| 摘要 |
An identification device 1 is provided with a quantitative-phase-image acquisition unit 11, a feature-quantity extraction unit 12, a learning unit 13, a storage unit 14, and an identification unit 15. The feature-quantity extraction unit 12 extracts feature quantities from quantitative phase images of cells, the images being acquired by the quantitative-phase-image acquisition unit 11. The learning unit 13 performs machine learning about quantitative phase images of known cells, the types of which are known, on the basis of the feature quantities extracted by the feature-quantity extraction unit 12. The storage unit 14 stores the results of machine learning performed by the learning unit 13. The identification unit 15 uses the learning results stored in the storage unit 14 to identify the type of an unknown cell, the type of which is unknown, on the basis of a feature quantity extracted by the feature-quantity extraction unit 12 from a quantitative phase image of the unknown cell. Accordingly, it is possible to realize a device and a method that are capable of identifying an object even when the object has a three-dimensional shape, has no large features in terms of size and shape, and is clear and colorless. |
