Search papers, labs, and topics across Lattice.
This study benchmarks thirteen symmetry scoring methods, including both classical and deep learning approaches, to evaluate their effectiveness in quantifying mirror symmetry in images across various datasets. The findings reveal that while deep learning methods excel in single-axis and challenging multi-axis scenarios, a classical histogram-of-oriented-gradients (HOG) descriptor performs comparably to the best deep feature methods while being significantly faster. The results indicate that mid-scale oriented features are crucial for effective symmetry discrimination, suggesting that classical methods remain competitive in this domain.
Classical symmetry scoring methods can rival deep learning approaches in performance while being orders of magnitude faster, challenging the assumption that deeper networks always outperform traditional techniques.
Quantifying how mirror-symmetric an image is about a given axis (symmetry scoring) underpins applications from visual aesthetics to medical imaging, yet proposed scoring methods have never been compared on a common, statistically grounded protocol. We benchmark 13 scoring methods (nine collected from literature, four introduced here) spanning from classical features to frozen deep features, across four single-axis and five multi-axis datasets under a reflection-exact protocol with a chance-anchored, significance-tested discrimination skill. Deep backbones perform best on single-axis and harder multi-axis protocols. However, a classical histogram-of-oriented-gradients (HOG) descriptor trails the best frozen-network readout by a small (but significant) margin, is not statistically separable from the runner-up (a CNN-filter measure), and runs ~300x faster on CPU. Our results show that discrimination concentrates in mid-scale oriented features, where deep backbones peak at a low or mid stage, and HOG peaks at a mid cell size. Among existing methods, frozen deep features thus offer little over a tuned classical descriptor for measuring symmetry; whether task-trained deep scorers can do better remains open. We release the scorers and harness in imgsym, an open toolkit for image symmetry detection and measurement.
