Low-level multiscale image segmentation and a benchmark for its evaluation

Date

2020-10-01

Author

Akbaş, Emre

Metadata

Show full item record

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

Item Usage Stats

201
views

0
downloads

In this paper, we present a segmentation algorithm to detect low-level structure present in images. The algorithm is designed to partition a given image into regions, corresponding to image structures, regardless of their shapes, sizes, and levels of interior homogeneity. We model a region as a connected set of pixels that is surrounded by ramp edge discontinuities where the magnitude of these discontinuities is large compared to the variation inside the region. Each region is associated with a scale that depends upon the fraction of the strong and weak parts of its boundary. Traversing through the range of all possible scales, we obtain all regions present in the image. Regions strictly merge as the scale increases; hence a tree is formed where the root node corresponds to the whole image, nodes closer to the root along a path correspond to larger regions and those further from the root capture smaller regions representing embedded details. To evaluate the accuracy and precision of our algorithm, as well as to compare it to the existing algorithms, we present a new benchmark dataset for low-level image segmentation. We provide evaluation methods for both boundary-based and region-based performance of algorithms. We also annotate different parts of the images that are difficult to segment with the types of segmentation challenges they pose. This enables our benchmark to give an account of which algorithm fails where. We show that our proposed algorithm performs better than the widely used low-level segmentation algorithms on this benchmark.

Subject Keywords

Signal Processing, Software, Computer Vision and Pattern Recognition

URI

https://hdl.handle.net/11511/41929

Journal

COMPUTER VISION AND IMAGE UNDERSTANDING

DOI

https://doi.org/10.1016/j.cviu.2020.103026

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Making linear prediction perform like maximum likelihood in Gaussian autoregressive model parameter estimation Candan, Çağatay (Elsevier BV, 2020-01-01) A two-stage method for the parameter estimation of Gaussian autoregressive models is proposed. The proposed first stage is an improved version of the conventional forward-backward prediction method and can be interpreted as its weighted version with the weights derived from the arithmetic mean of the log-likelihood functions for different conditioning cases. The weighted version is observed to perform better than the conventional forward-backward prediction method and other linear prediction based methods (...
Nested local symmetry set Tarı, Zehra Sibel (Elsevier BV, 2000-08-01) A local-symmetry-based representation for shapes in arbitrary dimensions and a method for its computation are presented. The method depends on analyzing the Hessian of a specific boundaryness function, v, which is computed as the minimizer of an energy functional. The method is basically a generalized ridge finding scheme in which the ridges are defined in terms of the orbit of the gradient vector del v under the action of the Hessian of v. Once the ridges are determined, the local extrema of the magnitude ...
One-dimensional representation of two-dimensional information for HMM based handwriting recognition Arica, N; Yarman Vural, Fatoş Tunay (Elsevier BV, 2000-06-01) In this study, we introduce a one-dimensional feature set, which embeds two-dimensional information into an observation sequence of one-dimensional string, selected from a code-book. It provides a consistent normalization among distinct classes of shapes, which is very convenient for Hidden Markov Model (HMM) based shape recognition schemes. The normalization parameters, which maximize the recognition rate, are dynamically estimated in the training stage of HMM. The proposed recognition system is tested on ...
Information permeability for stereo matching Cigla, Cevahir; Alatan, Abdullah Aydın (Elsevier BV, 2013-10-01) A novel local stereo matching algorithm is introduced to address the fundamental challenge of stereo algorithms, accuracy and computational complexity dilemma. The time consuming intensity dependent aggregation procedure of local methods is improved in terms of both speed and precision. Providing connected 2D support regions, the proposed approach exploits a new paradigm, namely separable successive weighted summation (SWS) among horizontal and vertical directions enabling constant operational complexity. T...
Multiple description coding of animated meshes Bici, M. Oguz; Akar, Gözde (Elsevier BV, 2010-11-01) In this paper, we propose three novel multiple description coding (MDC) methods for reliable transmission of compressed animated meshes represented by series of 3D static meshes with same connectivity. The proposed methods trade off reconstruction quality for error resilience to provide the best expected reconstruction of 3D mesh sequence at the decoder side. The methods are based on layer duplication and partitioning of the set of vertices of a scalable coded animated mesh by either spatial or temporal sub...

Citation Formats

E. Akbaş, “Low-level multiscale image segmentation and a benchmark for its evaluation,” COMPUTER VISION AND IMAGE UNDERSTANDING, pp. 0–0, 2020, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/41929.