Abstract: Ear Gear is a Hearing Aid security protection device that protects Hearing Aids from loss, moisture wind and dirt while making them more comfortable to wear. Made from spandex or other materials, Ear Gear comes in a variety of colors. The Ear Gear sleeve and cord come in a variety of lengths and widths to fit different types of Hearing Aids: BTEs, ITEs, Minis, Cochlear, FM. There are eight models. Ear Gear has a small opening at the top and a large opening at the bottom. There is a left and right sleeve attached to stretch cord connected to a clip which attaches to clothing. Remove the earmold from the Hearing Aid; the top of the Hearing Aid slides through the bottom of the Ear Gear sleeve through to the top where it locks. The earmold is reattached. Variations include mono, binaural, cordless, closed bottom, open back and flap cover.

Abstract: An insert earphone comprises a housing and at least one transducer that is located in the housing. The transducer is adapted to receive electrical energy and to responsively convert the electrical energy into acoustic energy for presentation to an eardrum of a user. The transducer is positioned within the housing so as to be in close proximity to the eardrum of the user when the housing is inserted into the ear canal. At least one sealing member is coupled to the housing. The at least one sealing member is adapted to provide an acoustic seal within the ear canal of the user.

Abstract: A hanging type earphone includes an earphone body and an ear hook. The earphone body has a speaking portion and a first connecting portion thereon. A pair of polygonal prisms is disposed at opposite ends of the first connecting portion. The ear hook is shaped to fit a shape of ears and pivotally mounted to the earphone body for hanging the earphone body on an ear. The ear hook has a second connecting portion shaped as a bridge with a pair of piers disposed there-beneath. The pair of piers each defines a polygonal hole. The second connecting portion rides on the first connecting portion with the polygonal prisms inserted into the respective polygonal holes. A wall of each polygonal hole is at least partially split so that the polygonal hole is enlargeable to enable the polygonal prism to pivot therein.

Abstract: A tactile sound speaker transmits sound-generated vibrations to a user through a touchpad to provide a tactile sound experience. The tactile sound speaker can include a speaker driver, a speaker cone, and a touchpad. The touchpad can be coupled to the speaker cone by transmission shafts that transmit vibrations generated by the speaker driver's output. A user may experience tactile sound by contacting the touchpad with a hand, foot, or other body part while listening to music or other sound.

Abstract: A speaker is provided and includes a diaphragm which is composed of a primary planar disc and a secondary planar disc which has a smaller diameter than the primary planar disc. The primary and secondary planar discs are concentrically put together by means of adhesive, which makes the outer rim of the primary planar disc clear of the secondary planar disc thus forming a surround thereat. The ratio of the diameter of the secondary planar disc relative to the effective diameter of the primary planar disc is optimally determined, whereby the resonance frequency of the diaphragm can be lowered, and the input power threshold limit value keeping off generation of an abnormal sound can be raised. Accordingly, a low profile speaker with an excellent performance can be produced.

Abstract: An apparatus acoustic loading of a diaphragm is disclosed. The apparatus comprises a rear face having a shape corresponding to a shape of a compression side of the diaphragm, a front face opposite to the rear face along an axis of symmetry, and a plurality of voids formed between the rear face and the front face. The plurality of voids are arranged so that their intersection with rear face forms a plurality of inlets, the plurality of inlets defining a higher compression ratio in the proximity of a voice coil compared to a compression ratio defined in at least a portion of the remaining area of the diaphragm.

Abstract: Disclosed is a speaker comprising a frame connected with a magnetic circuit having a magnetic gap, a voice coil disposed adjacent to but not in contact with an upper side of the magnetic circuit, and a diaphragm bonded to a circumferential edge of the frame, wherein the frame and the diaphragm are configured into such peripheral shapes that conform to a mounting space allowed for the speaker inside an apparatus. This structure allows an external shape of the speaker to be freely configurable according to a limited space, yet the irregularly-shaped diaphragm is capable of being driven with an uniform amplitude, thereby providing an advantage of down-sizing and high performance.

