Its'hak Dinstein

Textural Features for Image Classification

Texture is one of the important characteristics used in identifying objects or regions of interest in an image, whether the image be a photomicrograph, an aerial photograph, or a satellite image. This paper describes some easily computable textural features based on gray-tone spatial dependancies, and illustrates their application in category-identification tasks of three different kinds of image data: photomicrographs of five kinds of sandstones, 1:20 000 panchromatic aerial photographs of eight land-use categories, and Earth Resources Technology Satellite (ERTS) multispecial imagery containing seven land-use categories. We use two kinds of decision rules: one for which the decision regions are convex polyhedra (a piecewise linear decision rule), and one for which the decision regions are rectangular parallelpipeds (a min-max decision rule). In each experiment the data set was divided into two parts, a training set and a test set. Test set identification accuracy is 89 percent for the photomicrographs, 82 percent for the aerial photographic imagery, and 83 percent for the satellite imagery. These results indicate that the easily computable textural features probably have a general applicability for a wide variety of image-classification applications.

New maximum likelihood motion estimation schemes for noisy ultrasound images

When performing block-matching based motion estimation with the ML estimator, one would try to match blocks from the two images, within a predefined search area. The estimated motion vector is that which maximizes a likelihood function, formulated according to the image formation model. Two new maximum likelihood motion estimation schemes for ultrasound images are presented. The new likelihood functions are based on the assumption that both images are contaminated by a Rayleigh distributed multiplicative noise. The new approach enables motion estimation in cases where a noiseless reference image is not available. Experimental results show a motion estimation improvement with regards to other known ML estimation methods.

Geometric separation of partially overlapping nonrigid objects applied to automatic chromosome classification

A common task in cytogenetic tests is the classification of human chromosomes. Successful separation between touching and overlapping chromosomes in a metaphase image is vital for correct classification. Current systems for automatic chromosome classification are mostly interactive and require human intervention for correct separation between touching and overlapping chromosomes. Since chromosomes are nonrigid objects, special separation methods are required to segregate them. Common methods for overlapping chromosomes separation between touching chromosomes tend to fail where ambiguity or incomplete information are involved, and so are unable to segregate overlapping chromosomes. The proposed approach treats the separation problem as an identification problem, and, in this way, manages to segregate overlapping chromosomes. This approach encompasses low-level knowledge about the objects and uses only extracted information, therefore, it is fast and does not depend on the existence of a separating path. The method described in this paper can be adopted for other applications, where separation between touching and overlapping nonrigid objects is required.

DCT/DST alternate-transform image coding

An image coding method for low bit rates is proposed. It is based on alternate use of the discrete cosine transform (DCT) and the discrete sine transform (DST) on image blocks. This procedure achieves the removal of redundancies in the correlation between neighboring blocks as well as the preservation of continuity across the block boundaries. An outline of the mathematical justification of the method, assuming a certain first-order Gauss-Markov model, is given. The resulting coding method is then adapted to nonstationary real images by locally adapting the model parameters and improving the block classification technique. Simulation results are shown and compared with the performance of related previous methods, namely adaptive DCT and fast Karhunen-Loeve transform (FKLT). >

On stereo image coding

An approach to stereo image compression based on disparity compensation is proposed and evaluated. The scheme is motivated by the suppression theory in human vision. A methodology for evaluating compressed stereo images is proposed. It is based on time measurements of depth perception tasks performed by human subjects. Subjects taking part in the experiment were exposed to displays of stereo images, some of which had been compressed, and were asked to judge the relative depth within each display as fast as possible. Decision times were measured and used as the major dependent variable. It was found that very deep compression of one of the images of a stereo pair does not interfere with the perception of depth in the stereo image.<<ETX>>

Binarization, character extraction, and writer identification of historical Hebrew calligraphy documents

We present our work on the paleographic analysis and recognition system intended for processing of historical Hebrew calligraphy documents. The main goal is to analyze documents of different writing styles in order to identify the locations, dates, and writers of test documents. Using interactive software tools, a data base of extracted characters has been established. It now contains about 20,000 characters of 34 different writers, and will be distinctly expanded in the near future. Preliminary results of automatic extraction of pre-specified letters using the erosion operator are presented. We further propose and test topological features for handwriting style classification based on a selected subset of the Hebrew alphabet. A writer identification experiment using 34 writers yielded 100% correct classification.

A spatial clustering procedure for multi-image data

A spatial clustering procedure applicable to multispectral image data is discussed. The procedure takes into account the spatial distribution of the measurements as well as their distribution in measurement space. The procedure calls for the generation and then thresholding of the gradient image, cleaning the thresholded image, labeling the connected regions in the cleaned image, and clustering the labeled regions. An experiment was carried out on ERTS data in order to study the effect of the selection of the gradient image, the threshold, and the cleaning process. Three gradients, three gradient thresholds, and two cleaning parameters yielded 18 gradient-thresholds combinations. The combination that yielded connected homogeneous regions with the smallest variance was Roberts gradient with distance 2, thresholded by its running mean, and a cleaning process that considered a resolution cell to be homogeneous if and only if at least 7 of its nearest neighbors were homogeneous.

Line Segmentation for Degraded Handwritten Historical Documents

We propose a novel approach for text line segmentation based on adaptive local projection profiles. Our algorithm is suitable for degraded documents with text lines written in large skew. The main novelty of our approach is applying the local algorithm in an incremental manner that adapts to the skew of each text line as it progresses. The proposed approach achieves very accurate results on a set of degraded documents with lines written in different skew angles and curvatures.

An algorithm for polygonal approximation based on iterative point elimination

A simple and fast algorithm for polygonal approximation of digital curves is proposed. The algorithm is based on a greedy iterative elimination of a point with the currently minimal error value. The error criterion is defined such that the elimination of a curve point requires the update of the error associated only with its two neighbors. The use of a heap data-structure yields a worst case complexity of O(n log n). The algorithm is independent of the starting point.

Medial axis transform-based features and a neural network for human chromosome classification

Abstract Medial axis transform (MAT) based features and a multilayer perceptron (MLP) neural network (NN) were used for human chromosome classification. Two approaches to the MAT, one based on skeletonization and the other based on a piecewise linear (PWL) approximation, were examined. The former yielded a finer medial axis, as well as better chromosome classification performances. Geometrical along with intensity-based features were extracted and tested. The probability of correct training set classification of five chromosome types was 99.3–99.6%. The probability of correct test set classification was greater than 98% and greater than 97% using features extracted by the first and second approaches, respectively. It was found that only 5–10, out of all the considered features, were required to correctly classify the chromosomes with almost no performance degradation.