Abstract: A method of segmenting images receives an image (such as a medical image) and a segment in relation to the image, displays them to an observer, receives a modification to the segment from the observer, and generates a second segment in relation to a second image, responsive to the modification. An image segmentation system includes a learning scheme or model to take input from an observer feedback interface and to communicate with a means for drawing an image segment to permit adjustment of at least one image segmentation parameter (such as a threshold value). The learning scheme is provided with a knowledge base which may initially be created by processing offline images. The learning scheme may use any scheme such as a reinforcement learning agent, a fuzzy inference system or a neural network.

Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method for learning object recognition in an image is provided. According to a feature of the present invention, the method comprises the steps of providing a training set of standard images, calculating intrinsic images corresponding to the standard images and building a classifier as a function of the intrinsic images.

Abstract: An input layer outputs light having a relatively narrow emission angle distribution to a middle layer as an output signal if the signal level of input signal is relatively high and outputs light having a relatively broad emission angle distribution to the middle layer as the output signal if the signal level of input signal is relatively low. The middle layer outputs light having a relatively narrow emission angle distribution as an output signal to an output layer if the signal level of the output signal from input layer is relatively high and outputs light having a relatively broad emission angle distribution to the output layer as an output signal if the signal level of the output signal from the input layer is relatively low.

Abstract: A method adapts a boosted classifier to new samples. A boosted classifier is trained using initial samples. The boosted classifier is a combination of weak classifiers. Each weak classifier of the boosted classifier is updated adaptively by adding contributions of new samples and deleting contributions old samples.

Abstract: An apparatus and method for editing an optimized color preference are provided. The apparatus includes a color information controlling unit which extracts data about a preference by comparing color information of a transformed image generated by transforming color information of an original image and the original image according to a user preference; a learning unit which teaches a neural network about the preference, based on the extracted data, and predicts color information variation by the neural network; and an image correcting unit which corrects color information of an input image according to the predicted color information variation. The method includes extracting data about a preference; teaching a neural network about the preference, based on the extracted data; predicting color information variation by the neural network; and correcting color information of an input image according to the predicted color information variation.

Abstract: First order predicate logics are provided, extended with a bilattice based uncertainty handling formalism, as a means of formally encoding pattern grmmars, to parse a set of image features, and detect the presence of different patterns of interest implemented on a processor. Information from different sources and uncertainties from detections, are integrated within the bilattice framework. Automated logical rule weight learning in the computer vision domain applies a rule weight optimization method which casts the instantiated inference tree as a knowledge-based neural network, to converge upon a set of rule weights that give optimal performance within the bilattice framework. Applications are in (a) detecting the presence of humans under partial occlusions and (b) detecting large complex man made structures in satellite imagery (c) detection of spatio-temporal human and vehicular activities in video and (c) parsing of Graphical User Interfaces.

Abstract: A crystal lookup table used to define a matching relationship between a signal position of a detected event in a PET scanner and a corresponding detector pixel location is generated using a neural network-based algorithm, and is implemented by a FPGA.

Abstract: The disclosed terrain model is a generative, probabilistic approach to modeling terrain that exploits the 3D spatial structure inherent in outdoor domains and an array of noisy but abundant sensor data to simultaneously estimate ground height, vegetation height and classify obstacles and other areas of interest, even in dense non-penetrable vegetation. Joint inference of ground height, class height and class identity over the whole model results in more accurate estimation of each quantity. Vertical spatial constraints are imposed on voxels within a column via a hidden semi-Markov model. Horizontal spatial constraints are enforced on neighboring columns of voxels via two interacting Markov random fields and a latent variable. Because of the rules governing abstracts, this abstract should not be used to construe the claims.

Abstract: A method and apparatus are provided for removing regularly occurring visible artifacts in decompressed video images. Firstly a decompressed video signal is received. This is filtered frame-by-frame to extract data related to the artifacts. The thus extracted data is then processed in a neural network processor which has been trained to identify the artifacts in order to produce data identifying their locations. The video signal is then corrected to reduce the effect of the thus identified artifacts.