Abstract: A computer system and method that selects and records unique portions of media files (audio, video and graphical image, and other content) submitted for UMC cataloging. The unique fingerprint of the media is then stored in the associated UMC record for use by other computer systems to minimize duplicate claims of ownership relating to media which may be located on one or more owner controlled web servers connected to the Internet. In one embodiment, when a media file is being cataloged into the UMC database, the system performs an analysis of the media file to find a unique piece that can be saved as a fingerprint for the media file. This fingerprint is analyzed against the UMC database to locate duplicate fingerprints which may indicate either duplicate media or duplicate fingerprints for different media. In the case of duplicate fingerprints for different media a new analysis is of the new media is done to come up with a more unique fingerprint.

Abstract: A digital differential steganographic system and method includes a master key that is generated from an unmarked media, a mark-point reservoir created from the unmarked media and containing a set of viable candidate mark points for the unmarked media, and a mark-point applicator to insert data into the unmarked media at selected mark-points chosen from the mark-point reservoir creating a digital watermark. The method includes using an original unmarked media, shaping and testing marks in the original media for predictable distortion, verifying embedded marks at point of insertion in the original media, minimizing mark energy and duration for least-perceptible change, and using non-distributed, unmarked media of the original media as a master key.

Abstract: The present invention relates to a technology which acquires information specific to a device by an image pickup element and remotely controls a desired device based on the acquired device-specific information. Particularly, the present invention relates to a technology which displays information for performing detailed remote control easily. In the present invention, it is intended to display information about manipulation of a desired device as needed and to facilitate remote manipulation of the device. As a result, according to an aspect of the present invention, since detailed information of a desired device can be selected to be viewed, detailed information of each of multiple devices can be easily identified by a single controller as needed.

Abstract: A first-information obtaining unit that obtains first information and a second-information obtaining unit obtains second information. The second information has a higher degree of importance than that of the first information. A generating unit generates watermark image data including a group of first dot patterns including the first information and a group of second dot patterns including the first information and the second information and having a dot size enlarged from a dot size of the first dot patterns. A superposing unit superposes the generated watermark image data on a target image data.

Abstract: A specific frequency component extraction unit extracts a specific frequency component signal from an input image signal. A phase controller controls the phase of the specific frequency component signal. A correlator computes the cross-correlation value of the phase-controlled specific frequency component signal and the input image signal. A watermark information estimation unit filters the cross-correlation value to detect watermark information embedded in the input image signal.

Abstract: A specific frequency component extraction unit extracts a specific frequency component signal from an input image signal. A phase controller controls the phase of the specific frequency component signal. A correlator computes the cross-correlation value of the phase-controlled specific frequency component signal and the input image signal. A watermark information estimation unit filters the cross-correlation value to detect watermark information embedded in the input image signal.

Abstract: A system tracks multiple moving objects in a stream of video data. In an embodiment, the system uses a combination of video motion detection data and color based data. In another embodiment, the system combines this data into a condensation framework. In yet another embodiment, the integration of the video motion data and the color-based data is done is real time. In further embodiments, the robustness of the tracking is enhanced by applying heuristics.

Abstract: A device for detecting an image area from an image data that is inputted in series for each pixel is provided. The device includes a lateral direction edge detection portion for comparing pixel data of neighboring pixels in the lateral direction on one line of the image, a vertical direction detection portion for regarding pixels of edge addresses as a noted pixel and comparing pixel data of the noted pixel with that of a pixel one the next line neighboring the noted pixel so as to detect a pixel having a difference between the data within a predetermined range, an area address memory portion for storing an address of the detected pixel when the vertical direction detection portion detected that the difference is within a predetermined range, and an area extraction portion for extracting an area that satisfies a size condition stored in the area address memory portion.

Abstract: A method for detecting an obstacle by using two cameras, the obstacle being on a reference plane in a field of view common to the two cameras, the method inputting a first image and a second image from the two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on of the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D and the degree of similarity P both obtained as being on the reference plane region, judging that the obstacle is at a pos

Abstract: A computer readable storage medium storing instructions of a computer program which when executed by a computer results in performance of steps including inputting a first image and a second image from two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on of the degree of similarity D and the degree of similarity P on a reference plane region, detecting the obstacle on a basis of the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D and

