Walter G. Kropatsch

Comparison of three-dimensional surface-imaging systems

BACKGROUND In recent decades, three-dimensional (3D) surface-imaging technologies have gained popularity worldwide, but because most published articles that mention them are technical, clinicians often have difficulties gaining a proper understanding of them. This article aims to provide the reader with relevant information on 3D surface-imaging systems. In it, we compare the most recent technologies to reveal their differences. METHODS We have accessed five international companies with the latest technologies in 3D surface-imaging systems: 3dMD, Axisthree, Canfield, Crisalix and Dimensional Imaging (Di3D; in alphabetical order). We evaluated their technical equipment, independent validation studies and corporate backgrounds. RESULTS The fastest capturing devices are the 3dMD and Di3D systems, capable of capturing images within 1.5 and 1 ms, respectively. All companies provide software for tissue modifications. Additionally, 3dMD, Canfield and Di3D can fuse computed tomography (CT)/cone-beam computed tomography (CBCT) images into their 3D surface-imaging data. 3dMD and Di3D provide 4D capture systems, which allow capturing the movement of a 3D surface over time. Crisalix greatly differs from the other four systems as it is purely web based and realised via cloud computing. CONCLUSION 3D surface-imaging systems are becoming important in todays plastic surgical set-ups, taking surgeons to a new level of communication with patients, surgical planning and outcome evaluation. Technologies used in 3D surface-imaging systems and their intended field of application vary within the companies evaluated. Potential users should define their requirements and assignment of 3D surface-imaging systems in their clinical as research environment before making the final decision for purchase.

The generation of SAR layover and shadow maps from digital elevation models

As almost fully automated techniques as well as expert systems obtain more and more importance in the geocoding of synthetic aperture radar (SAR) images, the solution to the problem of the identification of homologue points between the SAR image and reference system moves into the fields of pattern recognition and feature matching. Shadow regions, which appear as dark regions in the SAR image, are independent from the backscattering of the imaged terrain. Due to the multiplicity of signals, layover regions appear brighter than the surrounding regions. Hence, the phenomena of layover and shadow are stressed in the present paper. The reasons for their occurrence are studied through the digital elevation model representing the Earths surface. An algorithm to define layover and shadow regions directly in the geometry of the digital elevation model is presented. The results are given in a so-called layover and shadow map. >

Segmentation graph hierarchies

The region’s internal properties (color, texture, ...) help to identify them and their external relations (adjacency, inclusion, ...) are used to build groups of regions having a particular consistent meaning in a more abstract context. Low-level cue image segmentation in a bottom-up way, cannot and should not produce a complete final “good” segmentation. We present a hierarchical partitioning of images using a pairwise similarity function on a graph-based representation of an image. The aim of this paper is to build a minimum weight spanning tree (MST) of an image in order to find region borders quickly in a bottom-up ’stimulus-driven’ way based on local differences in a specific feature.

Content based image retrieval using interest points and texture features

Content based image retrieval is the task of searching images from a database, which are visually similar to a given example image. We present methods for content based image retrieval based on texture similarity using interest points and Gabor features. Interest point detectors are used in computer vision to detect image points with special properties, which can be geometric (corners) or non-geometric (contrast etc.). Gabor functions and Gabor filters are regarded as excellent tools for feature extraction and texture segmentation. The article combines these methods and generates a textural description of images. Special emphasis is devoted to distance measures on texture descriptions. Experimental results of a query system are given.

TRAVELING SALESMAN PROBLEM: A FOVEATING PYRAMID MODEL

We tested human performance on the Euclidean Traveling Salesman Problem using problems with 6–50 cities. Results confirmed our earlier findings that: (a) the time of solving a problem is proportional to the number of cities, and (b) the solution error grows very slowly with the number of cities. We formulated a new version of a pyramid model. The new model has an adaptive spatial structure, and it simulates visual acuity and visual attention. Specifically, the model solves the E-TSP problem sequentially by moving attention from city to city, the same way human subjects do. The model includes a parameter representing the magnitude of local search. This parameter allows modeling individual differences among the subjects. The computational complexity of the current implementation of the model is O(n 2 ), but this can most likely be improved to O[nlog(n)]. Simulation experiments demonstrated psychological plausibility of the new model.

Vision pyramids that do not grow too high

In irregular pyramids, their vertical structure is not determined beforehand as in regular pyramids. We present three methods, all based on maximal independent sets from graph theory, with the aim to simulate the major sampling properties of the regular counterparts: good coverage of the higher resolution level, not too large sampling gaps and, most importantly, the resulting height, e.g. the number of levels to reach the apex. We show both theoretically and experimentally that the number of vertices can be reduced by a factor of 2.0 at each level. The plausibility of log (diameter) pyramids is supported by psychological and psychophysical considerations. Their technical relevance is demonstrated by enhancing appearance-based object recognition. An irregular pyramid hypothesis generation for robust PCA through top-down attention mechanisms achieves higher speed and quality than regular pyramids and non-pyramidal approaches.

Advances in Pattern Recognition — ICAPR 2001

Two novel concepts in structural pattern recognition are discussed in this paper. The rst, median of a set of graphs, can be used to characterize a set of graphs by just a single prototype. Such a characterization is needed in various tasks, for example, in clustering. The second novel concept is weighted mean of a pair of graphs. It can be used to synthesize a graph that has a speci ed degree of similarity, or distance, to each of a pair of given graphs. Such an operation is needed in many machine learning tasks. It is argued that with these new concepts various well-established techniques from statistical pattern recognition become applicable in the structural domain, particularly to graph representations. Concrete examples include k-means clustering, vector quantization, and Kohonen maps.

Introduction to combinatorial pyramids

A pyramid is a stack of image representations with decreasing resolution. Many image processing algorithms run on this hierarchical structure in O(log(n)) parallel processing steps where n is the diameter of the input image. Graph pyramids are made of a stack of successively reduced graphs embedded in the plane. Such pyramids overcome the main limitations of their regular ancestors. The graphs used in the pyramid may be region adjacency graphs or dual graphs. This paper reviews the different hierarchical data structures and introduces a new representation named combinatorial pyramid.

Curve representations in multiple resolutions

Abstract Both a linear and a spatial representation scheme are derived from binary curve relations. The linear scheme describes a curve by a simple chain code, called Ruli . The spatial approach works with the curve relations in a pyramid. The procedures reducing the resolution of both representations possess the length reduction property.

Contraction kernels and combinatorial maps

Graph pyramids are made of a stack of successively reduced graphs embedded in the plane. Such pyramids overcome the main limitations of their regular ancestors. The graphs used in the pyramid may be region adjacency graphs, dual graphs or combinatorial maps. Compared to usual graph data structures, combinatorial maps offer an explicit encoding of the orientation of edges around vertices. Each combinatorial map in the pyramid is generated from the one below by a set of edges to be contracted. This contraction process is controlled by kernels that can be combined in many ways. This paper shows that kernels producing a slow reduction rate can be combined to speed up reduction. Conversely, kernels decompose into smaller kernels that generate a more gradual reduction. We also propose one sequential and one parallel algorithm to compute the contracted combinatorial maps.