From a Non-Local Ambrosio-Tortorelli Phase Field to a Randomized Part Hierarchy Tree

Date

2014-05-01

Author

Tarı, Zehra Sibel

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

54
views

0
downloads

In its most widespread imaging and vision applications, Ambrosio and Tortorelli (AT) phase field is a technical device for applying gradient descent to Mumford and Shah simultaneous segmentation and restoration functional or its extensions. As such, it forms a diffuse alternative to sharp interfaces or level sets and parametric techniques. The functionality of the AT field, however, is not limited to segmentation and restoration applications. We demonstrate the possibility of coding parts-features that are higher level than edges and boundaries-after incorporating higher level influences via distances and averages. The iteratively extracted parts using the level curves with double point singularities are organized as a proper binary tree. Inconsistencies due to non-generic configurations for level curves as well as due to visual changes such as occlusion are successfully handled once the tree is endowed with a probabilistic structure. As a proof of concept, we present (1) the most probable configurations from our randomized trees; and (2) correspondence matching results between illustrative shape pairs.

Subject Keywords

Mumford-shah regularizer, Curve evolution, Segmentation, Representation, Recovery, Distance, Models

URI

https://hdl.handle.net/11511/32702

Journal

JOURNAL OF MATHEMATICAL IMAGING AND VISION

DOI

https://doi.org/10.1007/s10851-013-0441-8

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

From "Advertising Architecture” to “Media Façade" : communication through digital display skin Aydoğan, Esra; Balamir, Aydan; Department of Architecture (2009) There is a growing trend to design buildings with colourful and dynamic outer skins through the integration of digital media tools, particularly Led Emitting Diode (LED) systems, and the use of innovative technology. This integration has been discussed in recent conferences under the term “media façade” as a new research field. Discussing the intersection of media, technology, art, and architecture, this field introduces a new form of communication platform, urban space and public perception, which can be v...
A pixel-by-pixel learned lossless image compression method with parallel decoding Gümüş, Sinem; Kamışlı, Fatih; Department of Electrical and Electronics Engineering (2022-7) The success of deep learning in computer vision applications has led to the use of learning based algorithms also in image compression. Learning based lossless image compression algorithms can be divided into three categories, namely, pixel-by-pixel (or masked convolution based) algorithms, prior based algorithms and latent representation based algorithms. In the pixel-by-pixel algorithms, each pixel’s probability distribution is obtained by processing the previously coded left and upper neighbouring pixels...
Supervised mesh segmentation for 3D objects with graph Convolutional neural networks Perek, Emir Kaan; Sahillioğlu, Yusuf; Department of Computer Engineering (2019) Mesh segmentation is a fundamental application that is primarily used for understanding and analyzing 3D shapes in a broad range of areas in Computer Science. With the increasing trend of deep learning, there have been many learning-based solutions to the mesh segmentation problem based on the classification of the individual mesh polygons. In this thesis, we cast mesh segmentation as a supervised graph labeling problem by using Graph Convolutional Neural Networks (GCNN). We treat a mesh object as a graph t...
Using multi-modal 3D contours and their relations for vision and robotics BAŞESKİ, Emre; Pugeault, Nicolas; Kalkan, Sinan; BODENHAGEN, Leon; Piater, Justus H.; KRÜGER, Norbert (Elsevier BV, 2010-11-01) In this work, we make use of 3D contours and relations between them (namely, coplanarity, cocolority, distance and angle) for four different applications in the area of computer vision and vision-based robotics. Our multi-modal contour representation covers both geometric and appearance information. We show the potential of reasoning with global entities in the context of visual scene analysis for driver assistance, depth prediction, robotic grasping and grasp learning. We argue that, such 3D global reasoni...
From Streetscape to Data Semantic segmentation for the prediction of outdoor thermal comfort Yazıcıoğlu, Gülin; Gürsel Dino, İpek (2021-01-01) © 2021, Education and research in Computer Aided Architectural Design in Europe. All rights reserved.In recent years, the increasing pace of urbanization is expected to increase the temperatures in urban contexts and amplify the Urban Heat Island effect. This phenomenon has a negative impact on the urbanites` thermal comfort in outdoor spaces. Modeling and simulation-based approaches can precisely calculate outdoor thermal comfort; however, they are labor-intensive and high in computational cost. This diffi...

Citation Formats

Z. S. Tarı, “From a Non-Local Ambrosio-Tortorelli Phase Field to a Randomized Part Hierarchy Tree,” JOURNAL OF MATHEMATICAL IMAGING AND VISION, pp. 69–86, 2014, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/32702.