Abstract: A method for detecting an obstacle by using two cameras, the obstacle being on a reference plane in a field of view common to the two cameras, the method inputting a first image and a second image from the two cameras, respectively, transforming the first image to a transformed image, obtaining a degree of similarity D indicating a similarity between an image in a processing region established in the second image and an image in a corresponding processing region established in the first image, obtaining a degree of similarity P indicating a similarity between an image in the processing region established in the second image and an image in a corresponding processing region established in the transformed image, detecting the obstacle based on the degree of similarity D and the degree of similarity P on a reference plane region, detecting the obstacle on a basis of the degree of similarity D and the degree of similarity P on a reference plane region, obtaining a difference K between the degree of similarity D a

Abstract: A personal identification system using biometrics data including a biometrics data inputting section, a characteristic data obtaining section for obtaining characteristic data of the collation object person, a biometrics data retaining section for retaining registration biometrics data of each registered object person, which data is previously registered and correlated with one of collation groups according to registration characteristic data, and a biometrics data collating section for collating the collation biometrics data with the registration biometrics data, wherein the biometrics data collating section extracts a particular group from the plural collation groups based on the characteristic data of the collation object person, and collates the collation biometrics data with registration biometrics data of the particular group.

Abstract: A biometric authentication device, which uses biometrics characteristic information to perform individual authentication, prevents declines in verification speed even when numerous biometrics information sets have been registered. A control unit registers broad characteristic quantities for blood vessel image data from an image capture device, together with characteristic data for verification. And at the time of authentication the control unit uses degrees of similarity of characteristic quantities to determine an order of verification, and performs verification of blood vessel image characteristic data in the verification order thus determined. The order of verification is determined based on captured blood vessel images, so that even when numerous characteristic data sets have been registered, verification can be performed in an order of verification based on a blood vessel image of the user, and the speed of verification can be improved.

Abstract: An exemplary embodiment providing one or more improvements includes an authentication system which allows an article to be authenticated using an article serial number connected with the article and a self-authenticating document having a serial number that is associated with the article serial number. Access to a database containing the association is provided and the article is authenticated by self authenticating the document and accessing the database to determine the association.

Abstract: There is provided an electronic apparatus that can scroll an image on a display screen with a simple operation and in various modes. A glide point is provided and a fingerprint sensor is provided adjacently to the glide point. Scroll mode is changed in response to a touch of a finger or thumb on the glide point and a vertical or horizontal movement of the finger or thumb on the glide point and an image on the display screen is scrolled in response to an upward or downward movement of a finger or thumb on the fingerprint sensor.

Abstract: A registration apparatus includes an extraction unit that extracts characteristics of a subject of biometric identification at every predetermined period as a characteristics image on the basis of the video signals output from an image pickup element as a result of picking up images of the subject of biometric identification at sequentially differentiated image pickup position in response to a relative movement of the image pickup element and the subject of biometric identification at a predetermined biological site, a degree of similarity detection unit that detects the degree of similarity between the characteristics image currently being processed and the characteristics image processed immediately before the characteristics image currently being processed or the characteristics image to be processed next to the characteristics image currently being processed and a registration unit that registers the characteristics image currently being processed as biometric identification information when the degree of

Abstract: A computer-implemented method for detection of fiber pathways includes determining initial data as a subset of voxels that have been selected from a diffusion tensor image by applying a threshold to fractional anisotropy values, determining a cluster of points with highly collinear diffusion directions, and performing region growth to find suitable seed points in a plane that is normal to the cluster's mean direction, starting from the center of the cluster. The method further includes tracing pathways from the seed points, eliminating voxels of the subset from the initial data that are close to any of the pathways using a distance threshold, displaying a visualization of a selection of voxels used as seed points and of the pathways traced from the seed points.

Abstract: A method for matching tree-structures using original image data includes providing a first tree representative of an anatomical structure in a first digital medical image of a pair of digital medical images, said tree comprising a plurality of double linked, directed branches B=(S, P, C) of sites S, links to parents P, and links to children C, providing a second tree representative of an anatomical structure in a second digital medical image of said pair of images, registering said first medical image to said second medical image wherein a registration function is defined, and matching said first tree and said second tree using said registration function.

