Figure 3
From: Image-level and group-level models for Drosophilagene expression pattern annotation
The proposed framework of Drosophila gene pattern annotation. Given an image, the SIFT detector is utilized to generate descriptors for local patches of this image. After SIFT detection, the BoW or sparse coding is applied to transform the descriptors into representers. Then the pooling functions map the representers into features. We then use these features to perform keywords annotation via different schemes.