Table 5.

Performance summary of algorithm 1 on UNL-CPPD dataset (Naming convention for plant sequence is: Plant_ID-Genotype ID [1])

Plant sequence	Dataset	No. leaves	Detected leaves	False leaves	Accuracy
$Plant\_001-9$	CPPD-I	116	93	1	0.79
	CPPD-II	168	157	5	0.83
$Plant\_006-25$	CPPD-I	138	136	0	0.98
	CPPD-II	205	188	5	0.91
$Plant\_008-19$	CPPD-I	142	140	0	0.98
	CPPD-II	210	200	9	0.86
$Plant\_016-{20}^{+}$	CPPD-I	103	86	0	0.83
	CPPD-II	141	129	0	0.88
$Plant\_023-1$	CPPD-I	113	101	0	0.89
	CPPD-II	154	135	8	0.83
$Plant\_045-1$	CPPD-I	122	120	3	0.96
	CPPD-II	177	170	6	0.93
$Plant\_047-25$	CPPD-I	148	142	2	0.94
	CPPD-II	212	196	5	0.88
$Plant\_063-{32}^{†}$	CPPD-I	149	138	0	0.93
	CPPD-II	214	174	18	0.72
$Plant\_070-11$	CPPD-I	125	111	0	0.89
	CPPD-II	177	148	5	0.83
$Plant\_071-8$	CPPD-I	141	131	0	0.93
	CPPD-II	199	163	7	0.77
$Plant\_076-24$	CPPD-I	135	126	2	0.92
	CPPD-II	191	152	2	0.78
$Plant\_104-{24}^{‡}$	CPPD-I	144	140	0	0.97
	CPPD-II	186	185	0	0.96
$Plant\_191-28$*	CPPD-I	137	111	0	0.96
	CPPD-II	178	151	7	0.81
Average	CPPD-I	132	123	< 1	0.92
	CPPD-II	186	165	$\approx$ 6	0.85

* Plant sequence used to demonstrate inaccuracy in leaf detection due to self-occlusion and leaf crossover

⁺Plant-level accuracy for UNL-CPPD-II is higher than that of UNL-CPPD-I

^†Plant-level accuracy for UNL-CPPD-II is lower than that of UNL-CPPD-I

^‡Plant-level accuracy remains fairly similar for both UNL-CPPD-I and UNL-CPPD-II