Development of a Severity Calculator of a Sweet Pepper Cercospora Leaf Spot Disease Through Digital Image using Marker-Controlled Watershed and Contour Finding Algorithm

Bon Jovi Lapiceros, Michael Anthony Jay B Regis, Lucia M. Borines


The study of disease severity on crops would visually gauge the observable inter-related patterns. However, manual assessment of disease severity is subjective, thus decreasing the accuracy of the specied evaluation. Due to this, computer vision is necessary to objectively supplement the human capacity to perform image analysis. This study would develop a disease severity calculator of Cercospora leaf spot on sweet pepper. Eighteen leaf samples of
sweet pepper were collected from the eld and photographed under xed camera settings with white background. Digital images were resized to 640 x 480 pixels and pre-processed using the GimpTM image editor to remove unimportant infections and leaf shadow. Watershed transform was used to extract the foreground (i.e. leaf image) and then the contour-nding algorithm was used to compute the area of the leaf. Afterward, the leaf spots were isolated from the leaf using inverse thresholding and contour-nding algorithm. The area of the isolated leaf spots was then computed. Finally, the severity of the disease was calculated by dividing the disease area over the leaf area. Quantitative performance evaluation utilized the detection percentage, branching factor and receiver operating characteristics (ROC). After testing the system on the specied dataset, experimental results show a detection percentage
of 72.46% and branching factor of 37.97%. Moreover, the area under the curve (AUC) of the ROC graph is 0.988 (i.e. >0.5) which means that the study is eective on its detection


Watershed transformation; Contour finding; inverse thresholding


Arbelaez, P., Maire, M., Fowlkes, C.,& Malik, J. (2010). Contour Detection and Hierarchical Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 898 - 916.

Cheewawiriyakul, S., Conn, K., Gabor, B., Kao, J., & Salati, R. (2006). Pepper & Eggplant Disease Guide: A Practical Guide for Seedsmen, Growers and

Agricultural Advisors. Seminis Vegetable

Seeds, Inc.

Forsyth, D. A., & Ponce, J. (2012). Computer Vision: A Modern Approach (2nd ed.). Pearson Education, Inc.

Goncalves, L., Subtil, A., Oliveira, M. R., & Bermudez, P. d. (2014). Roc Curve Estimation: An Overview. REVSTAT { Statistical Journal, 1-20.

Horsfall, J., & Henberger, J. (1942). Measuring magnitude of defoliation disease of tomatoes. Phytopath, 226-232.

Jun, S., Zhiheng, L., Xinyang, H., Hong, Y., & Yukun, W. (2009). Biological characteristics of the pepper brown leaf spot,Cercospora capsici. Chinese Society

of Plant Protection. Kreiman, G., Koch, C., & Fried, I. (2002). Single-neuron correlates of subjective vision in the human medial temporal lobe. Proceedings of the National Academy of Sciences of the United States of America, (pp. 8378 - 8383).

Lin, C., & Nevatia, R. (1998). Building Detection and Description from a Single Intensity Image. Computer Vision and Image Understanding, 72, pp. 101-121.

Ludy, M.-J., Moore, G. E., & Mattes, R. D.

(2012). The Effects of Capsaicin and

Capsiate on Energy Balance: Critical

Review and Meta-analyses of Studies in

Humans. Oxford Chemical Senses ,


Marin, A., Ferreres, F., Tomas-Barberan, F. A., & Gil, M. I. (2004). Characterization and Quantitation of Antioxidant Constituents of Sweet Pepper (Capsicum

annuum L.). American Chemical Society Journal for Agricultural and Food Chemisty, 3861-3869.

Full Text: JST_2016 02


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.