News:

Performance Evaluation of State-of-the-Art Discrete Symmetry Detection Algorithms

Members: Minwoo Park1, Seungkyu Lee1, James Hays2, Po-Chun Chen1, Somesh Kashyap1, Asad Butt1 and Yanxi Liu1
1The Pennsylvania State University, 2Carnegie Mellon Univeristy

Project Descriptions


Symmetry is one of the important cues for human and machine perception of the world. For over three decades, automatic symmetry detection from images/patterns has been a standing topic in computer vision. We present a timely, systematic, and quantitative performance evaluation of three state of the art discrete symmetry detection algorithms. This evaluation scheme includes a set of carefully chosen synthetic and real images presenting justified, unambiguous single or multiple dominant symmetries, and a pair of well-defined success rates for validation. We make our 176 test images with associated hand-labeled ground truth publicly available with this paper. In addition, we explore the potential contribution of symmetry detection for object recognition by testing the symmetry detection algorithm on three publicly available object recognition image sets (PASCAL VOC'07, MSRC and Caltech-256). Our results indicate that even after several decades of effort, symmetry detection in real-world images remains a challenging, unsolved problem in computer vision. Meanwhile, we illustrate its future potential in object recognition.








Figure 1. Sample images and results from our test image set





Figure 2. The pairwise reflection and rotation symmetry detection algorithms evaluation on our 176 test-images with labeled ground truth

Publications

Related Links

Experimental results - reflection symmetry
Experimental results - rotation symmetry
Base test image and ground truth for Figure 2 above(Figure 4 in the paper)
Test image set