Figure 1 | Scientific Reports

Figure 1

From: Deep learning and wing interferential patterns identify Anopheles species and discriminate amongst Gambiae complex species

Figure 1

Schematic representation of the pipeline process developed for Anopheles identification using the Convolutional Neural Network approach. Example of classification output with the associated probability. The class of a given Anopheles WIPs image is predicted by two steps: (1) extracting hierarchical features (Convolutional layer) and (2) classifying these features (Fully-connected layer and softmax layer). In the feature extractor part, feature maps generated by filters at each convolution layer are indicated. These feature maps are used for visualization by weighting them with channel-wise averaged gradients.

Back to article page