LASP Local adaptive super pixels

Date

2015-09-30

Author

İNCE, Kutalmış Gökalp
Çığla, Cevahir
Alatan, Abdullah Aydın

Metadata

Show full item record

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

Item Usage Stats

167
views

0
downloads

In this study, a novel gradient ascent approach is proposed for super-pixel extraction in which spectral statistics and super-pixel geometry are utilized to obtain an optimal Bayesian classifier for pixel to super-pixel label assignment. Utilization of the spectral variances and super-pixel areas reduces the dependency on user selected global parameters, while increasing robustness and adaptability. Proposed Local Adaptive Super-Pixels (LASP) approach exploits hexagonal tiling, while achieving some refinement during initialization in order to improve computation time and accuracy. The experiments conducted on Berkeley segmentation database show that LASP outperforms the existing methods in terms of boundary recall and computation time. Moreover, the proposed method provides lower bleeding error performance compared to the existing gradient ascent techniques.

Subject Keywords

Over segmentation, Super pixel, Clustering

URI

https://hdl.handle.net/11511/33298

DOI

https://doi.org/10.1109/icip.2015.7351575

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

MRF Based Image Segmentation Augmented with Domain Specific Information Karadag, Ozge Oztimur; Yarman Vural, Fatoş Tunay (2013-09-13) A Markov Random Field based image segmentation system which combines top-down and bottom-up segmentation approaches is proposed in this study. The system is especially proposed for applications where no labeled training set is available, but some priori general information referred as domain specific information about the dataset is available. Domain specific information is received from a domain expert and formalized by a mathematical representation. The type of information and its representation depends o...
REGION-BASED IMAGE SEGMENTATION VIA GRAPH CUTS Cigla, Cevahir; Alatan, Abdullah Aydın (2008-01-01) A graph theoretic color image segmentation algorithm is proposed, in which the popular normalized cuts image segmentation method is improved with modifications on its graph structure. The image is represented by a weighted undirected graph, whose nodes correspond to over-segmented regions, instead of pixels, that decreases the complexity of the overall algorithm. In addition, the link weights between the nodes are calculated through the intensity similarities of the neighboring regions. The irregular distri...
Aerothermodynamic shape optimization using DSMC and POD-RBF methods Kutkan, Halit; Eyi, Sinan; Department of Aerospace Engineering (2018) This thesis study presents a hybrid method based on Proper Orthogonal Decomposition (POD) with Radial Basis Function (RBF), on Direct Simulation Monte Carlo (DSMC) solutions for aerothermodynamic front surface optimization of Stardust re-entry. Gaussian and multiquadric RBFs are implemented for comparison, and multiquadric functions are chosen due to their insensitivity to diverse shape parameters. Cubic uniform B-spline curves are used innovatively for parameterization of the geometry change, instead of cu...
Multi-image region growing for integrating disparity maps Leloglu, UĞUR MURAT; Halıcı, Uğur (1999-01-01) In this paper, a multi-image region growing algorithm to obtain planar 3-D surfaces in the object space from multiple dense disparity maps, is presented. A surface patch is represented by a plane equation and a set of pixels in multiple images. The union of back projections of all pixels in the set onto the infinite plane, forms the surface patch. Thanks to that hybrid representation of planar surfaces, region growing (both region aggregation and region merging) is performed on all images simultaneously. Pl...
Image segmentation with unified region and boundary characteristics within recursive shortest spanning tree Esen, E.; Alp, Y. K. (2007-06-13) The lack of boundary information in region based image segmentation algorithms resulted in many hybrid methods that integrate the complementary information sources of region and boundary, in order to increase the segmentation performance. In compliance with this trend, we propose a novel method to unify the region and boundary characteristics within the canonical Recursive Shortest Spanning Tree algorithm. The main idea is to incorporate the boundary information in the distance metric of RSST with minor cha...

Citation Formats

K. G. İNCE, C. Çığla, and A. A. Alatan, “LASP Local adaptive super pixels,” 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/33298.