Abstract: Locating the region of interest (ROI) in the histogram of a digital radiographic image is a key component for the optimized presentation of the image, either in hardcopy or softcopy display. A method for locating the ROI first locates key candidate landmarks present in a particular body part radiographic image (i.e., chest pelvis, hand, etc.). Next, a library of spatially located landmarks are matched to the candidate landmarks and used to locate the region of interest in the radiograph using geometric techniques. The histogram of the selected region of interest is used to develop the final tonescale curve used to process the image.

Abstract: A method of processing a digital image comprising the steps of:providing an input digital image having an input size;providing the output size of a desired output digital image;inputting the provided input digital image and the provided desired output digital image size to a weight estimation sub-system which operates to generate several weight derivative estimates;inputting the provided input digital image to an x-direction derivative estimation sub-system which produces an array of x-direction derivative estimates;inputting the provided input digital image, the weight derivative estimates and the x-direction estimates to an x-direction interpolated value estimation subsystem which produces in intermediate digital image which has the same number of rows as said input digital image while having the same number of columns as said output digital image;operating on said intermediate digital image by a y-direction derivative estimation sub-system to produce y-direction derivative estimates;inputting the intermedi

Abstract: A method for enhancing a digital image comprises the following steps.1. Providing a digital image.2. Decomposing the image into a multiresolution representation having low frequency images and high frequency images.3. Performing dynamic range modification on the low frequency images.4. Modifying the high frequency images with a method incorporating noise estimation, anatomical regions of importance, and edge estimation, such modification being a combination of attenuation and amplification.5. Combining the processed resolution images to form a resulting image.6. Shifting the pixel values of the resulting image to map the values into a desired range.7. Applying a tonescale to the shifted image for display.

Abstract: The body part classification of a radiographic image is a key component of systems that produce an optimal tone scale curve for either hard copy or soft copy presentation. A method automatically determines the body part class based on a subset of relevant features and a probabilistic reasoning unit (PRU). The reasoning unit estimates the most probable body part class based on probabilistic information that associates a given class with the joint probability of the detection of a subset of features and their spatial relationships.

Abstract: A method for detecting grids in a digital image having a plurality of pixels for capturing an image, comprises the steps of performing a high pass filter operation on a sample of pixels for filtering out the image from the sampled pixels; and performing a statistical F-test operation on the results of the high pass filter operation for determining when the digital image contains grids.

Abstract: The text to be classified as a dot matrix or ink jet printer character is scanned at a suitable resolution. Several horizontal and vertical slices are made through the bitmap image of individual characters. Density values of pixels contained in these slices are stored as a density profile for each slice. As a result of these density profiles, a determination is made as to whether or not the character was printed on a dot matrix or ink jet printer, or whether the characters were printed using a higher quality device such as a daisy wheel printer.

Abstract: Methods and apparatus for constructing a classification weights matrix for a pattern recognition system are provided which enable large system feature sets to be reduced and yield at least the same level of performance achieved using the large feature set. Methods and apparatus are also described for determining (evaluating) the classification efficiency of selected subsets of a given feature set. Further aspects of the invention are directed to: (a) methods and apparatus for constructing reduced element classification weights matrices utilizing a genetic search process to find the subset having a maximum classification efficiency; and (b) pattern recognition systems (including, in particular, character identification systems), which utilize classifiers constructed in accordance with the aforementioned aspects of the invention to actually perform pattern recognition.

Abstract: A method and apparatus for performing cursive script recognition is disclosed, wherein a cursive word, in the form of digitized data or bitmap, is simultaneously segmented and individual characters of the word are recognized using a scanning window that moves across a word field or segment. The bitmap data is preprocessed before being presented to a moving window letter center finding neural network that determines the spatial location of the centers of individual letters. Character center data generated by the center finding neural network is then used to define the left and right edges of a fixed size window. The fixed window contains width normalized word segments that are presented to a second neural network which is taught to recognize the central character of the window based on portions of adjacent characters contained within the window.

Abstract: An image processing technique especially useful in processing digital radiographic images. A method for finding a histogram region of interest for improved tone scale reproduction of digital radiographic images includes the following steps. A digital radiographic image is randomly sampled with a sample having an appropriate size to delineate an object of interest. Each sample is processed using texture analysis techniques to extract a plurality of texture features. Using the extracted texture features, each sample is classified with a previously trained neural network classifier to determine its class. Last, the pixel values belonging to the same class are accumulated to form separate histograms for each class. Each of the histograms are then used to optimize tone scale reproduction.

