Object-based image labeling through learning by example and multi-level segmentation

Xu, Y
Duygulu, P
Saber, E
Tekalp, AM
Yarman Vural, Fatoş Tunay
We propose a method for automatic extraction and labeling of semantically meaningful image objects using "learning by example" and threshold-free multi-level image segmentation. The proposed method scans through images, each of which is pre-segmented into a hierarchical uniformity tree, to seek and label objects that are similar to an example object presented by the user. By representing images with stacks of multi-level segmentation maps, objects can be extracted in the segmentation map level with adequate detail. Experiments have shown that the proposed multi-level image segmentation results in significant reduction in computation complexity for object extraction and labeling (compared to a single fine-level segmentation) by avoiding unnecessary tests of combinations in finer levels. The multi-level segmentation-based approach also achieves better accuracy in detection and labeling of small objects. (C) 2003 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

Citation Formats
Y. Xu, P. Duygulu, E. Saber, A. Tekalp, and F. T. Yarman Vural, “Object-based image labeling through learning by example and multi-level segmentation,” PATTERN RECOGNITION, vol. 36, no. 6, pp. 1407–1423, 2003, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/62981.