. 2019 Oct 31;15:122. doi: 10.1186/s13007-019-0510-0

Table 2.

Basic information of image dataset

Image acquisition method	Panicle shape	Indica rice		Japonica rice		Total
Image acquisition method	Panicle shape	Yangliangyou No. 6	Fengyou xiangzhan	Wuyunjing No. 27	Nanjing No. 9108	Total
Original image data
Camera	A	45	45	45	45	180
	B	45	45	45	45	180
	C	45	45	45	45	180
Scanner	A	45	45	45	45	180
	B	45	45	45	45	180
	C	45	45	45	45	180
Linear regression training data
Camera	B	40	40	40	40	160
Camera	C	45	45	45	45	180
Scanner	B	40	40	40	40	160
Scanner	C	45	45	45	45	180
Linear regression validation data
Camera	B	25	25	25	25	100
Camera	C	25	25	25	25	100
Scanner	B	25	25	25	25	100
Scanner	C	25	25	25	25	100
Deep learning training and validation data
Camera	B	5	5	5	5	20
Camera	C	5	5	5	5	20
Scanner	B	10	10	10	10	40
Scanner	C	10	10	10	10	40
Deep learning testing data
Camera	B	25	25	25	25	100
Camera	C	25	25	25	25	100
Scanner	B	25	25	25	25	100
Scanner	C	25	25	25	25	100