Beyond $χ^2$ Difference: Learning Optimal Metric for Boundary Detection
This work addresses boundary detection in natural images, which is an incremental improvement over existing methods.
The paper tackled the problem of detecting natural image boundaries by proposing a Learning-based Boundary Metric (LBM) to replace the χ² difference in the mPb algorithm, resulting in an increase in F-measure from 0.69 to 0.71 on the BSDS500 benchmark.
This letter focuses on solving the challenging problem of detecting natural image boundaries. A boundary usually refers to the border between two regions with different semantic meanings. Therefore, a measurement of dissimilarity between image regions plays a pivotal role in boundary detection of natural images. To improve the performance of boundary detection, a Learning-based Boundary Metric (LBM) is proposed to replace $χ^2$ difference adopted by the classical algorithm mPb. Compared with $χ^2$ difference, LBM is composed of a single layer neural network and an RBF kernel, and is fine-tuned by supervised learning rather than human-crafted. It is more effective in describing the dissimilarity between natural image regions while tolerating large variance of image data. After substituting $χ^2$ difference with LBM, the F-measure metric of mPb on the BSDS500 benchmark is increased from 0.69 to 0.71. Moreover, when image features are computed on a single scale, the proposed LBM algorithm still achieves competitive results compared with \emph{mPb}, which makes use of multi-scale image features.