• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Scale Invariant Auto-context for Object Segmentation and Labeling

Vol. 8, No. 8, August 28, 2014
10.3837/tiis.2014.08.018, Download Paper (Free):

Abstract

In complicated environment, context information plays an important role in image segmentation/labeling. The recently proposed auto-context algorithm is one of the effective context-based methods. However, the standard auto-context approach samples the context locations utilizing a fixed radius sequence, which is sensitive to large scale-change of objects. In this paper, we present a scale invariant auto-context (SIAC) algorithm which is an improved version of the auto-context algorithm. In order to achieve scale-invariance, we try to approximate the optimal scale for the image in an iterative way and adopt the corresponding optimal radius sequence for context location sampling, both in training and testing. In each iteration of the proposed SIAC algorithm, we use the current classification map to estimate the image scale, and the corresponding radius sequence is then used for choosing context locations. The algorithm iteratively updates the classification maps, as well as the image scales, until convergence. We demonstrate the SIAC algorithm on several image segmentation/labeling tasks. The results demonstrate improvement over the standard auto-context algorithm when large scale-change of objects exists.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
H. Ji, J. He and X. Yang, "Scale Invariant Auto-context for Object Segmentation and Labeling," KSII Transactions on Internet and Information Systems, vol. 8, no. 8, pp. 2881-2894, 2014. DOI: 10.3837/tiis.2014.08.018.

[ACM Style]
Hongwei Ji, Jiangping He, and Xin Yang. 2014. Scale Invariant Auto-context for Object Segmentation and Labeling. KSII Transactions on Internet and Information Systems, 8, 8, (2014), 2881-2894. DOI: 10.3837/tiis.2014.08.018.