Shriram V. Revankar

Multithresholding for document image segmentation

Document images contain information in several dominant intensity levels. Detecting these dominant levels helps segmenting the regions in the image that need to be processed differently, if subsequently the image was to be recognized or printed. In this paper we propose a multithresholding algorithm to segment different dominant intensity levels in a document image based on intensity histogram and intensity transition histograms of the image. The method involves determining the number of dominant intensity levels in the image and computing the necessary number of thresholds that facilitate the segmentation.

Computer methods in quantitation of cardiac wall parameters from two dimensional echocardiograms: a survey

With increasing use of two-dimensional echocardiograms (2DE) for diagnosis [1,2], efforts to computerize the process of quantification of cardiac parameters have increased. Visual processing of echocardiograms is time and labor intensive, and usually provides qualitative results with subjective variations [3]. In contrast, computer assisted methods are efficient and provide quantitative reproducible results. On the basis of the extent of computer usage, the 2DE processing methods are classified into three categories, namely, manual [9–30], interactive [32–49], and automatic methods [51–82]. This work is a structured survey of the published research on these three categories.

Picture, graphics, and text classification of document image regions

Various rendering techniques are being used for document reproduction and printing. Some rendering techniques work better for text, some for graphics and some others work better for picture regions. Therefore, dividing a document image into regions that need to be rendered differently from its neighboring regions is useful for good reproduction and printing. In this paper we describe a method to classify previously segmented regions of a page image into three classes, namely text, graphics and pictures. In addition to printing and copying, this classification of regions into broad basic classes is also useful for automatic storage and retrieval, and efficient communication of document images.

Constrained contouring in polar coordinates

A constrained contour is an outline of a region of interest, obtained by linking the possible edge points under the constraints of connectivity, smoothness, image context, and an externally specified approximate contour. A constrained contouring algorithm in polar coordinates that traces closed contours using their rough approximations is discussed. A set of locally optimal contour locations (LOCLs) is found in all the selected radial directions by analyzing the image features and the external constraints. A graph search based algorithm is used to select a smooth contour that passes through the maximum number of LOCLs.<<ETX>>

Mining the “Voice of the Customer” for Business Prioritization

To gain competitiveness and sustained growth in the 21st century, most businesses are on a mission to become more customer-centric. In order to succeed in this endeavor, it is crucial not only to synthesize and analyze the VOC (the VOice of the Customer) data (i.e., the feedbacks or requirements raised by customers), but also to quickly turn these data into actionable knowledge. Although there are many technologies being developed in this complex problem space, most existing approaches in analyzing customer requests are ad hoc, time-consuming, error-prone, people-based processes which hardly scale well as the quantity of customer information explodes. This often results in the slow response to customer requests. In this article, in order to mine VOC to extract useful knowledge for the best product or service quality, we develop a hybrid framework that integrates domain knowledge with data-driven approaches to analyze the semi-structured customer requests. The framework consists of capturing functional features, discovering the overlap or correlation among the features, and identifying the evolving feature trend by using the knowledge transformation model. In addition, since understanding the relative importance of the individual customer request is very critical and has a direct impact on the effective prioritization in the development process, we develop a novel semantic enhanced link-based ranking (SELRank) algorithm for relatively rating/ranking both customer requests and products. The framework has been successfully applied on Xerox Office Group Feature Enhancement Requirements (XOG FER) datasets to analyze customer requests.

Collaborative processing to extract myocardium from a sequence of two-dimensional echocardiograms

Echocardiography is an important clinical method for identification and assessment of the entire spectrum of cardiac diseases. Visual assessment of the echocardiograms is tedious and subjective, but on the other hand, owing to the poor quality of the data, the automatic techniques are unreliable. One can minimize these drawbacks through collaborative processing. The authors describe a collaborative method to extract the myocardium from a sequence of two-dimensional echocardiograms. Initially, a morphologically adaptive thresholding scheme generates a rough estimate of the myocardium, and then a collaborative scheme refines the estimate. The threshold is computed at each pixel as a function of the local morphology and a default threshold. The points that have echodensities greater than the threshold form a rough estimate of the myocardium. This is collaboratively refined in accordance with the corrections specified by the operator, through mouse gestures. The gestures are mapped on to an image processing scheme that decides the precise boundaries of the intended regions that are to be added to or deleted from the estimated myocardium.

An interactive thresholding scheme to extract myocardium from a sequence of two dimensional echocardiograms

The authors describe an interactive thresholding scheme to extract myocardium from a sequence of two dimensional echocardiograms (2DEs). An expert operator interactively picks a few points that are on the myocardium as the object points, and a few background points. The computer classifies the rest of the points of the image as myocardium or the background by comparing the echodensity at each point to a threshold which is computed as a function of the input points and their neighborhood echodensities. All the points with echodensities greater than the corresponding threshold form the myocardium and the rest form the background. This classification can be refined further by picking new sets of points at the misclassified regions.<<ETX>>

Supervised interpretation of echocardiograms with a psychological model of expert supervision

We have developed a collaborative scheme that facilitates active human supervision of the binary segmentation of an echocardiogram. The scheme complements the reliability of a human expert with the precision of segmentation algorithms. In the developed system, an expert user compares the computer generated segmentation with the original image in a user friendly graphics environment, and interactively indicates the incorrectly classified regions either by pointing or by circling. The precise boundaries of the indicated regions are computed by studying original image properties at that region, and a human visual attention distribution map obtained from the published psychological and psychophysical research. We use the developed system to extract contours of heart chambers from a sequence of two dimensional echocardiograms. We are currently extending this method to incorporate a richer set of inputs from the human supervisor, to facilitate multi-classification of image regions depending on their functionality. We are integrating into our system the knowledge related constraints that cardiologists use, to improve the capabilities of our existing system. This extension involves developing a psychological model of expert reasoning, functional and relational models of typical views in echocardiograms, and corresponding interface modifications to map the suggested actions to image processing algorithms.

Maximal detection of myocardium in echocardiograms for supervised refinement

A novel thresholding method to separate the myocardium of correct thickness from a sequence of two-dimensional echocardiograms is presented. The threshold is made adaptive by maintaining a constant wall width ratio throughout the image sequence. The width ratio is computed at an interactively indicated wall section where the wall width is known a priori. The method is well suited for detecting the heart walls in long axis views of the echocardiograms, but in general it can be used for detection or any striped object pattern.<<ETX>>

Selecting a threshold for two-dimensional echocardiograms

Thresholding has been extensively used to separate myocardium from two-dimensional echocardiograms. We present a critical review of the existing threshold-based methods, and propose a new interactive method that uses the known average wall thickness at the indicated region to determine a reference global threshold. The thickness of the wall as seen in the thresholded image is important for quantization of cardiac parameters such as ventricular volume, ejection fraction, etc. In echocardiograms, owing to the characteristics of the imaging environment, the cardiac wall thickness depends on the threshold. Many existing methods concentrate on extracting continuous wall regions. In our scheme we select a threshold that yields walls ofproper thickness, and then we attempt to obtain a continuous region. In our scheme, a userpicks two points on a clearly visible section of the wall where the thickness is known. We compute a threshold by analyzing the regionalhistogram at that wall section so that average thickness of the regional thresholded pattern is equal to the known wall thickness. This gives a reference threshold that is varied locally by regional three-dimensional morphology to obtain local thresholds. The thresholding scheme suppresses noise and generates smooth boundaries.