استخراج الميزات المستندة إلى AlexNet لتصنيف الكسافا: نهج التعلم الآلي
محتوى المقالة الرئيسي
الملخص
تعتبر الكسافا محصولًا مهمًا في أجزاء كثيرة من العالم، لا سيما في إفريقيا وآسيا وأمريكا الجنوبية، حيث تعمل كغذاء أساسي لملايين الأشخاص. يعتبر استخدام ميزات اللون والملمس والشكل أقل كفاءة في تصنيف أنواع الكسافا. وذلك لأن أوراق الكسافا لها نفس لون مورفولوجيا بين نوع وآخر. بالإضافة إلى ذلك، فإن أوراق الكسافا لها شكل مشابه نسبيًا لنوع واحد من الكسافا، وبالمثل، مع قوام أوراق الكسافا. إلى جانب ذلك، هناك أيضًا المنيهوت السامة. الكسافا السامة وغير السامة لها لون وشكل وملمس أوراق متطابق نسبيًا. يهدف هذا البحث إلى تصنيف أنواع الكسافا باستخدام طريقة التعلم العميق مع AlexNet المدربة مسبقًا كمستخرج للميزات. تم استخدام ثلاث طبقات مختلفة متصلة بالكامل لاستخراج السمات، وهي fc6 و fc7 و fc8. كانت المصنفات المستخدمة هي Support Vector Machine (SVM) و K-Nearest Neighbours (KNN) و Naive Bayes. تتكون مجموعة البيانات من 1400 صورة لأوراق الكسافا تتكون من أربعة أنواع من الكسافا: Gajah و Manggu و Kapok و Beracun. أوضحت النتائج أن أفضل طبقة استخلاص كانت fc6 وبدقة 90.7٪ للطبقة المتناهية الصغر (SVM). كان أداء SVM أيضًا أفضل مقارنةً بـ KNN و Naive Bayes، بدقة 90.7٪، وحساسية 83.5٪، ونوعية 93.7٪، ودرجة F1 83.5٪. ستساهم نتائج هذا البحث في تطوير تقنيات تصنيف النباتات، وتوفير رؤى حول الاستخدام الأمثل للتعلم العميق وطرق التعلم الآلي لتحديد الأنواع النباتية. في النهاية، يمكن للنهج المقترح أن يساعد الباحثين والمزارعين وعلماء البيئة في تحديد الأنواع النباتية ومراقبة النظام البيئي والإدارة الزراعية.
Received 24/05/2023
Revised 26/08/2023
Accepted 28/08/2023
تفاصيل المقالة
هذا العمل مرخص بموجب Creative Commons Attribution 4.0 International License.
كيفية الاقتباس
المراجع
Lilhore UK, Imoize AL, Lee CC, Simaiya S, Pani SK, Goyal N, et al. Enhanced Convolutional Neural Network Model for Cassava Leaf Disease Identification and Classification. Mathematics. 2022 ; 10(4), 580. https://doi.org/10.3390/math10040580
Sangbamrung I, Praneetpholkrang P, Kanjanawattana S. A Novel Automatic Method for Cassava Disease Classification Using Deep Learning. J Adv Inf Technol. 2020; 11(4): 241–8. https://doi.org/10.12720/jait.11.4.241-248
Wang G, Sun Y, Wang J. Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning. Comput Intell Neurosci. 2017; 2017:1–8. https://doi.org/10.1155/2017/2917536
Bodhwani V, Acharjya DP, Bodhwani U. Deep Residual Networks for Plant Identification. Procedia Comput Sci. 152(2019):186–94. https://doi.org/10.1016/j.procs.2019.05.042
Barhate D, Pathak S, Dubey AK. Hyperparameter-tuned batch-updated stochastic gradient descent: Plant species identification by using hybrid deep learning. Ecol Inform. 2023; 75(2023): 102094. https://doi.org/10.1016/j.ecoinf.2023.102094
Bojamma AM, Shastry C. A study on the machine learning techniques for automated plant species identification: current trends and challenges. Int j inf tecnol. 2021; 13(3): 989–95. https://doi.org/ 10.1007/s41870-019-00379-7
Yang K, Zhong W, Li F. Leaf Segmentation and Classification with a Complicated Background Using Deep Learning. Agronomy. 2020; 10(11):1721. https://doi.org/10.3390/agronomy10111721
Sachar S, Kumar A. Survey of feature extraction and classification techniques to identify plant through leaves. Expert Syst Appl. 2021; 167: 114181. https://doi.org/10.1016/j.eswa.2020.114181
Azadnia R, Kheiralipour K. Recognition of leaves of different medicinal plant species using a robust image processing algorithm and artificial neural networks classifier. J Appl Res Med Aromat Plants. 2021; 25: 100327. https://doi.org/10.1016/j.jarmap.2021.100327
