Research Article
An Image Similarity Acceleration Detection Algorithm Based on Sparse Coding
Table 1
Feature extraction and distance detection time of the three algorithms.
| Number of key frames | 5 | 15 | 25 | 35 | 45 | 55 | 65 | 75 | 85 | 95 |
| ScSIFT | Feature extraction time | 0.70 | 0.72 | 0.82 | 0.68 | 0.70 | 0.69 | 0.69 | 0.68 | 0.70 | 0.70 | Detection time | 0.21 | 0.54 | 0.71 | 0.90 | 1.14 | 1.32 | 1.58 | 1.75 | 1.87 | 2.18 | Single-frame detection time | 0.04 | 0.04 | 0.03 | 0.03 | 0.03 | 0.02 | 0.02 | 0.02 | 0.02 | 0.02 | Total runtime | 0.91 | 1.26 | 1.53 | 1.58 | 1.84 | 2.01 | 2.26 | 2.43 | 2.57 | 2.88 |
| SIFT | Feature extraction time | 0.46 | 0.46 | 0.45 | 0.46 | 0.45 | 0.45 | 0.45 | 0.45 | 0.46 | 0.45 | Detection time | 0.80 | 2.30 | 2.87 | 3.05 | 3.51 | 4.16 | 4.22 | 4.89 | 4.93 | 5.56 | Single-frame detection time | 0.16 | 0.15 | 0.11 | 0.09 | 0.08 | 0.08 | 0.06 | 0.07 | 0.06 | 0.06 | Total runtime | 1.27 | 2.75 | 3.32 | 3.51 | 3.96 | 4.61 | 4.67 | 5.35 | 5.40 | 6.02 |
| SURF | Feature extraction time | 2.76 | 2.76 | 2.76 | 2.76 | 2.75 | 2.77 | 2.76 | 2.75 | 2.76 | 2.76 | Detection time | 0.19 | 0.44 | 0.52 | 0.62 | 0.70 | 0.76 | 0.85 | 0.93 | 0.96 | 1.08 | Single-frame detection time | 0.04 | 0.03 | 0.02 | 0.02 | 0.02 | 0.01 | 0.01 | 0.01 | 0.01 | 0.01 | Total runtime | 2.95 | 3.20 | 3.28 | 3.38 | 3.45 | 3.54 | 3.61 | 3.69 | 3.72 | 3.84 |
|
|