6533b82efe1ef96bd1293d5d

RESEARCH PRODUCT

Salient Spin Images: A Descriptor for 3D Object Recognition

Ali BouzitAlamin MansouriPatrice MénielJihad H’rouraPatrick JuillionDriss MammassMichaël Roy

subject

Spin imageComputer sciencebusiness.industryDetectorComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONCognitive neuroscience of visual object recognition[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]02 engineering and technology[INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG]01 natural sciences[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR]010309 opticsRobustness (computer science)SalientComputer Science::Computer Vision and Pattern Recognition0103 physical sciences0202 electrical engineering electronic engineering information engineeringClutter020201 artificial intelligence & image processingComputer visionArtificial intelligencebusinessTrue positive rateScalingComputingMilieux_MISCELLANEOUS

description

In the last decades a wide range of algorithms have been devoted to recognize 3D free-from objects under real conditions such as occlusions, clutters, rotation, scale and translation. Spin image is one of these algorithms known to be robust to rotation, translation, occlusions up to 70% and clutters up to 60%, but still suffer from scaling, resolution changes and it is time consuming. In this paper we present a novel approach based on spin images, called salient spin images (SSI). This method enhances spin images algorithm based on its limits. Particularly, it decreases significantly the complexity of the algorithm using DoG detector, it shows a higher performance due to the relevant localization of salient vertices on the scene, and its robustness to occlusions reaches 80%.

yearjournalcountryeditionlanguage
2018-07-01
https://doi.org/10.1007/978-3-319-94211-7_26