Abstract: Various technologies and techniques are disclosed that improve handwriting recognition operations. Handwritten input is received in training mode and run through several base recognizers to generate several alternate lists. The alternate lists are unioned together into a combined alternate list. If the correct result is in the combined list, each correct/incorrect alternate pair is used to generate training patterns. The weights associated with the alternate pairs are stored. At runtime, the combined alternate list is generated just as training time. The trained comparator-net can be used to compare any two alternates in the combined list. A template matching base recognizer is used with one or more neural network base recognizers to improve recognition operations. The system provides comparator-net and reorder-net processes trained on print and cursive data, and ones that have been trained on cursive-only data. The respective comparator-net and reorder-net processes are used accordingly.

Abstract: Techniques are disclosed for detecting the occurrence of unusual events in a sequence of video frames Importantly, what is determined as unusual need not be defined in advance, but can be determined over time by observing a stream of primitive events and a stream of context events. A mapper component may be configured to parse the event streams and supply input data sets to multiple adaptive resonance theory (ART) networks. Each individual ART network may generate clusters from the set of inputs data supplied to that ART network. Each cluster represents an observed statistical distribution of a particular thing or event being observed that ART network.

Abstract: A system and method for detecting metal contraband such as weapons related material in shipping containers where a container is scanned with at least one penetrating beam, preferably a tomographic x-ray beam, and at least one image is formed. The image can be analyzed by a pattern recognizer to find voids representing metal. The voids can be further classified with respect to their 2 or 3-dimensional geometric shapes. Container ID and contents or bill of lading information can be combined along with other parameters such as total container weight to allow a processor to generate a detection probability. The processor can use artificial intelligence methods to classify suspicious containers for manual inspection.

Abstract: The present invention relates to an image processing apparatus and method, a learning apparatus and method, and a program which allow reliable evaluation of whether or not the subject appears sharp. A subject extraction unit 21 uses an input image to generate a subject map representing a region including the subject in the input image, and supplies the subject map to a determination unit 22. The determination unit 22 uses the input image and the subject map from the subject extraction unit 21 to determine the blur extent of the region of the subject on the input image, and calculates the score of the input image on the basis of the blur extent. This score is regarded as an index for evaluating the degree to which the subject appears sharp in the input image. The present invention can be applied to an image capture apparatus.

Abstract: We propose methods for generating a halftone image, in which each pixel takes one of two tone values. The generated image contains hidden data, which is present at data storage pixels chosen using a pseudo-random number generator. In a first case, the data is hidden within an existing halftone image by reversing the tone value at certain of the data storage pixels, and at pixels neighboring the data storage pixels. In a second case, the halftone image is generated from a grey-scale image, and data is hidden during this conversion process.

Abstract: A markerless motion capture system is provided for measurements accurate enough for biomechanical, clinical, sport, entertainment, animation, game and movie, design, ergonomics, surveillance applications. The system has multiple cameras distributed around a viewing volume. The cameras allow for the creation of three-dimensional mesh representations of an object dynamically moving within the viewing volume. A model of the object that incorporates specific morphological and kinematic model information (including soft joint constraints) is then matched to the captured three-dimensional mesh representations. The matching routine aims to embed the model into each of the three-dimensional representations using (i) iterative closest point or simulated annealing algorithms and (ii) using soft joint constraints. This unique combination of routines offers a simple, time-efficient, accurate and thus more meaningful assessment of movements.

Abstract: A calculation processing apparatus, which executes calculation processing based on a network composed by hierarchically connecting a plurality of processing nodes, assigns a partial area of a memory to each of the plurality of processing nodes, stores a calculation result of a processing node in a storable area of the partial area assigned to that processing node, and sets, as storable areas, areas that store the calculation results whose reference by all processing nodes connected to the subsequent stage of that processing node is complete. The apparatus determines, based on the storage states of calculation results in partial areas of the memory assigned to the processing node designated to execute the calculation processing of the processing nodes, and to processing nodes connected to the previous stage of the designated processing node, whether or not to execute a calculation of the designated processing node.

Abstract: A mobile communication terminal and method of inserting symbols thereof are disclosed, by which a convenient symbol input system is provided and by which a user is facilitated to input a symbol using a fingerprint pattern of the user. The present invention includes a fingerprint recognizer, a control unit searching a symbol matched to the recognized fingerprint pattern if a fingerprint pattern is recognized by the fingerprint recognizer, and an output unit outputting the searched symbol.

