
Data collection Image acquisition was done by searching a diversity of conditions, although the plants were grown in laboratory conditions. In this way, photographs included the growth stages of seedling, jointing, and flowering. The images were acquired inside a plastic shed, involving natural illumination, and five consecutive images were taken by plant. Acquisition device was a compact scientific camera (ThorLabs DCC1645C-HQ). Image preprocessing and augmentation The original images underwent a preprocessing stage in terms of cropping and resizing by two methods done simultaneously: Cut to central square: Image cropped to a central square. Cuadrant division: Square image divided into four equal parts. All cropped images were resized to 224x224 pixels size. As cuadrant division method can generate sub-images with black content or a minimum portion of the leaf, and these images can confuse the algorithm, a suffix is added to the images cosidered as empty on the Processed_dataset.
Composition of Processed_dataset folder Each image has a filename as 'S-T-- Were goes from 05 to 10 and represents the week of maize growth at the time image was collected. could be C, P or P50 is a unique id for each image and Could be present or not, indicating the number of the cuadrant obtained from the Cuadrant Division process, and goes from 0 to 3 In addition, some images have the suffix '_EMPTY' which leads to a blank image or one that does not have enough leaf content. For each image taken from a single leaf, there are 5 processed images in this folder.
This database presents samples of maize leaves placed on a withe background, representing three levels of phosphorus deficiency: complete absence of the nutrient (labeled -P), half dose of the required phosphorus for normal plant development (-P50), and complete supply (C). Its composed of two folders: Original_dataset: 722 jpg images of 1280 x 1020 pixels size divided into '_C', '-P' and '-P50' folders for class labels. Processed_dataset: 2433 png images of 224 x 224 pixels size divided into '-C', '-P' and '-P50' folders for class labels.
Image classification, Leaf analysis, Computer vision, Deep learning, Plant nutrition
Image classification, Leaf analysis, Computer vision, Deep learning, Plant nutrition
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 1 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