Prasetyo E. Detection of Mango Tree Varieties Based on Image Processing. Indonesia J Sci Technol. 2016; 1(2): 203–15. https://doi.org/10.17509/ijost.v1i2.3800
Prasetyo E, Adityo RD, Suciati N, Fatichah C. Mango Leaf Classification with Boundary Moments of Centroid Contour Distances as Shape Features. In: 2018 International Seminar on Intelligent Technology and Its Applications (ISITIA) 2018. p. 317–20. https://doi.org/10.1109/ISITIA.2018.8711115
Unajan MC, Tabada WM, Gerardo B, Fajardo AC. Sweet Potato ( Ipomoea batatas ) Variety Recognizer Using Image Processing and Artificial Neural Network. In: 2017 Manila International Conference on “Trends in Engineering and Technology” (MTET-17). 2017. p. 87–90. http://doi.org/10.17758/URUAE.AE0117518
Selvam L, Kavitha P. Classification of ladies finger plant leaf using deep learning. J Ambient Intell Humaniz Comput. 2020 ; 1–9 http://doi.org/10.1007/s12652-020-02671-y
Wang M, Fu B, Fan J, Wang Y, Zhang L, Xia C. Sweet potato leaf detection in a natural scene based on faster R-CNN with a visual attention mechanism and DIoU-NMS. Ecol Inform. 2023 ; 73: 101931. http://doi.org/10.1016/j.ecoinf.2022.101931
Vilasini M, Ramamoorthy P. CNN Approaches for Classification of Indian Leaf Species Using Smartphones. Comput Mater Contin. 2020; 62(3): 1445–72. http://doi.org/10.32604/cmc.2020.08857
Yang HW, Hsu HC, Yang CK, Tsai MJ, Kuo YF. Differentiating between morphologically similar species in genus Cinnamomum (Lauraceae) using deep convolutional neural networks. Comput Electron Agric. 2019; 162: 739–48. http://doi.org/10.1016/j.compag.2019.05.003
Pereira CS, Morais R, Reis MJCS. Deep Learning Techniques for Grape Plant Species Identification in Natural Images. Sensors. 2019; 19(22): 4850. http://dx.doi.org/10.3390/s19224850
Kaya A, Keceli AS, Catal C, Yalic HY, Temucin H, Tekinerdogan B. Analysis of transfer learning for deep neural network based plant classification models. Comput Electron Agric. 2019 ; 158: 20–9. http://doi.org/10.1016/j.compag.2019.01.041
Asroni A, Ku-Mahamud KR, Damarjati C, Slamat HB. Arabic Speech Classification Method Based on Padding and Deep Learning Neural Network. Baghdad Sci J. 2021; 18(2(Suppl.)):0925–0925. http://doi.org/10.21123/bsj.2021.18.2 (Suppl.).0925
Dyrmann M, Karstoft H, Midtiby HS. Plant species classification using deep convolutional neural network. Biomater Biosyst. 2016; 151: 72–80 http://doi.org/10.1016/j.biosystemseng.2016.08.024
Tiwari S. A Comparative Study of Deep Learning Models with Handcraft Features and Non-Handcraft Features for Automatic Plant Species Identification: Int J Agric Environ Inf Syst 2020; 11(2): 44–57. http://doi.org/10.4018/IJAEIS.2020040104
Anubha Pearline S, Sathiesh Kumar V, Harini S. A study on plant recognition using conventional image processing and deep learning approaches. J Intell Fuzzy Syst. 2019; 36(3): 1997–2004. http://doi.org/ 10.3233/JIFS-169911
Brahimi M, Boukhalfa K, Moussaoui A. Deep Learning for Tomato Diseases: Classification and Symptoms Visualization. Appl Artif Intell. 2017; 31(4): 299–315. https://doi.org/10.1080/08839514.2017.1315516
Fadhil OY, Mahdi BS, Abbas AR. Using VGG Models with Intermediate Layer Feature Maps for Static Hand Gesture Recognition. Baghdad Sci J. 2023. http://doi.org/10.21123/bsj.2023.7364
