Hyperspectral remote sensing IQA via learning multiple kernels from mid-level features |
| |
Institution: | 1. Servei de Cirurgia General i de l’Aparell Digestiu, Hospital Universitari de Bellvitge, Barcelona, Spain;2. Gastro Obeso Center, Sao Paulo, Brazil;3. Cirurgia Geral, Centre Hospitalar entre o Douro e Vouga, Santa Maria de Feira, Portugal;4. Servicio de Cirugía General y del Aparato Digestivo, Hospital Clínico San Carlos, Madrid, Spain |
| |
Abstract: | Hyperspectral image quality assessment (HIQA) is an indispensable technique in both academic and industry domain However, HIQA is still a challenging task since those fine-grained and quality-aware visual details are difficult to be captured. Compared with the conventional low-level features, mid-level features usually contain more semantic and quality clues and exhibit higher discriminant ability. Thus, we aim to leverage the mid-level features for HIQA. More specifically, three-scale superpixel mosaics are generated from the input image pre-processed by PCA. Each superpixel scale corresponds to various homogeneousobject parts. Subsequently, three mid-level visual features (fisher vector, combined mean features, reconstructed image matrix) as well as deep features of hyperspectral images are calculated with three-scale superpixel images to constitute multiple kernels. Afterwards, we integrate these kernels into a multimodal one, which is further integrated into a feature vector by row-wise stacking. The image quality evaluation can be calculated based on the designed similarity metric. Comprehensive experiments have demonstrated the effectiveness of our proposed HIQA algorithm. |
| |
Keywords: | Hyperspectral image quality assessment Mid-level feature Deep features Multiple kernel learning Quality-aware |
本文献已被 ScienceDirect 等数据库收录! |
|