Table 7 The parameters used for training libSVM for feature set HPP [15], TUHPP, DCT136 [11], and TUDCT136 on QCIF video dataset
From: HEVC double compression detection under different bitrates based on TU partition type
B1 − B2 (Kbps) | 100–200 | 100–300 | 100–400 | 200–300 | 200–400 | 300–400 |
|---|---|---|---|---|---|---|
HPP(25D) | ||||||
 c | 1.4142 | 2.0000 | 0.7071 | 2.0000 | 2.0000 | 2.0000 |
 g | 0.5000 | 0.3536 | 1.4142 | 0.7071 | 0.7071 | 0.5000 |
TUHPP(35D) | ||||||
 c | 0.5000 | 0.5000 | 0.7071 | 16 | 4.0000 | 5.6569 |
 g | 0.3536 | 0.5000 | 0.7071 | 0.1768 | 0.5000 | 0.1768 |
DCT136(136D) | ||||||
 c | 0.5000 | 32.0000 | 32.0000 | 32.0000 | 32.00 | 32.0000 |
 g | 8.0000 | 0.0313 | 0.0313 | 0.0313 | 0.0625 | 0.0625 |
TUDCT136(146D) | ||||||
 c | 0.25 | 0.25 | 0.25 | 1.4142 | 0.25 | 16 |
 g | 0.13 | 0.06 | 0.09 | 0.25 | 0.71 | 0.25 |