Abstract: Efficiently simulating an Amari dynamics of a neural field (a), the Amari dynamics being specified by the equation (1) where a(x,t) is the state of the neural field (a), represented in a spatial domain (SR) using coordinates x,t, i(x,i) is a function stating the input to the neural field at time t, f[.] is a bounded monotonic transfer function having values between 0 and 1, F(x) is an interaction kernel, s specifies the time scale on which the neural field (a) changes and h is a constant specifying the global excitation or inhibition of the neural field (a). A method for simulating an Amari dynamics of a neural field (a), comprising the step of simulating an application of the transfer function (f) to the neural field (a). According to the invention, the step of simulating an application of the transfer function (f) comprises smoothing the neural field (a) by applying a smoothing operator (S).

Abstract: A system for detecting smoke in a monitored area includes: (a) a video device for capturing a series of successive video images of the monitored area as a series of two-dimensional bitmaps having a specified number of pixels, (b) a processing device having memory capability for storing said series of images and processing capability for analyzing the series of images, and (c) an analysis algorithm that runs on the processing device and has: (i) an identification portion for examining this series of bitmaps to identify indicator areas in successive bitmaps of adjacent pixels that have the potential for being used as indicators for the existence of smoke in the monitored area, (ii) a tracking portion for identifying the trends in the growth and movement of the indicator areas, and (iii) a trend comparison portion for comparing the identified trends to determine which of the trends are consistent with those produced by a smoke cloud.

Abstract: Identifying objects in images is a difficult problem, particularly in cases an original image is noisy or has areas narrow in color or grayscale gradient. A technique employing a convolutional network has been identified to identify objects in such images in an automated and rapid manner. One example embodiment trains a convolutional network including multiple layers of filters. The filters are trained by learning and are arranged in successive layers and produce images having at least a same resolution as an original image. The filters are trained as a function of the original image or a desired image labeling; the image labels of objects identified in the original image are reported and may be used for segmentation. The technique can be applied to images of neural circuitry or electron microscopy, for example. The same technique can also be applied to correction of photographs or videos.

Abstract: The technical field of the invention is that of processing or generating image data, and it more particularly relates to a method for processing images consisting of pixels generated by an image sensor with a view to supplying input data to a simulated or wired neural process. The method is characterized in that it comprises a step of reading pixel-by-pixel in real time by processing means and a step of constructing prototype vectors during the pixel-by-pixel reading process on the basis of the values read, the prototype vectors constituting the input data of the neural process. It is intended for applications in global environmental perception and movement analysis. The method to which the invention relates may also be used for conventional image processing operations such as temporal filtering, and it makes it possible to save on computing time and memory space.

Abstract: A pulse signal processing circuit, a parallel processing circuit, and a pattern recognition system including a plurality of arithmetic elements for outputting pulse signals and at least one modulation circuit, synaptic connection element(s), or synaptic connection means for modulating the pulse signals, the modulated pulse signals then being separately or exclusively output to corresponding signal lines.

Abstract: An artificial neural network (ANN) based system that is adapted to process an input pattern to generate an output pattern related thereto having a different number of components than the input pattern. The system (26) is comprised of an ANN (27) and a memory (28), such as a DRAM memory, that are serially connected. The input pattern (23) is applied to a processor (22), where it can be processed or not (the most general case), before it is applied to the ANN and stored therein as a prototype (if learned). A category is associated with each stored prototype. The processor computes the coefficients that allow the determination of the estimated values of the output pattern, these coefficients are the components of a so-called intermediate pattern (24). Assuming the ANN has already learned a number of input patterns, when a new input pattern is presented to the ANN in the recognition phase, the category of the closest prototype is output therefrom and is used as a pointer to the memory.

Abstract: A method detects objects in an image. First, features are extracted from the image. A frequency transform is applied to the features to generate transformed features. A covariance matrix is constructed from the transformed features, and the covariance matrix is classified to determine whether the image includes the object, or not.

