Biomedical image time series registration with particle filtering (Parçacık süzgeci ile biyomedikal görüntü zaman serisi çakıştırma)

Warning The system is temporarily closed to updates for reporting purpose.

Yağcı, A. Murat and Erdil, Ertunç and Argunşah, Ali Özgür and Ünay, Devrim and Çetin, Müjdat and Akarun, Lale and Gürgen, Fikret (2013) Biomedical image time series registration with particle filtering (Parçacık süzgeci ile biyomedikal görüntü zaman serisi çakıştırma). In: 21st Signal Processing and Communications Applications Conference (SIU 2013), Haspolat, Cyprus

[thumbnail of yagci_SIU13.pdf] PDF
yagci_SIU13.pdf

Download (250kB)

Abstract

We propose a family of methods for biomedical image time series registration based on Particle filtering. The first method applies an intensity-based information-theoretic approach to calculate importance weights. An effective second group of methods use landmark-based approaches for the same purpose by automatically detecting intensity maxima or SIFT interest points from image time series. A brute-force search for the best alignment usually produces good results with proper cost functions, but becomes computationally expensive if the whole search space is explored. Hill climbing optimizations seek local optima. Particle filtering avoids local solutions by introducing randomness and sequentially updating the posterior distribution representing probable solutions. Thus, it can be more robust for the registration of image time series. We show promising preliminary results on dendrite image time series.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: Biomedical image registration, Bayesian filtering, Neural image analysis
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Electronics
Faculty of Engineering and Natural Sciences
Depositing User: Müjdat Çetin
Date Deposited: 13 Jan 2014 16:00
Last Modified: 26 Apr 2022 09:13
URI: https://research.sabanciuniv.edu/id/eprint/23473

Actions (login required)

View Item
View Item