Marine Animal Classification With Correntropy-Loss-Based Multiview Learning
To analyze marine animals' behavior, seasonal distribution, and abundance, digital imagery can be acquired by a camera or a Lidar. Depending on the quantity and properties of acquired imagery, the animals are characterized as either features (shape, color, texture, etc.) or dissimilarity matrices derived from different shape analysis methods (shape context, internal distance shape context, etc.). For both cases, multiview learning is critical in integrating more than one set of feature/dissimilarity matrix for higher classification accuracy. This paper adopts correntropy loss as the cost function in multiview learning, which has favorable statistical properties for rejecting noise. For the case of features, the correntropy-loss-based multiview learning and its “entrywise” variation are developed based on the multiview intact space learning algorithm. For the case of dissimilarity matrices, the robust Euclidean embedding algorithm is extended to its multiview form with the correntropy loss function. Results from simulated data and real-world marine animal imagery show that the proposed algorithms can effectively enhance classification rate as well as suppress noise under different noise conditions.
- Research Organization:
- Florida Atlantic Univ., Fort Pierce, FL (United States)
- Sponsoring Organization:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE)
- Grant/Contract Number:
- EE0006787
- OSTI ID:
- 1799247
- Journal Information:
- IEEE Journal of Oceanic Engineering, Vol. 44, Issue 4; ISSN 0364-9059
- Publisher:
- IEEECopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Technical Performance and Cost Optimization of Unobtrusive Multi-static Serial LiDAR Imager (UMSLI) for Wide-area Surveillance and Identification of Marine Life at Marine Energy Installations
Automatic optical detection and classification of marine animals around MHK converters using machine vision