Table 3.

TRA, SEG and OPT performance for our method, CPN, KTH (Magnusson and Jaldén, 2012), BLOB (Akram et al., 2016), U-Net (Ronneberger et al., 2015), U-Net-S (Gupta et al., 2019), and GC-ME (Bensch and Ronneberger, 2015).

		TRA	SEG	OPT
Fluo-N2DH-GOWT1-01	CPN	0.9864	0.8506	0.9185
	BLOB	0.9733	0.7415	0.8574
	KTH	0.9462	0.6849	0.8155
	Ours	0.9875	0.8585	0.9230
Fluo-N2DH-GOWT1-02	CPN	0.9719	0.8725	0.9222
	BLOB	0.9628	0.9046	0.9337
	KTH	0.9452	0.8942	0.9197
	Ours	0.9575	0.9181	0.9378
PhC-C2DH-U373-01	CPN	0.9594	0.7336	0.8456
	U-Net	0.9869	0.9375	0.9622
	GC-ME	0.9779	0.8748	0.9264
	Ours	0.9919	0.8527	0.9223
PhC-C2DH-U373-02	CPN	0.9346	0.7376	0.8361
	U-Net	0.9547	0.8303	0.8925
	GC-ME	0.9040	0.7567	0.8304
	Ours	0.9318	0.7735	0.8527
Fluo-N2DH-SIM+-01	U-Net-S	0.9862	0.8866	0.9364
	Ours	0.9841	0.8854	0.9348
Fluo-N2DH-SIM+-02	U-Net-S	0.9597	0.7381	0.8489
	Ours	0.9618	0.7616	0.8617

The best TRA and SEG values for each sequence are highlighted.