A framework for measuring infection level on cacao pods

Cacao farms worldwide lose up to 40% of their crops annually due to several diseases. To reduce the damage, farmers and agricultural technicians regularly monitor the well-being of their crops. But at present many still rely on visual inspection to assess the degree of infection on their crops, resulting to several errors and inconsistencies due to the subjective nature of the assessment procedure. To improve the inspection procedure, this research developed a framework for detecting and segmenting the infected parts of the fruit to measure the level of infection on the cacao pods based on k-means algorithm supplemented by a Support Vector Machine (SVM) using image colors as features. The highest attained accuracy was 89.2% using k=4 clusters. Results of this research provides promise in the implementation of the proposed framework in developing a more accurate assessment of infection level; thus, potentially improving decision support for managing cacao diseases.

[1]  Mary Inaba,et al.  Applications of weighted Voronoi diagrams and randomization to variance-based k-clustering: (extended abstract) , 1994, SCG '94.

[2]  Cao Qixin,et al.  Study on color image processing based intelligent fruit sorting system , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[3]  A. Akrofi,et al.  Natural occurrence and distribution of stem cankers caused by Phytophthora megakarya and Phytophthora palmivoraon cocoa , 2004, European Journal of Plant Pathology.

[4]  B. Adomako.  Causes and extent of yield losses in cocoa progenies , 2007 .

[5]  P. Hebbar.  Cacao diseases: a global perspective from an industry point of view. , 2007, Phytopathology.

[6]  R. Ploetz.  Cacao diseases: important threats to chocolate production worldwide. , 2007, Phytopathology.

[7]  D. Guest.  Black pod: diverse pathogens with a global impact on cocoa yield. , 2007, Phytopathology.

[8]  José Blasco,et al.  Original paper: Automatic sorting of satsuma ( Citrus unshiu ) segments using computer vision and morphological features , 2009 .

[9]  M. Omid,et al.  Implementation of an Efficient Image Processing Algorithm for Grading Raisins , 2010 .

[10]  Xu Liming,et al.  Automated strawberry grading system based on image processing , 2010 .

[11]  Fernando López-García,et al.  Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach , 2010 .

[12]  Wei Li,et al.  Combining discriminant analysis and neural networks for corn variety identification , 2010 .

[13]  Richard Szeliski,et al.  Computer Vision - Algorithms and Applications , 2011, Texts in Computer Science.

[14]  Amir Akramin Shafie,et al.  Automatic Fruits Identification System Using Hybrid Technique , 2011, 2011 Sixth IEEE International Symposium on Electronic Design, Test and Application.

[15]  E. O. Gunes,et al.  Detection of the pomegranate fruits on tree using image processing , 2012, 2012 First International Conference on Agro- Geoinformatics (Agro-Geoinformatics).

[16]  A. Kamalakannan,et al.  Surface defect detection and classification in mandarin fruits using fuzzy image thresholding, binary wavelet transform and linear classifier model , 2012, 2012 Fourth International Conference on Advanced Computing (ICoAC).

[17]  N. Kumar,et al.  Effect of fertigation through drip and micro sprinkler on physiological parameters in cocoa (Theobroma cacao L.). , 2013 .

[18]  Shiv Ram Dubey,et al.  Infected Fruit Part Detection using K-Means Clustering Segmentation Technique , 2013, Int. J. Interact. Multim. Artif. Intell..

[19]  Lu Wang,et al.  Detection of Fruit Skin Defects Using Machine Vision System , 2013, 2013 Sixth International Conference on Business Intelligence and Financial Engineering.

[20]  Monika Jhuria,et al.  Image processing for smart farming: Detection of disease and fruit grading , 2013, 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013).

[21]  Mohamed Rizon,et al.  Detecting Mango Fruits by Using Randomized Hough Transform and Backpropagation Neural Network , 2014, 2014 18th International Conference on Information Visualisation.

[22]  D. Alvindia,et al.  Revisiting the efficacy of hot water treatment in managing anthracnose and stem-end rot diseases of mango cv. ‘Carabao’ , 2015 .