Abstract: An apparatus and method for obtaining a planar image of a portion (4) of a body (5) and enhancing image quality of at least one specific organ or volume of interest located within the portion (4) of the body (5), administered with radiopharmaceutical substance radiating gamma rays, by using single photon emission imaging, for determination of functional information thereon, comprising: (a) acquiring at least one projection data of the portion (4), by means of a gamma camera detector (2); (b) determining the effective distance between the detector (2) and the specific organ of interest; (c) calculating weight values taking into account acceptance angles of the gamma camera detector (2) and the effective distance; and (d) obtaining a two dimensional image of a spatial distribution of the pharmaceutical substance within the portion (4) by mathematically analyzing the data in conjunction with weight values.

Abstract: The invention relates to an image processing device for processing X-ray images, in particular mammography X-ray images, and also to a corresponding X-ray device, to a method for this and to a computer program or computer program product. In the image processing device, display images are created from X-ray images which show at least two spatially separate objects such as a marker and a mamma Part-images which show the respective objects are determined in the X-ray images and the part-images are arranged in the display images. The size of the display images is such that the part of the display images that is free of the part-images is smaller than the corresponding part of the X-ray images.

Abstract: The invention relates to a method of segmenting an object in a data set, wherein the object is initially segmented resulting in a first set (N0) of voxels. An erosion operation is performed on the first set (N0) of voxels resulting in an eroded set (N?) of voxels. A dilation operation is performed on the eroded set (N?) of voxels resulting in a dilated set (N+) of voxels.

Abstract: The present invention is directed to methods and apparatus for processing check data, such as data stored using magnetic indicia. In one embodiment, a check transaction processing system receives an indication that a first check transaction from a first payor failed to clear because at least a portion of first MICR or other account data associated with the first check transaction is incorrect. The check transaction processing system reads a personal identifier associated with the first payor, wherein the personal identifier was provided in association with the first check transaction. MICR data or other account data associated with a previously processed check transaction associated with the personal identifier is located.

Abstract: An automatic inspection system is provided for monitoring rail track for detecting and generating alerts for certain hazards to the operation of trains that may cause various safety concerns and even derailment. The monitoring is during normal railway service runs without interrupting the normal railway services. In one implementation, an imaging module is used on a passenger or freight train to capture video images of the rail track under the train in motion. In one implementation, the captured video images are automatically processed in a computer using a software module which is based on digital image processing techniques and algorithms to determine whether an irregularity is present on the rail track. In one implementation, video images containing detected irregularities on the rail track are transmitted to a control center for further analysis and possible alert.

Abstract: A method of characterizing surface structures using a chemically curable impression material to take an impression of at least one site of the undamaged surface of an article and of a surface of an article damaged by mechanical and/or chemical exposure and/or by exposure to radiation and/or heat, and/or of a surface of a test specimen mounted on the surface of an article, said test specimen surface being damaged by mechanical and/or chemical exposure and/or by exposure to radiation and/or heat, curing the impression material to produce a negative of the damage pattern, and using image analysis to determine the extent of the surface structures and/or the extent of the surface damage within the damage pattern on the basis of light-microscope pictures of the negative. Use of the method for the preparation, modification and/or development of new and/or existing materials.

Abstract: An inspection apparatus (10) applying two dimensional nondestructive examination images onto a three dimensional solid model of a component (12) to display a virtual component (73) that may be manipulated to perform a nondestructive inspection. The two dimensional nondestructive examination images may be acquired from a plurality of views of the component in order to provide full coverage of the surface to be inspected, with appropriate stitching of images in regions of overlap between adjacent views. The two dimensional images (62) may be color or black and white photographs or ultraviolet or infrared images, for example. Multiple types of nondestructive examination images, results of inspection data evaluations, and design, operational and/or maintenance information may be displayed separately or jointly on the three dimensional solid model.

Abstract: A device and method for detecting the presence or absence of an object which has repetitive motion are disclosed comprising, a receiver for receiving a signal from the object, and circuitry for determining the presence or absence of the object to be detected, wherein the circuitry records the signal from the receiver as a pattern of data during at least part of the repetitive motion of the object, compares the data with a previously recorded data pattern and, produces an output signal based on the comparison. The signal may be received during discrete time intervals, and may be light which can be transmitted with varying intensity. The circuitry may determine the value of signal received at a receiver and produce a binary value. The signal received at the receiver can be reflected from the object to be detected.

Abstract: Provided is a method for converting a first image signal expressed in a first color space into a second image signal expressed in a second color space on a subword parallelism basis.

