Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

One of the two settings for photography.

A proper holder was used to attach a high-end (VIVO-V21) camera phone equipped with a clip-on macro lens and an LED ring light. A mosquito was placed approximately 7 cm (the shortest focusable distance) below the phone’s camera. The smartphone was triggered by a remote control in order to minimize vibration and ensure high-quality photos. In another setting, mosquitoes were photographed from a variety of angles using a midrange (Samsung Galaxy A52s) or subpar (Vivo Y21) camera phone without the aid of holders or lighting. Due to blurring caused by hand movement, shading caused by flash lighting, or higher noise caused by a low-quality sensor, photos taken in such a way turn out to be of low quality.

More »

Fig 1 Expand

Fig 2.

Cropped and resized mosquito images.

Having the correct setting and a high-quality camera, the 512x512 images are of excellent quality (LHS). Without a holder, adequate lighting, or a camera of sufficient quality, the resulting image may be blurry with high shading and noise levels (middle). Blurry photographs reduce the accuracy of all classification models (RHS). The picture on the right was purposely blurred from the one in the middle.

More »

Fig 2 Expand

Table 1.

Biological mosquito species, collection sites, and the number of females/images taken in various lighting conditions by three different smartphones.

More »

Table 1 Expand

Fig 3.

Architecture of VGG16.

It is composed of five convolution blocks, each followed by a max pooling layer, and a block of three fully-connected layers.

More »

Fig 3 Expand

Fig 4.

Dropout vs. spatial dropout.

The conventional dropout (left) blocks some nodes (gray squares) in 3-D randomly; the spatial dropout (right) selects at random some channels first and blocks all the nodes in the chosen ones.

More »

Fig 4 Expand

Fig 5.

Architecture of SDVGG16.

Modified from the VGG16, a spatial dropout layer is inserted after each of the five max pooling layers.

More »

Fig 5 Expand

Fig 6.

Combining two inputs.

Adapted from the spatial dropout, channels from two images can be combined by interleaving the odd channels from one image, and the even one from the other.

More »

Fig 6 Expand

Fig 7.

Architecture of early-combined model (Model (A)).

Two branches from two image inputs are combined just after the first convolution block.

More »

Fig 7 Expand

Fig 8.

Architecture of middle-combined model (Model (B)).

Two branches from two image inputs are combined after the third convolution block.

More »

Fig 8 Expand

Fig 9.

Architecture of late-combined model (Model (C)).

Two branches from two image inputs are combined after the fifth convolution block.

More »

Fig 9 Expand

Fig 10.

The classifier.

It is composed of three deep learning models: Models (A), (B) and (C), which attempt to predict the species from three image pairs from three input images, and an ensemble model (Model (D)), which combines and yields the optimal classification result.

More »

Fig 10 Expand

Table 2.

Mean and standard deviation of classification accuracy of the reference model in comparison to those of the SDVGG16 model with the dropout rate from 0.1 to 0.6 on the reference dataset.

More »

Table 2 Expand

Table 3.

Mean and standard deviation of classification accuracy of the reference model in comparison to those of our multi-view models on the reference dataset.

More »

Table 3 Expand

Table 4.

Mean and standard deviation of classification accuracy of our multi-view models when trained on 80% high-quality images and tested on 20% high-quality images.

More »

Table 4 Expand

Table 5.

Mean and standard deviation of the classification accuracy of our proposed models, which were trained on all high-quality images but tested on 90% low-quality images.

More »

Table 5 Expand

Table 6.

Mean and standard deviation of the classification accuracy of our proposed models, which were retrained on 80% of high- and low-quality images and tested on remaining 20% of high- and low-quality images.

More »

Table 6 Expand

Table 7.

Mean and standard deviation of the classification accuracy of our proposed models, which were trained on all high-quality images but tested on 90%low-quality images, one input was blurred intentionally.

More »

Table 7 Expand

Table 8.

Mean and standard deviation of the classification accuracy of our proposed models, which were trained on all high-quality images but tested on 90%low-quality images, two inputs were blurred intentionally.

More »

Table 8 Expand