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.

Watermarking steps using a DCT coefficient.

More »

Fig 1 Expand

Fig 2.

DCT watermarking transformation workflow.

More »

Fig 2 Expand

Fig 3.

DCT coefficient for matrix factorization.

More »

Fig 3 Expand

Fig 4.

SURF feature extraction and clustering.

More »

Fig 4 Expand

Fig 5.

SURF for feature selection.

More »

Fig 5 Expand

Fig 6.

Feature matrix implemented by a hash sequence function.

More »

Fig 6 Expand

Fig 7.

The flow of watermark embedding.

More »

Fig 7 Expand

Fig 8.

The flow of watermark extraction.

More »

Fig 8 Expand

Fig 9.

Original image and watermark image.

More »

Fig 9 Expand

Table 1.

SURF-DCT coefficient changes by different attacks for the original image (set of features S1 to S9).

More »

Table 1 Expand

Table 2.

Dct and SURF ON conventional attacks.

More »

Table 2 Expand

Fig 10.

Impact of 4% Gaussian noise.

More »

Fig 10 Expand

Table 3.

Geometric attacks based on NC and PSNR values using the DCT-SURF.

More »

Table 3 Expand

Fig 11.

A 30% clockwise rotation after a geometric attack.

More »

Fig 11 Expand

Fig 12.

The impact of 25% UP and 30% translation attack on the image.

More »

Fig 12 Expand

Fig 13.

Clipping attack on the x-axis after 8%.

More »

Fig 13 Expand

Table 4.

Proposed algorithm comparison with SURF and DCT.

More »

Table 4 Expand

Table 5.

Comparison of the proposed algorithm with other improved hybrid algorithms.

More »

Table 5 Expand

Table 6.

Features comparison of the proposed algorithm with other techniques.

More »

Table 6 Expand

Fig 14.

Comparison of proposed algorithm with DCT and SURF on different values of attacks with correlation values.

More »

Fig 14 Expand