Browsing by Author "Guallpa Duy, Steven Alexander"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Detección temprana de antracnosis foliar en plantas de fréjol (Phaseolus vulgaris) mediante análisis espectral visible
    (Universidad de Cuenca, 2025-08-05) Guallpa Duy, Steven Alexander; Villamagua Vergara, Gabriela Carolina
    Plant diseases cause significant economic losses in agriculture. In Ecuador, the common bean (Phaseolus vulgaris) is a key crop for food security and sustainable production. However, it faces threats such as foliar anthracnose, caused by Colletotrichum lindemuthianum, which can reduce yields by up to 95% in humid, mountainous regions like Azuay. Early detection of this disease is essential for implementing effective control measures and minimizing production losses. Although various diagnostic methods exist, many are costly or slow, limiting their adoption in resource-constrained settings. This study aimed to evaluate the application of visible spectral analysis for the early detection of foliar anthracnose in bean plants using RGB images captured with mobile devices (Samsung A11 and Tecno Spark 20), based on three vegetation indices: MPRI, MGRVI, and VARI. A total of 25 inoculated leaflets and 25 control (non-inoculated) leaflets were photographed over five days post-inoculation. The first non-visible spectral symptoms appeared 72 hours after inoculation, increasing progressively in the following days, unlike the control group, which showed no signs of disease. No significant differences were found among the indices used, but there were differences between the devices: the Samsung A11 stood out for a higher number of detections, while the Tecno Spark 20 excelled in quantifying diseased area in the later stages of sampling. Additionally, the underside of the leaf showed greater sensitivity to symptom detection than the upper side. These findings support the use of visible spectral analysis with conventional cameras as an accessible and efficient tool for the development of automated early detection systems for fungal diseases in food crops.