Wolfgang Ortmann

Difference of Boxes Filters Revisited: Shadow Suppression and Efficient Character Segmentation

A robust segmentation is the most important part of an automatic character recognition system (e.g. document processing, license plate recognition etc.). In our contribution we present an efficient segmentation framework using a preprocessing step for shadow suppression combined with a local thresholding technique. The method is based on a combination of difference of boxes filters and a new ternary segmentation, which are both simple low-level image operations. We also draw parallels to a recently published work on a ganglion cell model and show that our approach is theoretically more substantiated as well as more robust and more efficient in practice. Systematic evaluation of noisy input data as well as results on a large dataset of license plate images show the robustness and efficiency of our proposed method. Our results can be applied easily to any optical character recognition system resulting in an impressive gain of robustness against nonlinear illumination.

Automated analysis of confocal laser endomicroscopy images to detect head and neck cancer

The purpose of this study was to develop an automated image analysis algorithm to discriminate between head and neck cancer and nonneoplastic epithelium in confocal laser endomicroscopy (CLE) images.

Robust matching of affinely transformed objects

This paper presents a general robust solution for the problem of affine object matching, whereby an object can be given as a discrete point set, a set of lines, or a closed region. Let be given two such objects which are related by a general affine transformation (up to noise and maybe some additional distortions of the object). Then we can determine the six parameters a/sub ik/ of the affine transformation using some new general moment invariants. These invariants are global, but assigned locally to any object point. With these invariants and using the Hungarian method or dynamic programming it can be computed a weighted point reference list. The affine parameters a/sub ik/ can be calculated from this list using the method of the least absolute differences (LAD) method. Our approach is very robust against noise and distortions. The algorithm can be used also for all subgroups of the affine group. Additionally, it is an unifying approach for all classes of objects: Discrete point sets, sets of lines, and closed regions. Many well known algorithms have problems with the case of symmetries of the objects, our approach is stable against symmetries. Experimental results both on simulated and real objects validate the robustness of the algorithm. In the case of closed regions our algorithm performs better than SQUID F. Mokhtarian et al. (1996).

Shift Detection by Restoration

In this paper an approach is presented for robust shift detection of two given images. The new unifying idea is that we determine a shifted delta impulse using some well-known restoration techniques, e.g. the Wiener filtering, constraint restoration, entropy restoration, and Baysian restoration. The used restoration techniques imply the robustness of the presented method. Our approach is a generalization of the matched filtering approach. Additionally, we describe in the paper the problem of calculating an evaluation measure of the restored delta impulse image. This measure is the basis for the uncertainty of the detected shift. The unifying approach of shift detection by restoration (SDR-method) could be tested successfully, for example using a series of fundus image pairs which are of practical interest and which contain also small rotations, scalings and even deformations

Shift detection by restoration

In this paperan approachis presentedfor robustshift detectionof two givenimages.Thenew unifying ideais thatwedetermineashifteddeltaimpulse usingsomewell-known restorationtechniques, e.g. theWienerfiltering, constraintrestoration,entropy restoration,andBaysianrestoration.The usedrestorationtechniquesimply the robustnessof the presentedmethod. Our approachis a generalizationof the matchedfiltering approach.Additionally, we describein the paperthe problemof calculatingan evaluation measureof the restoreddeltaimpulseimage. This measureis the basisfor the uncertaintyof the detectedshift. The unifying approachof shift detection by restoration(SDR-method)couldbetestedsuccessfullyfor aseriesof practicalapplications.

Novel computer vision algorithm for the reliable analysis of organelle morphology in whole cell 3D images--A pilot study for the quantitative evaluation of mitochondrial fragmentation in amyotrophic lateral sclerosis.

The function of intact organelles, whether mitochondria, Golgi apparatus or endoplasmic reticulum (ER), relies on their proper morphological organization. It is recognized that disturbances of organelle morphology are early events in disease manifestation, but reliable and quantitative detection of organelle morphology is difficult and time-consuming. Here we present a novel computer vision algorithm for the assessment of organelle morphology in whole cell 3D images. The algorithm allows the numerical and quantitative description of organelle structures, including total number and length of segments, cell and nucleus area/volume as well as novel texture parameters like lacunarity and fractal dimension. Applying the algorithm we performed a pilot study in cultured motor neurons from transgenic G93A hSOD1 mice, a model of human familial amyotrophic lateral sclerosis. In the presence of the mutated SOD1 and upon excitotoxic treatment with kainate we demonstrate a clear fragmentation of the mitochondrial network, with an increase in the number of mitochondrial segments and a reduction in the length of mitochondria. Histogram analyses show a reduced number of tubular mitochondria and an increased number of small mitochondrial segments. The computer vision algorithm for the evaluation of organelle morphology allows an objective assessment of disease-related organelle phenotypes with greatly reduced examiner bias and will aid the evaluation of novel therapeutic strategies on a cellular level.

A novel approach for affine point pattern matching

Affine point pattern matching (APPM) is an integral part of many pattern recognition problems. Given two sets P and Q of points with unknown assignments pi →qj between the points, no additional information is available. The following task must be solved: – Find an affine transformation T such that the distance between P and the transformed set Q′= TQ is minimal. In this paper, we present a new approach to the APPM problem based on matching in bipartite graphs. We have proved that the minimum of a cost function is an invariant under special affine transformations. We have developed a new algorithm based on this property. Finally, we have tested the performance of the algorithm on both synthetically generated point sets and point sets extracted from real images.

Shift detection by restoration-demonstrated by signal based point pattern matching

Shift detection is one of the fundamental tasks within the field of picture registration. With SDR (shift detection by restoration) a robust signal-based procedure is given for detection of real shifts of pictures. On the basis of a model which contains various perturbances, the shifted delta impulse determining the shift is restored with methods of image restoration. By the use of the magnitude spectrum of two pictures also rotation and scaling can be detected by SDR. After a brief introduction to the basics of SDR, the procedure is demonstrated in a further problem-point pattern matching (PPM). A new extremely robust method is derived whereby pictures are generated from point patterns, which are used for the matching. An evaluation of the restored delta impulse is used, in order to determine weights for point correspondences.