Frank Schmitt

Color image segmentation using an enhanced Gradient Network Method

The objective of this paper is to evaluate a new combined approach intended for reliable color image segmentation, in particular images presenting color structures with strong but continuous color or luminosity changes, such as commonly found in outdoors scenes. The approach combines an enhanced version of the Gradient Network 2, with common region-growing approaches used as pre-segmentation steps. The GNM2 is an post-segmentation procedure based on graph analysis of global color and luminosity gradients in conjunction with a segmentation algorithm to produce a reliable segmentation result. The approach was automatically evaluated using a close/open world approach. Two different region-growing segmentation methods, CSC and Mumford and Shah with and without the GNM post-processing were compared against ground truth images using segmentation evaluation indices Rand and Bipartite Graph Matching. These results were also confronted with other well established segmentation methods (RHSEG, Watershed, EDISON, JSEG and Blobworld).

Fast two-step segmentation of natural color scenes using hierarchical region-growing and a color-gradient network

We present evaluation results with focus on combined image and efficiency performance of the Gradient Network Method to segment color images, especially images showing outdoor scenes. A brief review of the techniques, Gradient Network Method and Color Structure Code, is also presented. Different region-growing segmentation results are compared against ground truth images using segmentation evaluation indices Rand and Bipartite Graph Matching. These results are also confronted with other well established segmentation methods (EDISON and JSEG). Our preliminary results show reasonable performance in comparison to several state-of-art segmentation techniques, while also showing very promising results comparatively in the terms of efficiency, indicating the applicability of our solution to real time problems.

Vanishing point detection with an intersection point neighborhood

A new technique to automatically detect the vanishing points in digital images is presented. The proposed method borrows several ideas from various papers on vanishing point detection and segmentation in sparse images and recombines them with a new intersection point neighborhood on Z2.

Grouping of Semantically Similar Image Positions

Features from the Scale Invariant Feature Transformation (SIFT) are widely used for matching between spatially or temporally displaced images. Recently a topology on the SIFT features of a single image has been introduced where features of a similar semantics are close in this topology. We continue this work and present a technique to automatically detect groups of SIFT positions in a single image where all points of one group possess a similar semantics. The proposed method borrows ideas and techniques from the Color-Structure-Code segmentation method and does not require any user intervention.

Analysis of brain images using the 3D-CSC segmentation method

The 2D segmentation method CSC (Color Structure Code) for color images has recently been generalized to 3D color or grey valued images. To apply this technique for an automated analysis of 3D MR brain images a few preprocessing and postprocessing steps have been added. We present this new brain analysis technique and compare it with SPM.

3D-CSC: A General Segmentation Technique for Voxel Images with Application in Medicine

The successful 2d segmentation method CSC has recently been generalized to 3d. We shortly introduce the concept of both 2D- and 3D-CSC and present two use cases (classification of MR brain data and CT bone data) which demonstrate that analysis of segments generated by the CSC allows high quality classification of 3d data by relatively easy means.

Recent advances in 3D-CSC based MR brain image segmentation

The 3D-CSC is a general segmentation method for voxel images. One of its possible applications is the segmentation of MR images of the human head. We here propose a self-contained method consisting of preprocessing steps which remove common artifacts from the input image, a 3D-CSC segmentation which partitions the input image into gray value similar, spatially connected regions and a final classification of CSC segments into white matter, gray matter and non-brain. We evaluate our method using the brainweb dataset for which a ground truth is available.

Automatische Rekonstruktion des Verlaufs aneurysmatischer Aorten in postoperativen CTA-Bildern

Zur Behandlung abdominaler Aortenaneurysmen stellt die minimal-invasive endovaskulare Stent-Graft-Methode eine wichtige Alternative zur offenen Operation dar. Nach erfolgter Stent-Graft-Implantation sind regelmasige Nachkontrollen und Analysen der eventuellen Veranderung von Stent und Aneurysmasack notig, um Undichtigkeiten des Implantats fruhzeitig feststellen zu konnen.Wahrend zur praoperativen Aneurysmasegmentierung bereits erste automatisierte Verfahren zur Verfugung stehen, geschieht die Nachuntersuchung heute meist durch manuelle, nicht-computerunterstutzte Analyse der CTA-Aufnahmen. Das in diesem Artikel vorgestellte Verfahren vereinfacht die Nachuntersuchung, indem das Aortenlumen automatisch und robust gegenuber Metallartefakten, wie sie z.B. durch die Prothese erzeugt werden konnen, segmentiert wird. Ausgehend von der Lumensegmentierung wird mit Hilfe eines Shortest-Path-Verfahrens die Mittellinie durch das Lumen bestimmt. Diese dient als Grundlage fur eine kurvenbasierte Reformation, durch die die Lange und der Durchmesser des Aneurysmas leicht bestimmt werden kann.