Abstract: Image processing method wherein each image is composed of an array of image points, so called pixels or voxels particularly in a two-, three-, or more dimensional space respectively each image point being univocally defined by its position within the array of image points and by one or more numerical parameters defining the image point appearance as regards characteristics of brightness, grey, colour shade or the like, and wherein each image point is considered to be a node of an artificial neural network, the image being processed as a function of parameters defining the appearance of each pixel as values of the nodes of said artificial neural network and as a function of connections of each pixel under processing with neighbouring pixels composed of pixels of a predetermined subset of pixels, particularly with neighbouring pixels of said pixel under processing, so called pixel window, while pixels of the new image i.e.

Abstract: Disclosed herein are systems and methods for facilitating the usage of an online workforce to remotely monitor security-sensitive sites and report potential security breaches. In some embodiments, cameras are configured to monitor critical civilian infrastructure, such as water supplies and nuclear reactors. The cameras are operatively connected to a central computer or series of computers, and images captured by the cameras are transmitted to the central computer. After initially registering with the central computer, Guardians “log on” to a central website hosted by the central computer and monitor the images, thereby earning compensation. In one embodiment, images of “no-man” zones—areas where no humans or vehicles should be present or monitored—are sent to Guardians for a simple determination of whether or not a human exists in the picture.

Abstract: Various technologies and techniques are disclosed for improving handwriting recognition using a neural network by allowing a user to provide samples. A recognition operation is performed on the user's handwritten input, and the user is not satisfied with the recognition result. The user selects an option to train the neural network on one or more characters to improve the recognition results. The user is prompted to specify samples for the certain character, word, or phrase, and the neural network is adjusted for the certain character, word, or phrase. Handwritten input is later received from the user. A recognition operation is performed on the handwritten input using the neural network that was adjusted for the certain character or characters.

Abstract: A probabilistic boosting tree framework for computing two-class and multi-class discriminative models is disclosed. In the learning stage, the probabilistic boosting tree (PBT) automatically constructs a tree in which each node combines a number of weak classifiers (e.g., evidence, knowledge) into a strong classifier or conditional posterior probability. The PBT approaches the target posterior distribution by data augmentation (e.g., tree expansion) through a divide-and-conquer strategy. In the testing stage, the conditional probability is computed at each tree node based on the learned classifier which guides the probability propagation in its sub-trees. The top node of the tree therefore outputs the overall posterior probability by integrating the probabilities gathered from its sub-trees. In the training stage, a tree is recursively constructed in which each tree node is a strong classifier. The input training set is divided into two new sets, left and right ones, according to the learned classifier.

Abstract: We propose methods for generating a halftone image, in which each pixel takes one of two tone values. The generated image contains hidden data, which is present at data storage pixels chosen using a pseudo-random number generator. In a first case, the data is hidden within an existing halftone image by reversing the tone value at certain of the data storage pixels, and at pixels neighbouring the data storage pixels. In a second case, the halftone image is generated from a grey-scale image, and data is hidden during this conversion process.

Abstract: In a hierarchical neural network having a module structure, learning necessary for detection of a new feature class is executed by a processing module which has not finished learning yet and includes a plurality of neurons which should learn an unlearned feature class and have an undetermined receptor field structure by presenting a predetermined pattern to a data input layer. Thus, a feature class necessary for subject recognition can be learned automatically and efficiently.

Abstract: Image processing method for a digital medical examination image, the pixels of which are assigned a gray-scale value in each instance, with a minimum and a maximum gray-scale value being defined as limit values for the purpose of displaying the examination image, with the pixels being subjected to an evaluation by means of a neural network, in order to determine such pixels and to disregard them when defining the gray-scale values which are located in a direct radiation region or in a projected collimator region.

Abstract: A system is provided in which the spatial values (S1 to Sn) of the physical quantity are represented by measurement pulses (I1 to In), the temporal ordering of which represents the values, which are processed by processing units (U1 to Un) arranged in at least one row and each include an output (SOR1 to SORn). During successive processing cycles, a measurement pulse processed therein can be delivered to form the output signal (SU) of the system. Each processing unit includes an inhibiting unit (BI) for, in other units and during a given processing cycle, inhibiting the passage to the outputs of the other units respective measurement pulses processed therein and hence preventing them from forming the output signal, if the measurement impulses are temporally ordered later in the given processing cycle than the one processed in the unit concerned.

