Abstract: A computerized rating tool is described that assists a user in efficiently and consistently assigning expert ratings (i.e., labels) to a large collection of training images representing samples of a given product. The rating tool provides mechanisms for visualizing the training images in an intuitive and configurable fashion, including clustering and ordering the training images. In some embodiments, the rating tool provides an easy-to-use interface for exploring multiple types of defects represented in the data and efficiently assigning expert ratings. In other embodiments, the computer automatically assigns ratings (i.e., labels) to the individual clusters containing the large collection of digital images representing the samples.

Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7 T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.

Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.

Abstract: A system is described for detecting the presence of non-uniformity patterns and providing output indicative of a severity of each type of non-uniformity pattern. The system includes a computerized rating tool that assists a user in efficiently and consistently assigning expert ratings (i.e., labels) to a large collection of training images representing samples of a given product. In addition, the rating software develops a model that allows a computerized inspection system to detect the presence of non-uniformity patterns in a manufactured web material in real time and provide output indicative of a severity level of each pattern on a continuous scale. The system also includes algorithmic and hardware approaches to significantly that increase the throughput of the inspection system.

Abstract: A computerized inspection system is described for detecting the presence of non-uniformity defects and providing output indicative of a severity of each type of non-uniformity defect. Techniques are described that increase the throughput of the inspection system. Algorithmic and hardware approaches are described to significantly decrease the average amount of time required to inspect a given quantity of material that is expected to be mostly uniform. The techniques described herein involve dynamic selection of which image features to compute by starting with a base feature set and only triggering additional feature computations as needed until the features are sufficient to compute a severity for each type of non-uniformity defect. The number of features extracted and the order in which the features are extracted is dynamically determined in real-time to reduce a cost associated with the feature extraction.

Abstract: A computerized inspection system is described for detecting the presence of non-uniformity defects in a manufactured web material and for providing output indicative of a severity level of each defect. The system provides output that provides the severity levels of the non-uniformity defects in real-time on a continuous scale. Training software processes a plurality of training samples to generate a model, where each of the training samples need only be assigned one of a set of discrete rating labels for the non-uniformity defects. The training software generates the model to represent a continuous ranking of the training images, and the inspection system utilizes the model to compute the severity levels of the web material on a continuous scale in real-time without limiting the output to the discrete rating labels assigned to the training samples.

Abstract: A computerized rating tool is described that assists a user in efficiently and consistently assigning expert ratings (i.e., labels) to a large collection of training images representing samples of a given product. The rating tool provides mechanisms for visualizing the training images in an intuitive and configurable fashion, including clustering and ordering the training images. In some embodiments, the rating tool provides an easy-to-use interface for exploring multiple types of defects represented in the data and efficiently assigning expert ratings. In other embodiments, the computer automatically assigns ratings (i.e., labels) to the individual clusters containing the large collection of digital images representing the samples.

Abstract: Images are colorized, recolorized, or otherwise manipulated by adding scribbles of a blending medium (such as chrominance) to a measurement medium (such as luminance) of the image. The blending medium propagates from the scribbles according to an intrinsic or geodesic distance that is a function of the measurement medium. Intrinsic distances may be weighted. An effect scribble may produce an effect, such as result data, in the blending medium according to a predefined function. A preprocessing scribble may be converted to one or more effect scribbles which are then propagated. A measurement scribble may propagate so as to alter the intrinsic distances of other scribbles.

Abstract: Images are colorized, recolorized, or otherwise manipulated by adding scibbles of a blending medium (such as chrominance) to a measurement medium (such as luminance) of the image. The blending medium propagates from the scribbles according to an intrinsic or geodesic distance that is a function of the measurement medium. Intrinsic distances may be weighted. An effect scribble may produce an effect, such as result data, in the blending medium according to a predefined function. A preprocessing scribble may be converted to one or more effect scribbles which are then propagated. A measurement scribble may propagate so as to alter the intrinsic distances of other scribbles.

Abstract: An image compression system having a causal, context-based, single-pass adaptive filter encoder that encodes pixel values using multiple context-based threshold values. In the general case, the threshold value is a function of the context of a pixel being encoded. In one specific embodiment one threshold value is used in non-run mode contexts and another threshold value is used in run mode contexts. A single threshold decompressor may decode images encoded using the multi-threshold encoder of the invention. Other systems and methods are disclosed.

Abstract: A lossless image compression encoder/decoder system having a context determination circuit and a code table generator. The image compressor uses the context of a pixel to be encoded to predict the value of the pixel and determines a prediction error. The image compressor contains a context quantizer that quantizes the context of pixels. The image compressor counts the error values for each quantized context and uses these counts to generate context-specific coding tables for each quantized context. As it encodes a particular pixel, the encoder looks up the prediction error in the context-specific coding table for the context of the pixel and encodes that value. To decompress an image, the decompressor determines and quantizes the context of each pixel being decoded. The decompressor uses the same pixels as the compressor to determine the context. The decompressor retrieves from the context-specific coding table the error value corresponding to the coded pixel.

Abstract: A lossless image compression encoder/decoder system having a context determination circuit and a code table generator. The image compressor uses the context of a pixel to be encoded to predict the value of the pixel and determines a prediction error. The image compressor contains a context quantizer that quantizes the context of pixels. The image compressor counts the error values for each quantized context and uses these counts to generate context-specific coding tables for each quantized context. As it encodes a particular pixel, the encoder looks up the prediction error in the context-specific coding table for the context of the pixel and encodes that value. To decompress an image, the decompressor determines and quantizes the context of each pixel being decoded. The decompressor uses the same pixels as the compressor to determine the context. The decompressor retrieves from the context-specific coding table the error value corresponding to the coded pixel.