Abdulmunem IA, Harba ES, Harba HS. Advanced Intelligent Data Hiding Using Video Stego and Convolutional Neural Networks. Baghdad Sci J. 2021. 18(4): 1317–1317. https://doi.org/10.21123/bsj.2021.18.4.1317
Lee SH, Chan CS, Mayo SJ, Remagnino P. How deep learning extracts and learns leaf features for plant classification. Pattern Recognition. 2017; 71:1–13. https://doi.org/10.1016/j.patcog.2017.05.015
Villaruz JA. Deep Convolutional Neural Network Feature Extraction for Berry Trees Classification. J Adv Inf Technol. 2021; 12(3): 226–33. https://doi.org/10.12720/jait.12.3.226-233
Dudi B. Medicinal Plant Recognition based on CNN and Machine Learning. Int J Adv Trends Comput Sci Eng. 2019; 8(4): 999–1003. https://doi.org/10.30534/ijatcse/2019/03842019
Koklu M, Unlersen MF, Ozkan IA, Aslan MF, Sabanci K. A CNN-SVM study based on selected deep features for grapevine leaves classification. Measurement. 2022; 188: 110425. https://doi.org/10.1016/j.measurement.2021.110425
Beikmohammadi A, Faez K. Leaf Classification for Plant Recognition with Deep Transfer Learning. In: 2018 4th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS). 2018. p. 21–6. http://dx.doi.org/10.1109/ICSPIS.2018.8700547
Huynh HX, Truong BQ, Nguyen Thanh KT, Truong DQ. Plant Identification Using New Architecture Convolutional Neural Networks Combine with Replacing the Red of Color Channel Image by Vein Morphology Leaf. Vietnam J Comput Sci. 2020; 07(02): 197–208. https://doi.org/10.1142/S2196888820500116
Liu J, Yang S, Cheng Y, Song Z. Plant Leaf Classification Based on Deep Learning. In: 2018 Chinese Automation Congress (CAC). 2018. p. 3165–9. https://doi.org/10.1109/CAC.2018.8623427
Pierre Barré, Ben C. Stöver, Kai F. Müller, Volker Steinhage. LeafNet: A computer vision system for automatic plant species identification. Ecol Inform. 2017; 40: 50–6. https://doi.org/10.1016/j.ecoinf.2017.05.005
Jeon WS, Rhee and SY. Plant Leaf Recognition Using a Convolution Neural Network. Int J Fuzzy Log Intell Syst. 2017; 17(1): 26–34. https://doi.org/10.5391/IJFIS.2017.17.1.26
Hassoon IM, Qassir SA, Riyadh M. PDCNN: FRAMEWORK for Potato Diseases Classification Based on Feed Foreword Neural Network. Baghdad Sci J. 2021. 18.2(Suppl.); 1012–1012. https://doi.org/10.21123/bsj.2021.18.2(Suppl.).1012
Tian K, Li J, Zeng J, Evans A, Zhang L. Segmentation of tomato leaf images based on adaptive clustering number of K-means algorithm. Comput Electron Agric. 2019; 165: 104962. https://doi.org/10.1016/j.compag.2019.104962
Peng Y, Zhao S, Liu J. Fused Deep Features-Based Grape Varieties Identification Using Support Vector Machine. Agriculture. 2021 ; 11(9): 869. https://doi.org/10.3390/agriculture11090869
Suh HK, IJsselmuiden J, Hofstee JW, van Henten EJ. Transfer learning for the classification of sugar beet and volunteer potato under field conditions. Biomater Biosyst. 2018; 174: 50–65. https://doi.org/10.1016/j.biosystemseng.2018.06.017
Sethy PK, Barpanda NK, Rath AK, Behera SK. Deep feature based rice leaf disease identification using support vector machine. Comput Electron Agric . 2020; 175: 105527. https://doi.org/10.1016/j.compag.2020.105527
Chan GCY, Muhammad A, Shah SAA, Tang TB, Lu CK, Meriaudeau F. Transfer learning for Diabetic Macular Edema (DME) detection on Optical Coherence Tomography (OCT) images. In: 2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA). 2017. p. 493–6. https://doi.org/10.1109/ICSIPA.2017.8120662