Automated classification of brain tumor type in whole-slide digital pathology images using local representative tiles.

https://hal.univ-reims.fr/hal-01694418/document

Grey-level hit-or-miss transforms-Part I: Unified theory

https://hal.archives-ouvertes.fr/hal-00512734/document

A hit-or-miss transform for multivariate images

The usefulness of the hit-miss transform (HMT) and re- lated transforms for pattern matching in document image applica- tions is examined. Although the HMT is sensitive to the types of noise found in scanned images, including both boundary and ran- dom noise, a simple extension, the blur HMT, is relatively robust. The noise immunity of the blur HMT derives from its ability to treat both types of noise together, and to remove them by appropriate dilations. In analogy with the Hausdorff metric for the distance be- tween two sets, metric generalizations for special cases of the blur HMT are derived. Whereas Hausdorff uses both directions of the directed distances between two sets, a metric derived from a special case of the blur HMT uses just one direction of the directed dis- tances between foreground and background components of two sets. For both foreground and background, the template is always the first of the directed sets. A less-restrictive metric generalization, where the disjoint foreground and background components of the template need not be set complements, is also derived. For images with a random component of noise, the blur HMT is sensitive only to the size of the noise, whereas Hausdorff matching is sensitive to its location. It is also shown how these metric functions can be derived from the distance functions of the foreground (FG) and background (BG) of an image, using dilation by the appropriate templates. The blur HMT can be used as a fast heuristic to avoid more expensive integer-based matching techniques, and it is implemented efficiently with boolean image operations. The FG and BG images are dilated with structuring elements that depend on image noise and pattern variability, and the results are then eroded with templates derived from patterns to be matched. Subsampling the patterns on a regular grid can improve speed and maintain match quality, and examples are given that indicate how to explore the parameter space. Trun- cated matches give the same result as full erosions, are much faster, and for some applications can be performed at a restricted set of locations. © 2000 SPIE and IS&T. (S1017-9909(00)00802-3)

/pdf/pattern-matching-using-the-blur-hit-miss-transform-2qtpto9mah.pdf

Pattern matching using the blur hit-miss transform

The hit-or-miss transform (HMT) is a well-known morphological transform capable of identifying features in digital images. When image features contain noise, texture, or some other distortion, the HMT may fail. Various researchers have extended the HMT in different ways to make it more robust to noise. The most successful, and most recent extensions of the HMT for noise robustness, use rank-order operators in place of standard morphological erosions and dilations. A major issue with the proposed methods is that no technique is provided for calculating the parameters that are introduced to generalize the HMT, and, in most cases, these parameters are determined empirically. We present here, a new conceptual interpretation of the HMT which uses a percentage occupancy (PO) function to implement the erosion and dilation operators in a single pass of the image. Further, we present a novel design tool, derived from this PO function that can be used to determine the only parameter for our routine and for other generalizations of the HMT proposed in the literature. We demonstrate the power of our technique using a set of very noisy images and draw a comparison between our method and the most recent extensions of the HMT.

/pdf/a-new-design-tool-for-feature-extraction-in-noisy-images-2x1if9xt09.pdf

A New Design Tool for Feature Extraction in Noisy Images Based on Grayscale Hit-or-Miss Transforms

A morphological hit-or-miss algorithm is presented which can distinguish a distorted shape from among others and locate it. Shape recognition is presented in noisy environments as a problem of recognizing imperfect shapes. The method employs only one hit-or-miss operation. The resultant shape location is presented by a small cluster of points within a known set. The role of window W in the hit-or-miss transformation is discussed, and it is shown that the boundary of the complement of the shape, delta A/sup c/, can be used as a structuring element on the complement of the image, I/sup c/, with the result of the hit-or-miss transformation being the same as that when a window is used in the transformation. Without a window restriction, the hit-or-miss transformation is more practical in shape recognition. >

Shape recognition using morphological transformations

Automated shape recognition in two dimensions is analyzed, and an efficient approach is provided to reduce the redundancy of the matching process. Shape recognition is achieved through locating the objects to be recognized within the field of view. Two theorems are presented. The first theorem is applied to the shape-recognition problem and indicates a clear advantage in reducing the redundancy involved in the matching process when morphological operations are used. Experiments show that a large amount of computing time is saved as a consequence of this theorem. This theorem also offers advantages when performing automated shape recognition on images acquired in a noisy environment. The second theorem suggests that edges of shapes can be used as a structuring element, and all possible outcomes due to noisy environments need to be exhausted. >

D.G. Daut

Papers

Shape recognition using morphological transformations

An efficient approach to automatic shape recognition