Multi-Scale Superpatch Matching using Dual Superpixel Descriptors - Archive ouverte HAL Access content directly
Journal Articles Pattern Recognition Letters Year : 2020

Multi-Scale Superpatch Matching using Dual Superpixel Descriptors


Over-segmentation into superpixels is a very effective dimensionality reduction strategy, enabling fast dense image processing. The main issue of this approach is the inherent irregularity of the image decomposition compared to standard hierarchical multi-resolution schemes, especially when searching for similar neighboring patterns. Several works have attended to overcome this issue by taking into account the region irregularity into their comparison model. Nevertheless, they remain sub-optimal to provide robust and accurate superpixel neighborhood descriptors, since they only compute features within each region, poorly capturing contour information at superpixel borders. In this work, we address these limitations by introducing the dual superpatch, a novel superpixel neighborhood descriptor. This structure contains features computed in reduced superpixel regions, as well as at the interfaces of multiple superpixels to explicitly capture contour structure information. A fast multi-scale non-local matching framework is also introduced for the search of similar descriptors at different resolution levels in an image dataset. The proposed dual superpatch enables to more accurately capture similar structured patterns at different scales, and we demonstrate the robustness and performance of this new strategy on matching and supervised labeling applications.
Fichier principal
Vignette du fichier
Giraud_DSPM_2019.pdf (5.36 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Public Domain

Dates and versions

hal-02409963 , version 1 (13-12-2019)


Public Domain


  • HAL Id : hal-02409963 , version 1


Rémi Giraud, Merlin Boyer, Michaël Clément. Multi-Scale Superpatch Matching using Dual Superpixel Descriptors. Pattern Recognition Letters, 2020. ⟨hal-02409963⟩
81 View
40 Download


Gmail Mastodon Facebook X LinkedIn More