Wimmelbild analysis with approximate curvature coding distance images

Date

2013-09-25

Author

Bergbauer, Julia
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

84
views

0
downloads

We consider a task of tracing out target figures hidden in teeming figure pictures come to known as Wimmelbild(er). Wimmelbild is a popular genre of visual puzzles; a timeless classic for children, artists and cognitive scientists. Particularly suited to the considered task, we propose a diffuse representation which serves as a heuristic approximation mimicking curvature coding distance images. Curvature coding distance images received increased attention in recent years. Typically, they are computed as solutions to variants of Poisson PDE. The proposed approximation is based on erosion of the white space (background) followed by isotropic averaging, hence, does not require solving a PDE. © 2013 Springer-Verlag.

Subject Keywords

Poisson PDE and its variants , Level sets , Non-linear diffusion, Figure-hunt games , Teeming figure pictures , Applications of variational and PDE methods

URI

https://hdl.handle.net/11511/57307

DOI

https://doi.org/10.1007/978-3-642-38267-3_41

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

The Role of Diffusion in Figure Hunt Games Diebold, Julia; Tarı, Zehra Sibel; Cremers, Daniel (2015-05-01) We consider the task of tracing out target figures hidden in teeming figure pictures known as figure hunt games. Figure hunt games are a popular genre of visual puzzles; a timeless classic for children, artists and cognitive scientists. We argue and experimentally demonstrate that diffusion is a key to algorithmically search for a target figure in a binary line drawing. Particularly suited to the considered task, we propose a diffuse representation which diffuses the image while retaining the contour inform...
A NOVEL SHADOW RESTORATION ALGORITHM BASED ON ATMOSPHERIC EFFECTS FOR AERIAL IMAGES Aytekin, Caglar; Alatan, Abdullah Aydın (2010-09-29) In aerial images, the performance of the segmentation and object recognition algorithms could suffer due to shadows in the scene. This effort describes a novel shadow restoration algorithm based on atmospheric effects and characteristics of sun light for aerial images. Firstly, shadow regions are detected exploiting the Rayleigh scattering phenomena and the well-known fact related to the low illumination intensity in the shadow regions. After detection, shadow restoration is achieved by first restoring part...
SUPERPIXEL BASED HYPERSPECTRAL TARGET DETECTION Çalışkan, Akın; BATI, Emrecan; Koz, Alper; Alatan, Abdullah Aydın (2016-07-15) Using the spectral signature of a target by means of matching the signature with the pixels of an acquired hyperspectral image has been proven as an effective way of classifying hyperspectral pixels in most of the proposed methods in hyperspectral image analysis. A disadvantage of these methods is however to use only the spectral characteristics of pixels for detection while ignoring the spatial relations between the neighbouring pixels. In this paper, we propose a hyperspectral target detection method whic...
Brillouin-zone database on the Bilbao Crystallographic Server Aroyo, Mois I.; Orobengoa, Danel; de la Flor, Gemma; Tasci, Emre S.; Perez-Mato, J. Manuel; Wondratschek, Hans (International Union of Crystallography (IUCr), 2014-03-01) The Brillouin-zone database of the Bilbao Crystallographic Server (http://www.cryst.ehu.es) offers k-vector tables and figures which form the background of a classification of the irreducible representations of all 230 space groups. The symmetry properties of the wavevectors are described by the so-called reciprocal-space groups and this classification scheme is compared with the classification of Cracknell et al. [Kronecker Product Tables, Vol. 1, General Introduction and Tables of Irreducible Representati...
MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face Images Cugu, Ilke; Sener, Eren; Akbaş, Emre (2019-01-01) This paper is aimed at creating extremely small and fast convolutional neural networks (CNN) for the problem of facial expression recognition (FER) from frontal face images. To this end, we employed the popular knowledge distillation (KD) method and identified two major shortcomings with its use: 1) a fine-grained grid search is needed for tuning the temperature hyperparameter and 2) to find the optimal size-accuracy balance, one needs to search for the final network size (or the compression rate). On the o...

Citation Formats

J. Bergbauer and Z. S. Tarı, “Wimmelbild analysis with approximate curvature coding distance images,” 2013, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/57307.