Deep learning and hand-crafted features for virus image classification
This work addresses virus classification from microscopy images, which is important for medical diagnostics, but it is incremental as it fuses existing techniques.
The authors tackled virus image classification by combining handcrafted and deep learning features in an ensemble, achieving state-of-the-art performance with a strong boost over individual methods.
In this work, we present an ensemble of descriptors for the classification of transmission electron microscopy images of viruses. We propose to combine handcrafted and deep learning approaches for virus image classification. The set of handcrafted is mainly based on Local Binary Pattern variants, for each descriptor a different Support Vector Machine is trained, then the set of classifiers is combined by sum rule. The deep learning approach is a densenet201 pretrained on ImageNet and then tuned in the virus dataset, the net is used as features extractor for feeding another Support Vector Machine, in particular the last average pooling layer is used as feature extractor. Finally, classifiers trained on handcrafted features and classifier trained on deep learning features are combined by sum rule. The proposed fusion strongly boosts the performance obtained by each stand-alone approach, obtaining state of the art performance.