Skip to main content
Fig. 1 | Plant Methods

Fig. 1

From: SpikeSegNet-a deep learning approach utilizing encoder-decoder network with hourglass for spike segmentation and counting in wheat plant from visual imaging

Fig. 1

Dataset preparation: a LemnaTec image (of size 6576 × 4384) consists of not only the plant regions but also the chamber used in imaging; b the images are cropped (of size 1656 * 1356) to get only the region of interests; c spike pixels (x, y) are selected and previous color of the selected pixel is replaced by the fill_color; d segmented mask image is generated by setting the pixel value of fill_color as 0 (black) elsewhere, 255 (white)

Back to article page

Plant Methods

ISSN: 1746-4811