Automatically generated HTML, as produced by WYSIWYG programs, typically contains much repetitive and unnecessary markup. Thispaper identifies aspects of such HTML that may be altered whileleaving a semantically equivalent document, and proposes techniques to achieve optimizing modifications. These techniques include attribute re-arrangement via dynamic programming, the use of style classes, and dead-coderemoval. These techniques produce documents as small as 33% of original size. The size decreases obtained are still significant when the techniques are used in combination with conventional text-based compression.

This paper describes an efficient and effective image similarity calculation method for object-based image comparison at the level of object classes. It uses probabilistic-prediction voting based on the predicted class distribution of each segment of the contour of an object in an image to determine the class of the object. The C4.5 inductive learning algorithm is used to predict the class distribution of object-contour segments. This method is invariant to rotation, scaling and translation of objects. Experimental results show that the method is effective and efficient. It can be used for object-based image retrieval.

The authors present two new corner detectors. One works by using dissimilarity, along the contour direction to detect curves in the image contour, and the other estimates image curvature along the contour direction. These operators are fast, robust to noise, and require no subjective thresholding.>

Two corner detectors are presented, one of which works by testing similarity of image patches along the contour direction to detect curves in the image contour, and the other of which uses direct estimation image curvature along the contour direction. The operators are fast, robust to noise, and self-thresholding. An interpretation of the Kitchen-Rosenfeld corner operator is presented which shows that this operator can also be viewed as the second derivative of the image function along the edge direction.>

There are two basic ways to improve the speed of a low-level vision algorithm: careful code optimization and selective processing. Reducing the computational effort expended on each pixel reduces the time required to process an image by a constant factor. Selective processing on a limited portion of an image using a focus of attention can decrease overall computation by orders of magnitude. A fast pixel-based algorithm is developed that uses these principles to achieve fast extraction of lines for use in vision-guided mobile robot navigation. It builds upon an algorithm for extracting lines by grouping pixels with similar gradient orientation. It allows parametric control of computational resources required to extract lines with particular characteristics.>

Multispectral images can be effectively smoothed by using the global distribution of pixel values to guide a local selective averaging process. After several iterations of this process, a typical image is virtually segmented into regions of constant value while significant edges in the image are preserved.

A method of evaluating edge detector output is proposed, based on the local good form of the detected edges. It combines two desirable qualities of well-formed edges-good continuation and thinness. It yields results generally similar to those obtained with measures based on discrepancy of the detected edges from their known ideal positions, but it has the advantage of not requiring ideal positions to be known. It can be used as an aid to threshold selection in edge detection (pick the threshold that maximizes the measure), as a basis for comparing the performances of different detectors, and as a measure of the effectiveness of various types of preprocessing operations facilitating edge detection.