Abstract: Dimensionality reduction systems and methods facilitate visualization, understanding, and interpretation of high-dimensionality data sets, so long as the essential information of the data set is preserved during the dimensionality reduction process. In some of the disclosed embodiments, dimensionality reduction is accomplished using clustering, evolutionary computation of low-dimensionality coordinates for cluster kernels, particle swarm optimization of kernel positions, and training of neural networks based on the kernel mapping. The fitness function chosen for the evolutionary computation and particle swarm optimization is designed to preserve kernel distances and any other information deemed useful to the current application of the disclosed techniques, such as linear correlation with a variable that is to be predicted from future measurements. Various error measures are suitable and can be used.

Abstract: A program storage device is provided readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for classification of biological tissue by gene expression profiling. The method steps include providing a training set of gene expression profiles of known tissue samples, providing a first-layer strong classifier of the known tissue samples by combining weak classifiers using boosting, creating two sample sets based on the first classifier, populating the two sample sets with a next-layer of classifiers based on a previous-layer classifier, organizing the classifiers in a tree data structure, and outputting the tree data structure as a probabilistic boosting tree classifier for tissue sample classification and disease subtype discovery. A multi-class diagnosis problem is transformed to a two-class diagnosis process by finding an optimal feature and dividing the multi-class problem into two-classes.

Abstract: A process for intelligent importation of information from a foreign application user interface includes extraction of raster data from a pre-designated region of a screen displayed in the foreign application, segmentation of the raster data into prospective sets of character raster data; application of the character raster data and a feature data set and a vector data set derived from the character raster data as inputs to respective raster, feature, and vector artificial neural networks to generate candidate characters; using a voting process to identify a character represented by the character raster data from the candidate characters; assembly of the remaining characters as recognized by the neural networks into a key; and association of the key with an external data file which may be stored and thereafter retrieved in association with the screen displayed in the foreign application.

Abstract: Shape recognition is performed based on determining whether one or more ink strokes is not part of a shape or a partial shape. Ink strokes are divided into segments and the segments analyzed employing a relative angular distance histogram. The histogram analysis yields stable, incremental, and discriminating featurization results. Neural networks may also be employed along with the histogram analysis to determine complete shapes from partial shape entries and autocomplete suggestions provided to users for conversion of the shape into a known object.

Abstract: Systems, methods, and computer program products implementing techniques for training classifiers. The techniques include receiving a training set that includes positive samples and negative samples, receiving a restricted set of linear operators, and using a boosting process to train a classifier to discriminate between the positive and negative samples. The boosting process is an iterative process. The iterations include a first iteration where a classifier is trained by (1) testing some, but not all linear operators in the restricted set against a weighted version of the training set, (2) selecting for use by the classifier the linear operator with the lowest error rate, and (3) generating a re-weighted version of the training set. The iterations also include subsequent iterations during which another classifier is trained by repeating steps (1), (2), and (3), but using in step (1) the re-weighted version of the training set generated during a previous iteration.

Abstract: In an example embodiment, a method of identifying an item depicted in an image is provided. In this method, the image depicting the item is accessed; in addition, other images and their item identifiers are also accessed. A match of the image with one of the other images is identified. With a match, the image is then associated with an item identifier of the matched image.

Abstract: A biometric identification apparatus and method using bio signals and an artificial neural network, are provided. The biometric identification apparatus includes: a periodic signal extraction unit which extracts one or more periodic signals from an input bio signal; a template calculation unit which calculates a template value using the extracted periodic signals; a template storage unit which stores a plurality of template values corresponding to a plurality of living bodies; and a reading unit which reads the template value that is most approximate to the template value calculated by the template calculation unit from the template storage unit. Accordingly, it is possible to identify a living body by taking into consideration all of the characteristics of bio signals detected from the living body.

Abstract: A face recognition method, apparatus and system uses an architecture comprising multiple dual Linear Discriminant Analysis (LDA) transformations applied to coefficients of a frequency-based transformation applied to the facial image and its components. This new method significantly reduces extraction complexity compared to prior art and also offers increased robustness to face pose, illumination conditions and other factors, thus improving the recognition or authentication performance.