Abstract: Height attributes of features of an object having a plurality of physical features thereon is determined by illuminating the features of the object at a low angle and capturing the reflected light at a camera mounted along the z-axis perpendicular to the object. The reflected light from the features is analyzed to determine if any of the features is of an unacceptable height. The reflected light being either brighter or dimmer than the average determines that the corresponding feature is higher or lower respectively than the average feature.

Abstract: A method for classifying or comparing objects includes detecting points of interest within two objects, computing feature descriptors at said points of interest, forming a multi-resolution histogram over feature descriptors for each object and computing a weighted intersection of multi-resolution histogram for each object. An alternative embodiment includes a method for matching objects by defining a plurality of bins for multi-resolution histograms having various levels and a plurality of cluster groups, each group having a center, for each point of interest, calculating a bin index, a bin count and a maximal distance to the bin center and providing a path vector indicative of the bins chosen at each level. Still another embodiment includes a method for matching objects comprising creating a set of feature vectors for each object of interest, mapping each set of feature vectors to a single high-dimensional vector to create an embedding vector and encoding each embedding vector with a binary hash string.

Abstract: A system and method are provided for processing a document. The method comprises: marking an area of a document, using at least one predetermined markup symbol; identifying a markup symbol; using the identified markup symbol to locate the document area; determining characters in the document area; and, processing the determined characters. Fields that can be processed include title, keywords, author, signature, document name, category, subject, or document status, to name but a few examples. In some aspects, marking an area of a document, using at least one predetermined markup symbol includes: electronically marking using a medium such as a touchscreen, pressure pad, or a mouse. Alternately, the paper document can be physically marked (with a pen or pencil) before scanning. Typically, marking an area of a document includes forming a markup character proximate to an enclosing figure. A wide range of markup characters can be defined cross-referenced to document processes.

Abstract: There is provided technology which, when producing metadata for correlation with image data to which predetermined processing is to be administered and for characterizing that image data, can produce metadata that is more appropriate to the predetermined processing and can contribute to alleviating the work burden. A metadata producing apparatus produces metadata for correlation with image data to which predetermined processing is to be administered and for characterizing that image data, the metadata producing apparatus including: a type information acquiring unit that acquires information relating to the type of metadata necessary to conduct the predetermined processing; and a metadata producing unit that produces, on the basis of the information acquired by the type information acquiring unit, metadata to be correlated with the image data to which the predetermined processing is to be administered.

Abstract: Disclosed is an abnormal pattern detection program for a function call in a source program that makes a computer, which is connected to a main memory and an output device, execute the following processes. (1) A reading process for reading the source program onto the main memory. (2) A sentence extracting process for extracting previous and next sentences of every function call of each function from the source program read onto the main memory. (3) A setting process for setting common appearance patterns, which are included in the previous and next sentences of every function call extracted through the sentence extracting process and appear in a high frequency, on the main memory. (4) An output process for outputting a warning message from the output device when a function call whose previous and next sentences do not include any of the common appearance patterns is found in the source program.

Abstract: A digital image pickup device is provided with an input unit that inputs a photographed digital image, a predetermined information detector that detects predetermined information, a predetermined information embedding unit that embeds the detected predetermined information in the digital image and a browse restriction applying unit that executes a process for applying browse restriction to the digital image in which the predetermined information is embedded.

Abstract: The invention concerns a method for determining feature data that represents information about the shape of an object. A partitioning scheme (RP) is determined that defines a plurality of cells (p) in the space in which the object is located such that at least some of the cells (p) each contain a respective portion of the object, and the feature data is determined for the object on the basis of at least one property of the respective portions of the object that are contained in the plurality of cells (p). According to a first aspect of the invention, at least two of the plurality of cells (p) overlap each other at least in part, and according to a second aspect of the invention, at least some of the boundaries of the cells (p) delimit a plurality of regions (r) in the space in which the object is located such that the respective portions of the object that are contained in the plurality of regions (r) are approximately equal to each other with respect to a predetermined measurement metric.

Abstract: An image feature analyzing section performs an image feature analysis with respect to an input image to output an image feature vector. A parameter output section stores a plurality of image feature vectors and a plurality of parameters corresponding to the respective image feature vectors and outputs an original parameter value corresponding to an image feature vector. A parameter operation setting section determines contents of an operation of an illumination equation parameter, depending on a prescribed image conversion. A parameter operating section operates the original parameter value in accordance with a prescription of the parameter operation setting section, to obtain a new parameter value. An image generating section generates an output image based on the new parameter value.

