for collecting an image having a target character therein comprising a camera system that captures an image in which the target character is caught in a predetermined area; an image database that stores images captured by the camera system; a character information database that stores character information for identifying a person caught in an image as the target character; a character positioning unit for obtaining position information of the target character at a certain time; and an image collecting unit that connects to the image database and the character information database to identify images stored in the image database with the target character therein based on the character information stored in the character information database and the position information of the target character obtained by the character positioning unit, and collect images in which the target character is caught from the images stored in the image database.

Abstract: A method for correcting color variations on the surface of a wafer, a method for selectively detecting a defect from different patterns, and computer readable recording media for the same are provided. Color variations in images of different parts of a wafer can be corrected using the mean and standard deviation of grey level values for the pixels forming each of the different parts of the wafer. In addition, different threshold values are applied to metal interconnect patterns and spaces of the wafer so that a defect can be selectively detected from the different patterns. Thus, a bridge known as a fatal, or killing defect to a semiconductor device can be detected without also falsely detecting grains as fatal defects. Due to increased defect screening capacity of the methods, the defect detecting method can be further efficiently managed.

Abstract: A method and system are provided for constructing a virtual three-dimensional model of an object using a data processing system, and at least one machine-readable memory accessible to the data processing system. A set of at least two digital three-dimensional frames of portions of the object are obtained from a scanner or other source comprising a set of point coordinates in a three dimensional coordinate system providing differing information of the surface of the object. The frames provide a substantial overlap of the represented portions of the surface of the object, but do not coincide exactly. Data representing the set of frames are stored in the memory and processed by the data processing system so as to register the frames relative to each other to thereby produce a three-dimensional virtual representation of the portion of the surface of the object covered by the set of frames.