Abstract: An electronic organizer is provided that incorporates an internal electronic scanner and a touch sensitive display screen to enter text and image data. The internal electronic scanner permits both machine generated text and image data to be scanned and directly entered into the electronic organizer. Hand-printed text data is also entered directly via the touch sensitive display screen using a stylus or pen. The scanned machine generated text, the scanned image data and the hand-printed text can either be preserved as an image-oriented bit map, or optical character recognition routines can be applied to the data to identify characters and convert the identified characters to computer coded text data. Data entered into the electronic organizer is arranged in a relational database format, which permits the operator to quickly and easily enter and retrieve related information between a number of different databases with a minimal amount of effort.

Abstract: Character segmentation apparatus for an optical character recognition system for segmenting individual character images in an image of a document having many characters prior to performing character identification, including a movable kernel for capturing a sub-image framed within a window having an area corresponding to an area occupied by an individual character, the window being movable in the document image in pixel-by-pixel steps to capture a sub-image for each step of the window, an associative memory for responding to the captured sub-image by producing a corresponding one of a set of images of known characters with which the associative memory has been trained, and a sensor responsive to the behavior of the associative memory for determining whether the sub-image is the image of an individual character or a non-character.

Abstract: Method and apparatus are disclosed for processing image data of dot-matrix/ink-jet printed text to perform Optical Character Recognition (OCR) of such image data. In the method and apparatus, the image data is viewed for detecting if dot-matrix/ink-jet printed text is present. Any detected dot-matrix/ink-jet produced text is then pre-processed by determining the image characteristic thereof by forming a histogram of pixel density values in the image data. A 2-D spatial averaging operation as a second pre-processing step smooths the dots of the characters into strokes and reduces the dynamic range of the image data. The resultant spatially averaged image data is then contrast stretched in a third pre-processing step to darken dark regions of the image data and lighten light regions of the image data. Edge enhancement is then applied to the contrast stretched image data in a fourth pre-processing step to bring out higher frequency line details.

Abstract: In an optical character recognition system, character strokes are automatically enhanced prior to processing by matching the character bit map with a set of templates. Each template has a stripe of thickness W composed of binary ones surrounded by zeroes along a horizontal, vertical, major diagonal or minor diagonal direction. If the template matches a character stroke to a predetermined degree, the stroke is enhanced by increasing its thickness to a predetermined number N of binary ones.

Abstract: Apparatus, and an accompanying method, for a neural network, particularly one suited for use in optical character recognition (OCR) systems, which through controlling back propagation and adjustment of neural weight and bias values through an output confidence measure, smoothly, rapidly and accurately adapts its response to actual changing input data (characters). Specifically, the results of appropriate actual unknown input characters, which have been recognized with an output confidence measure that lies within a pre-defined range, are used to adaptively re-train the network during pattern recognition. By limiting the maximum value of the output confidence measure at which this re-training will occur, the network re-trains itself only when the input characters have changed by a sufficient margin from initial training data such that this re-training is likely to produce a subsequent noticeable increase in the recognition accuracy provided by the network.

Abstract: Vertically segmented characters are pre-processed for optical character recognition so as to remove skew and noise by convolution with a mask consisting of parallel vertical lines with a one-pixel spatial frequency. The horizontal alignment of the mask with respect to each segmented character is adjusted until a maximum cross-correlation is found. Then, the product of the mask and the character image is formed. A histogram of the number of pixels in the product image along each vertical line of the mask is compared with a library of such histograms of known symbols and the best match identifies the symbol represented by the character image. Alternatively, the histogram is converted to a binary codeword which is compared with a library of such codewords corresponding to a set of known symbols.

Abstract: Character images which are to be sent to a neural network trained to recognize a predetermined set of symbols are first processed by an optical character recognition pre-processor which normalizes the character images. The output of the neural network is processed by an optical character recognition post-processor. The post-processor corrects erroneous symbol identifications made by the neural network. The post-processor identifies special symbols and symbol cases not identifiable by the neural network following character normalization. For characters identified by the neural network with low scores, the post-processor attempts to find and separate adjacent characters which are kerned and characters which are touching. The touching characters are separated in one of nine successively initiated processes depending upon the geometric parameters of the image.

Abstract: A library of templates defining the spacings between pre-printed lines and the corresponding line lengths for a plurality of different business forms is compared with the image data of an unknown document to determine the known business form (template) to which the document corresponds. Once the form of the document is determined, the optical character recognition system may intelligently associate the text characters in certain locations on the document with information fields defined by the pre-printed lines. The pre-printed lines in the image data are determined from the corresponding template and removed from the image data prior to optical character recognition processing.

Abstract: Character stroke is strengthened by processing video image data with a 16.times.16 kernal, and moving the kernal one pixel at a time through the image. For each pixel position, sections of the kernal, are selectively filled with black pixels in proportion to the number of black pixels in each section, in accordance with a set of predetermined rules.