3 May 2017 Multiple-instance learning-based sonar image classification
Author Affiliations +
An approach to image labeling by seabed context based on multiple-instance learning via embedded instance selection (MILES) is presented. Sonar images are first segmented into superpixels with associated intensity and texture feature distributions. These superpixels are defined as the "instances" and the sonar images are defined as the "bags" within the MILES classification framework. The intensity feature distributions are discrete while the texture feature distributions are continuous, thus the Cauchy-Schwarz divergence metric is used to embed the instances in a higher-dimensional discriminatory space. Results are given for labeled synthetic aperture sonar (SAS) image database containing images with a variety of seabed textures.
Conference Presentation
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
J. Tory Cobb, J. Tory Cobb, Xiaoxiao Du, Xiaoxiao Du, Alina Zare, Alina Zare, Matthew Emigh, Matthew Emigh, } "Multiple-instance learning-based sonar image classification", Proc. SPIE 10182, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXII, 101820H (3 May 2017); doi: 10.1117/12.2262530; https://doi.org/10.1117/12.2262530


Word segmentation of off-line handwritten documents
Proceedings of SPIE (January 28 2008)
Text location in color documents
Proceedings of SPIE (January 13 2003)
Using mathematical morphology for document skew estimation
Proceedings of SPIE (December 15 2003)
Optimized filterbank fingerprint recognition
Proceedings of SPIE (May 28 2003)

Back to Top