Abstract: A device and method for detecting feature points of an object from an image. A three-dimensional model is created in which a plurality of nodes corresponding to feature points in a learning image are defined. The model is projected onto an input image and a feature value is derived from a plurality of sampling points around a projection point of each node. An error estimated amount is computed based on the displacement of a feature point between a correct model and an error model. The three dimensional position of each feature point in the input image is estimated based on the error estimated amount and a three dimensional model.

Abstract: A region data describing method for describing, over a plurality of frames, region data about the region of an arbitrary object in a video, the method specifying the object region in the video with at least either of an approximate figure approximating the region or characteristic points of the region, approximating a trajectory obtained by arranging position data of the representative points or the characteristic point in a direction in which frames proceed with a predetermined function and describing the parameter of the function as region data. Thus, the region of a predetermined object in the video can be described with a small quantity of data. Moreover, creation and handling of data can easily be performed.

Abstract: A region data describing method for describing, over a plurality of frames, region data about the region of an arbitrary object in a video, the method specifying the object region in the video with at least either of an approximate figure approximating the region or characteristic points of the region, approximating a trajectory obtained by arranging position data of the representative points or the characteristic point in a direction in which frames proceed with a predetermined function and describing the parameter of the function as region data. Thus, the region of a predetermined object in the video can be described with a small quantity of data. Moreover, creation and handling of data can easily be performed.

Abstract: A pattern matching system that outputs an likeness values, comprising a designation block, a comparison block, a calculation block and an output block, is provided. The likeness value shows how much a first and second image compares to each other. The designation block designates a first and second image data as data to be compared. The first and second image data comprises 2?x of area data. The comparison block compares the data level of the area data corresponding to pattern areas at the relatively same location in the first and second images. The calculation block calculates the likeness value. The likeness value varies according to the number of the pattern areas where the absolute value of the difference between the compared data levels of the area data is less than a predetermined standard value.

Abstract: To provide a method for controlling the display of a screen which allows the user to discriminate the scanned image and the recognition result intuitively and easily. The display control method for allowing the user to verify the recognition result of a character on a verification screen form 300 is implemented as follows. First of all, the standard pattern of a specific character stored in a memory and a plurality of character images recognized as the specific character are read, upon an operation of the user. And the read standard pattern is displayed in a recognition result character display portion 310 within the verification screen form 300 and a plurality of the read character image are displayed sequentially in a character image display portion 320 adjacent or proximal to the recognition result character display portion 310 and at a predetermined position of a character image list display portion 330.

Abstract: An information processing apparatus includes a higher node having a plurality of weak discriminators that have learned a learning sample of a first label and a learning sample of a second label that has a predetermined coordinate relationship with the learning sample of the first label, a first lower node having a plurality of weak discriminators that have learned the learning sample of the first label based on the discrimination result of the higher node and a second lower node that has no weak discriminator.

Abstract: Complex multidimensional datasets generated by digital imaging spectroscopy can be organized and analyzed by applying software and computer-based methods comprising sorting algorithms. Combinations of these algorithms to images and graphical data, allow pixels or features to be rapidly and efficiently classified into meaningful groups according to defined criteria. Multiple rounds of pixel or feature selection may be performed based on independent sorting criteria. In one embodiment sorting by spectral criteria (e.g., intensity at a given wavelength) is combined with sorting by temporal criteria (e.g., absorbance at a given time) to identify microcolonies of recombinant organisms harboring mutated genes encoding enzymes having desirable kinetic attributes and substrate specificity. Restriction of the set of pixels analyzed in a subsequent sort based on criteria applied in an earlier sort (“sort and lock” analyses) minimize computational and storage resources.

Abstract: An image processing system provides faster than real-time skin detection and localization. The system uses the highly optimized architecture of a graphics processing unit to quickly and efficiently detect and locate skin in an image. By performing skin detection and localization on the graphics processing unit, the image processing system frees the main system processor to perform other important tasks, including running general purpose applications. The speed with which the image processing system detects and localizes skin also facilitates subsequent processing steps such as face detection and motion tracking.