XPMap-Based Irregular Pyramids for Image Segmentation

نویسنده

  • Hans Meine
چکیده

Acknowledgements It is hard for me to keep these words short. First of all, my biggest thanks go to Ulli, for making me come to KOGS and stay there, introducing countless ideas and approaches to me that I cannot live without anymore, creating the VIGRA library, and finally, customiz-ing my thesis's topic to meet my interests (in fact, it seemed this was just a selection of favorites out of an endless store of ideas he collected in the last years. . .) Furthermore, I want to thank Prof. Stiehl for rising and feeding my interest in computer vision (and biological vision) throughout my studies and beyond. I have to thank Katrin (who encouraged me throughout the work), Gunnar, and Peer for reading parts of the thesis and giving me feedback, Ji-Young for both spending time reading and discussing my thesis and lending me several useful books, and in particular Jürgen, who probably spent more time reading my thesis than even Ulli. Finally, I cannot thank everyone at KOGS personally here, so let my just say I am glad to work in the company of Alex (thanks for all L A T E X-related ideas), Dieter, Gunnar, Jörn (who gave wise tips in many situations), Joshua, Leonid, Peer, Sven (from whom I learned countless vision-and computer-related things), Thomas (who had very interesting and inspiring discussions with me) Erklärung Hiermit erkläre ich, daß ich die vorliegende Diplomarbeit selbstständig durchgeführt und dabei keine anderen als die angegebenen Quellen benutzt habe.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Hierarchical Interactive Image Segmentation Using Irregular Pyramids

In this paper we describe modifications of irregular image segmentation pyramids based on user-interaction. We first build a hierarchy of segmentations by the minimum spanning tree based method, then regions from different (granularity) levels are combined to a final (better) segmentation with user-specified operations guiding the segmentation process. Based on these operations the users can pr...

متن کامل

Voronoi Pyramids and Hoppeld Networks

We present an algorithm for image segmentation with irregular pyramids. Instead of starting with the original pixel grid, we rst apply an adaptive Voronoi tessellation to the image. For irregular pyramid construction we present a Hoppeld neural network which controls the decimation process. The validity of our approach is demonstrated by several examples in image segmentation.

متن کامل

Noise Robustness of Irregular LBP Pyramids

In this paper, we briefly introduce the SCIS algorithm a hierarchical image segmentation approach based on LBP pyramids and evaluate its robustness to uniform, Gaussian, and Poisson distributed additive chromatic noise. Moreover, we study the influence of image properties such as the amount of details and SNR on the segmentation performance. Our evaluation shows that SCIS is robust to Gaussian ...

متن کامل

Annotated Contraction Kernels for Interactive Image Segmentation

This article shows how the interactive segmentation tool termed “Active Paintbrush” and a fully automatic region merging can both be based on the theoretical framework of contraction kernels within irregular pyramids instead of their own, specialized data structures. We introduce “continous pyramids” in which we purposely drop the common requirement of a fixed reduction factor between successiv...

متن کامل

Spatiotemporal video segmentation and motion estimation through irregular pyramids

This paper presents a new spatiotemporal segmentation technique for video sequences. It relies on building irregular pyramids based on its homogeneity over consecutive frames. Pyramids are interlinked to keep a relationship between the regions in the frames. Its performance is good in real-world conditions because it does not depend on image constrains. ? 2003 Pattern Recognition Society. Publi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008