# Insect Identification using Machine learning ### Background <p style="text-align:justify;">The international centre of insect physiology and ecology is a leading institution in insect research in Africa and the world. There are several reasons why icipe focuses on insect research: they are a source of food and feed, they are the most diverse and abundant forms of life on earth, and they are crop pests and disease vectors. There is a need to harness the potential of insects for food and feed, pest, disease vectors etc. and develop appropriate strategies e.g. control, industrialization and research. All these starts with identifying the insects, which is a role taken up by a well-trained entomologist. However, since entomologists are few and not always available, and insects varieties are many, raises the need for other automated techniques. Machine learning approaches (especially deep learning) have become a go-to tool for automated image identification and classification. These digital solutions can be deployed on mobile phones and used by farmers and communities at large for image identification and classifiation.</p> ### Tasks In this project, you are expected to: <ol> <li> Review some of the machine learning algorithms that can be developed for insect identification </li> <li> Identify open datasets that can be used for training the algorithms </li> <li> Curate data available at icipe and make them machine learning ready </li> <li> Develop a proof of concept model for the identification of one insect (this can be identified from further consultations with entomologists) </li> <li> Provide recommendations on how this can be adopted, including deployment platforms </li> </ol> ### Useful Resources and References <ol> <li> <a href="https://ais-lab.di.unimi.it/Teaching/AdvancedIntelligentSystems/ProjectDocuments/Insects%20Image%20Classification%20through%20Deep%20Convolutional%20Neural%20Networks.pd">Insects Image Classification through Deep Convolutional Neural Networks</a> </li> <li> <a href="https://www.mdpi.com/1424-8220/21/5/1601">AgriPest: A Large-Scale Domain-Specific Benchmark Dataset for Practical Agricultural Pest Detection in the Wild</a> </li> <li> <a href="https://deliverypdf.ssrn.com/delivery.php?ID=618009031125123080124105082101123123117011052016042090064106006010124065088002019092041039044052007031061094095018006122121005008053029080082121089000008115026122025091013021068109106024104026029120097084107100009096076088010029109103085089114089093067&EXT=pdf&INDEX=TRUE">A Case Study of Image Classification Based on Deep Learning using Tensor Flow</a> </li> <li> <a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8336590&casa_token=QN8GXDwwMRMAAAAA:n86AZX8Mxiw7z7Wp1m8-XYZ37Ln4Sarz2pu4xBKITH1U47WeY_9TLwygSDsuFYLL2j87jrS_2LvgSw&tag=1">MobileNets for Flower Classification using TensorFlow</a> </li> <li> <a href="https://ieeexplore.ieee.org/abstract/document/8634690?casa_token=FD1wuQ_g9zIAAAAA:PF8xGNNVewsSKOK-3LNIDD4uL2gbuDEZo_wRuUvXOqCGxswnviO5Gz5tzmImQRpaZ7FXm_oFexp35w">Breast Cancer Histopathology Image Classification with Deep Convolutional Neural Networks</a> </li> </ol>