Thresholding algorithm

We use a thresholding algorithm to discriminate the low level noise from the video CCD. 

Budenz DL, Rhee FJ FeuerWJ, et al. Comparison of glaucomatous visual field defects using standard full threshold and Swedish interactive threshold algorithms. Arch Ophthalmol 2002 120 1136-1141. 

Schimiti RB, Avehno RR, Kara-Jose N, Costa VP (2002) Pull-threshold versus Swedish Interactive Threshold Algorithm (SITA) in normal individnals nndergoing antomated perimetry for the first time. Ophthalmology 109 2084—2092 discnssion 2092. 

After receiving the mediator s proposal, both players check whether the proposal can be accepted or not according to line 10 and 11 of Algorithm 1 (see p. 177). As we mentioned above, the threshold value can vary according to the types of the utility values. Here, we assume that the threshold (Algorithm 1, line 4, see p. 177) is 3. Both players reject the proposal because the difference between the maximum utility (see Table 2) and the utility of the proposal is greater than the threshold value (20 — 14 = 6 > 3 and 20 — 16 = 4 > 3). 

Performance assessment of the segmentation results is done by comparing the ROI results obtained from the thresholding algorithm with the actual ROI provided by neuroradiologists. Area overlap (AO), false positive rate (FPR) and false negative rate (FNR) are used as the performance metrics. These metrics are computed as follows [16]... 

Ju, D., Shiimpton, J. S., Hearn, A. (2012). A multi-thresholding algorithm fw sizing out of focus particles. Particle Particle Systems Characterization, 29(2), 78-92. Available at http //dx.doLorg/10.1002 psc.201100032. 

---