Eastman-kodak Company

Roger S Gaborski

Lori L Barski

Thaddeus Francis Pawlicki

Ben K Jang

Andrew M Assad

Robert Allen Senn

Louis J Beato

Christopher T Asbury

Richard Lawrence VanMetter

Robert H Philbrick

Hin-Leong Tan

Patricia D Snyder

Peter G Anderson

Kenneth G Corl

J Terrence Flynn

Jay B Soper

Carl W Schlack

Olorunfunmi A Oliyide

Dawn L Dutton

Yuan-Ming Fleming Lure

David G Tilley

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.

Technique for finding the histogram region of interest based on landmark

A method of processing a digital image comprising the steps of:

Method for resizing of a digital image

A method for enhancing a digital image comprises the following steps.

Image enhancement in digital image processing

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.

Body part recognition in radiographic images

The present invention efficiently and quickly estimates signal (code value) dependant noise in an image and subsequently reduces that noise. The digital image is segmented both according to code value and into smooth vs. textured regions. Noise estimates taken from smooth regions are used to model noise as a function of code value. The predictions of the model are used to tone noise reduction in all areas of the image according to the appropriate code value.

Apparatus and method for signal dependent noise estimation and reduction

An automated method and system for determining the positional orientation of radiographic images, wherein digital image data is acquired and subjected to multiple phases of digital imaging processing. The image is processed to segment the object of interest, i.e., a body region, from the foreground and background of the image. Next, the center is determined for the body region. The body region center is then positioned so that it coincides with the center of the film or medium. The image is subsequently decomposed into one or more horizontal and vertical strips. Feature extraction is performed on these strips to preliminarily determine the orientation of the image. Finally, a set of rules is applied to the image information described above to determine the positional orientation of the image.

Automated method and system for determination of positional orientation

An automated method and system for digital imaging processing of radiologic images, wherein digital image data is acquired and subjected to multiple phases of digital imaging processing. During the Pre-Processing stage, simultaneous box-rim filtering and k-nearest neighbor processing and subsequent global thresholding are performed on the image data to enhance object-to-background contrast, merge subclusters and determine gray scale thresholds for further processing. Next, during the Preliminary Selection phase, body part segmentation, morphological erosion processing, connected component analysis and image block segmentation occurs to subtract unwanted image data preliminarily identify potentials areas including abnormalities. During the Pattern Classification phase, feature patterns are developed for each area of interest, a supervised, back propagation neural network is trained, a feed forward neural network is developed and employed to detect true and several false positive categories, and two types of pruned neural networks are utilized in connection with a heuristic decision tree to finally determine whether the regions of interest are abnormalities or false positives.

Automated method and system for digital image processing of radiologic

A method of identifying tissue regions in a digital image representing a body part provides a digital image representing a body part having tissue regions. The digital image is scaled by subsampling or interpolation, and texture extraction is applied to the scaled image to produce a plurality of texture images each having a different measure of the image texture. The texture images are clustered, and the clustered image is labeled based on both pixel intensity values and geometric adjacency of pixels. A threshold is applied to the labeled image, which is then filtered using a largest component filter system to determine the largest geometrically connected region in the threshold image. The filtered image is subjected to edge detection to produce an edge image containing only edge pixels at high code value, and the edge image is operated on to produce a convex hull image which outlines the skin line of the tissue region of the body part provided in the digital image.

Apparatus and method for identification of tissue regions in digital

A method of automatically segmenting the bone regions in a digital radiograph of a body extremity comprising the steps of: providing a digital radiographic image of a body extremity having one or more digits; estimating the upper and lower threshold values of the provided image; binarizing the provided image by a binarization system which uses the estimated upper and lower threshold values to produce a bi-tonal image; removing noise from the binarized image by a noise removal system; processing the noise removed binary image by a skeletonization technique in order to form an initial estimate of the central axis of each body extremity digit; approximating the locus of points generated by the processing step by a linear fit system; joining lines with near end points with a line linking system which results in a piece wise linear approximation of the central axis for each body extremity digit; for each point along the axes, generating perpendicular projections which extend a fixed pixel distance; for each perpendicular projection, averaging the pixel values by a trace generation system; convolving each density trace with a matched filter; analyzing the output of the matched filter step by a joint detection system to locate digit joints; for each body extremity digit, determining the bone edges between two joints; and determining the average density of the digit region between the digit joints and bone edges.

Apparatus and method for identifying specific bone regions in digital

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.

Method and system for detecting grids in a digital image

A character bit map is skeletonized using competitive locally independent processes (CLIPs) by defining for each foreground pixel an individual CLIP with a center location and radius defining the pixels included in the CLIP. In iterative cycles, each CLIP varies its center location and radius over predetermined ranges to produce a predetermined number of permutations thereof, computes a trial fitness value for each permutation, the trial fitness value being rewarded and penalized in accordance with foreground and background pixels included in the CLIP and penalized for each pixel included in both the CLIP and in another CLIP of greater fitness value. Each CLIP adopts the maximum trial fitness value as its next fitness value along with the corresponding center location and radius. Each CLIP is eliminated if its next fitness value falls below a predetermined minimum value. Whenever an iterative cycle fails to produce a change in the number or radii of the CLIPs greater than a predetermined threshold, the center locations of all surviving CLIPs are output as a skeleton character map.

Character thinning using emergent behavior of populations of competitive

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.

Method for detecting ink jet or dot matrix printing

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.

Constructing classification weights matrices for pattern recognition

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. A final character recognition decision is made using a third neural network that combines the results of second neural network at three positions, namely, when the character to be recognized was in a precharacter position, a central position and a post character position relative to the third neural network.

Method and apparatus for cursive script recognition

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.

Growing community of inventors

Pittsford, NY, United States of America

Roger S Gaborski