Abstract: A face image-output control device includes a face image detecting unit that detects a face image positioned in an approximately front direction from a target image and an output control unit that outputs the target image and a predetermined mark indicating that a face image of the target image can be printed as an identification photograph to a predetermined output target for a case where the face image positioned in an approximately front direction is detected by the face image detecting unit.

Abstract: Data set generation and data set presentation for image processing are described. The processing determines a location for each of one or more musical artifacts in the image and identifies a corresponding label for each of the musical artifacts, generating a training file that associates the identified labels and determined locations of the musical artifacts with the image, and presenting the training file to a neural network for training.

Abstract: A temporary self-organizing map in which classes are associated with respective vector points is first derived by a first learning section of a data learning apparatus. Thereafter, by use of, for example, an improved method incorporating concept of vicinity learning intp learning vector quantization, a second learning section modifies the temporary self-organizing map and obtains a final self-organizing map. By use of the final self-organizing map thus derived, image meaning determining processing is performed.

Abstract: A fire detection system has a video sensor, a processor, and a database. The database has a statistical model representing the characteristics of a fire. The video sensor captures images, and sends the images to the processor. The processor computes statistics on the characteristics of the captured image, and compares it to the statistical model to determine if a fire is present in the captured image.

Abstract: Designs for cognitive memory systems storing input data, images, or patterns, and retrieving it without knowledge of where stored when cognitive memory is prompted by query pattern that is related to sought stored pattern. Retrieval system of cognitive memory uses autoassociative neural networks and techniques for pre-processing query pattern to establish relationship between query pattern and sought stored pattern, to locate sought pattern, and to retrieve it and ancillary data.

Abstract: In an image enhancement method, a regular enhancement function and an aggressiveness parameter are computed using characteristics of a digital image. A first, relatively slow enhancement algorithm is applied to the digital image using the regular enhancement function, when an aggressiveness parameter is in a predetermined high range. A second, relatively fast enhancement algorithm is applied to the digital image using the regular enhancement function, when an aggressiveness parameter is in a predetermined low range. A modified enhancement function is calculated using characteristics of the digital image and is used with a second, relatively fast enhancement algorithm, when the aggressiveness parameter is in a predetermined medium range.

Abstract: A method and system for container identification are disclosed. The method comprises obtaining a plurality of digital images of a character sequence on the container, extracting the character sequences from the images, combining the character sequences into at least one identification code candidate, and selecting one of the candidates as the identification code. The system comprises at least one camera and a computer system that is electrically coupled to the camera, whereby when the computer system receives a trigger signal, said computer system takes a plurality of digital images from the camera, produces character sequences as partial recognition results for the plurality of digital images, and combines the partial recognition results together to produce the identification code.

Abstract: The present invention discloses methods and systems for discovering printers and shares on a computer network. Each domain on the network is identified, and each computer in the domain is identified. In addition, each printer connected to the computer and each share on the computer is identified. Shortcuts to the identified printers and shares are created on at least one computer on the network. Moreover, drivers are preferably installed on the computer for each printer for which a shortcut was created. In the event that the total number of resources (i.e., shares and/or printers) exceeds a threshold, then the process terminates. Otherwise, the present invention continues until all printers and shares on the network are identified, and the appropriate shortcuts are created. Thus, the present invention provides methods and systems for discovering resources on a network.

Abstract: A three-dimensional object recognizing system comprises a distance image generating portion for generating a distance image by using image pairs picked up by a stereoscopic camera, a grouping processing portion for grouping the distance data indicating the same three-dimensional object on the distance image, an input value setting portion for setting an area containing distance data group of grouped three-dimensional object on the distance image and also setting input values having typical distance data as elements every small area that is obtained by dividing the area by a set number of partition, a computing portion for computing output values having a pattern that responds to a previously set three-dimensional object by using a neural network that has at least the input values Xin as inputs to an input layer, and a discriminating portion for discriminating the type of the three-dimensional object based on the pattern of the output values.

Abstract: A method constructs a strong classifier from weak classifiers by combining the weak classifiers to form a set of combinations of the weak classifiers. Each combination of weak classifiers is boosted to determine a weighted score for each combination of weak classifiers, and combinations of weak classifiers having a weighted score greater than a predetermined threshold are selected to form the strong classifier.