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.

The proposed BISA system.

A gray-scale image is pre-processed with local contrast normalization and then a number of image patches are randomly cropped for CNN training, validation and final testing.

More »

Fig 1 Expand

Fig 2.

MLP with one hidden layer.

It consists of three layers, the input layer, the hidden layer and the output layer.

More »

Fig 2 Expand

Fig 3.

A semantic description of GRNN.

It consists of four layers, the input layer, the pattern layer, the summation layer and the output layer.

More »

Fig 3 Expand

Fig 4.

Example of Gaussian blurring images in four databases.

More »

Fig 4 Expand

Fig 5.

CNN prediction performance with Ni or Pn changes.

More »

Fig 5 Expand

Table 1.

CNN performance with regard to kernel number and kernel size.

More »

Table 1 Expand

Fig 6.

GRNN (left) and SVR (right) respectively perform when the spread parameter σ and the cost function c changes based on learned CNN features.

More »

Fig 6 Expand

Fig 7.

One trained kernel visualized by using “monarch.bmp”.

After convolutional filtering with the trained kernel, edge structures is hard to notice in heavily blurred images (y11), while fine structures can be seen in relatively high-quality images (y96).

More »

Fig 7 Expand

Table 2.

Performance evaluation with PLCC on Gaussian blurring images.

More »

Table 2 Expand

Table 3.

Performance evaluation of SROCC on Gaussian blurring images.

More »

Table 3 Expand

Fig 8.

The time spent on score prediction of image sharpness.

Several algorithms show promise in real-time image sharpness estimation.

More »

Fig 8 Expand

Fig 9.

Effect of color information on our CNN.

Compared to gray-scale input, color image input positively enhances our network’s prediction metrics.

More »

Fig 9 Expand