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 workflow of the proposed approach.

More »

Fig 1 Expand

Fig 2.

The model of DIDSON sonar.

More »

Fig 2 Expand

Fig 3.

Flow chart of the proposed method.

(i) clustering analysis, (ii) adaptive tensor voting, (iii) minimum spanning tree construction and edge pruning.

More »

Fig 3 Expand

Fig 4.

Image detection process results.

a(i∼iii): original images, b(i∼iii): image blocks, c(i∼iii): crack fragments, d(i∼iii): crack probability map, e(i∼iii): final crack curves.

More »

Fig 4 Expand

Table 1.

Classification for different crack types.

More »

Table 1 Expand

Fig 5.

Statistical properties of sample characteristic set and test characteristics.

(a) sonar images for 1.8 MHz pattern. (b) sonar images for 1.1 MHz pattern.

More »

Fig 5 Expand

Table 2.

The fuzzy rules for BBA values of relative lengths and gray intensity ratios.

More »

Table 2 Expand

Fig 6.

The fusion results from different perspectives alongside a comparison of different frequencies and their fusion.

More »

Fig 6 Expand

Table 3.

The BBA values obtained from sonar imagery using different frequencies and the results of the evidence fusion.

More »

Table 3 Expand

Table 4.

The BBA values for different perspectives.

More »

Table 4 Expand

Fig 7.

Image detection results comparing the proposed method and other classical methods.

(a) Original image, (b) Tensor voting, (c) Wasp colony algorithm and (d) The proposed method.

More »

Fig 7 Expand

Table 5.

Classification accuracy results for different crack types.

More »

Table 5 Expand