Skip to main content

Table 2 Recall and precision of each feature detector/descriptor combination. The test run on the MSP dataset and results in the 4th through 6th columns are for each image on average. For reference, the average raw image volume is 19.2 KB. Assume a float type number takes 4 Bytes in storage. (The numbers in the parentheses in columns 4, 5, and 6 indicate the "rank'' of the detector/descriptor combination in terms of the corresponding performance metric in that column. The "rank-based score'' in the last column is the summation of the three ranks along the row.)

From: Feature-Based Image Comparison for Semantic Neighbor Selection in Resource-Constrained Visual Sensor Networks

  Descr. length No. of feature points Feature data vol. (KB) Recall Precision Rank-based score
SIFT 128 139 71.2() 0.4000() 0.3077() 17
SURF 64 72 18.4() 0.4500() 0.5294() 8
Harris + SIFT descr. 128 39 20.0() 0.3500() 0.3043() 18
Harris + SURF descr. 64 39 10.0() 0.4500() 0.1915() 15
DWT + SIFT descr. 128 87 44.5() 0.4000() 0.3636() 15
DWT + SURF descr. 64 87 22.2() 0.2500() 0.2000() 23
SIFT detec.+ M. I. 7 139 3.9() 0.1500() 0.2000() 20
SURF detec.+ M. I. 7 72 2.0() 0.1500() 0.1071() 21
Harris + M. I. 7 39 1.1() 0.4000() 0.4211() 6
DWT + M. I. 7 87 2.4() 0.3000() 0.2609() 16