Developing a Computer Application for the Identification of Similar Butterfly Species Using MATLAB Image Processing
Identification of insect pests to the species level is very important in the field of plant protection. The species name is a filing and retrieval system which enables us to store and/or retrieve all data for a species such as host plants, life cycle, damage, or pesticide resistance. However, identification of insects to the species level requires special knowledge and training. We aimed in this research to develop a computer application for the untrained person to identify digital images for three morphologically similar butterfly species. The first was the cabbage butterfly, Pieris rapae leucosoma Schawerda, a common pest of Cruciferae, while the other two (Euchloe ausonia melisande Fruhstorfer, Pontia daplidice daplidice Linnaeus) were generally considered non-pest species. Matlab 2017 software was used to build an implementation of the developed image processing technique. The insect digital image processing steps included resizing, orientation, filtering, extracting wing colors, and finally calculating the ratio of colors. Some images were used to train the computer to identify the images and the rest of images were used for identification by the computer. In addition, Graphical User Interface Application was developed to let any user (computer programmer or amateur) to upload process and identify an image. More than 99% correct identifications were obtained. The developed application may be a promising tool for insect image identification when more species are included and refinement of the technique is achieved.
Gardens With Wings website, http://gardenswithwings.com/identify-butterflies.html
British Butterflies identification website, https://www.britishbutterflies.co.uk/identification.asp
MATLAB for Artificial Intelligence official website, www.Mathworks.com
S. A. Hassan, N. A. Rahman, “AUTOMATIC CLASSIFICATION OF INSECTS USING COLOR-BASED AND SHAPE-BASED DESCRIPTORS”, International Journal of Applied Control, Electrical and Electronics Engineering (IJACEEE) Vol 2, No.2, May 2014.
H. Yang et al., "Research on insect identification based on pattern recognition technology," 2010 Sixth International Conference on Natural Computation, Yantai, 2010, pp. 545-548.
L. Zhu and Z. Zhang, "Auto-classification of insect images based on color histogram and GLCM," 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery, Yantai, 2010, pp. 2589-2593.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.