Indonesian Journal of Electrical Engineering and Computer Science Vol. 29, No. 2, February 2023, pp. 1030~1038 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v29.i2.pp1030-1038  1030 Journal homepage: http://ijeecs.iaescore.com Identifying corn leaves diseases by extensive use of transfer learning: a comparative study Ahmed Samit Hatem 1 , Maha Sabri Altememe 2 , Mohammed Abdulraheem Fadhel 3 1 Department of Basic Sciences, College of Nursing, University of Kerbala, Kerbala, Iraq 2 Department of Computer Sciences, College of Computer Science and Information Technology, University of Kerbala, Kerbala, Iraq 3 College of Computer Science and Information Technology, University of Sumer, Thi Qar, Iraq Article Info ABSTRACT Article history: Received Jul 1, 2022 Revised Oct 12, 2022 Accepted Oct 20, 2022 Deep learning is currently playing an important role in image analysis and classification. Diseases in maize diminish productivity, which is a major cause of economic damages in the agricultural business throughout the world. Researchers have previously utilized hand-crafted characteristics to classify images and identify leaf illnesses in Maize plants. With the advancement of deep learning, researchers can now significantly enhance the accuracy of object classification and identification. Using the "Corn or Maize Leaf Disease Dataset" from the Kaggle website, four forms of maize leaf diseases were investigated: blight, common rust, gray leaf spot, and healthy. The pictures obtained from these corn leaf illnesses are categorized using four deep convolutional neural network (CNN) models that have been pre-trained (GoogleNet, AlexNet, ResNet50 and VGG16). Accuracy, precision, specificity, recall, F-score, and time are the six metrics used to assess the performance of any transfer learning (TL) model. MATLAB programming software is used to design and train the TL models. The accuracy of each item in the dataset has been checked. It has been determined that GoogleNet, AlexNet, VGG16, and ResNet50 each have an accuracy of 98.57%, 98.81%, 99.05%, and 99.36%, respectively. Keywords: Convolutional neural network Corn diseases Pretrained model ResNet50 Transfer learning This is an open access article under the CC BY-SA license. Corresponding Author: Ahmed Samit Hatem Department of Basic Sciences, College of Nursing, University of Kerbala Kerbala, Iraq Email: ahmed.samit@uokerbala.edu.iq 1. INTRODUCTION The maize crop is among the most adaptable new agricultural crops, allowing it to thrive in a variety of agro-climatic situations. After rice and wheat, it is the third most important agricultural product. Maize is the two most common grown cereal crop, earning it the title of "Queen of Cereals." It has an energy density of 3365 Kcal/kg and comprises 10.11% protein, 79.95% starch, and 4.19% fat. During the kharif season, maize is mostly grown in highland areas. Maize is a mixture of lemon yellow, and gamboge in hue. The internal diversity of maize is its distinguishing trait. Different varieties of maize, such as popcorn, grain maize, baby corn and sweet corn are mostly grown in India. The maize crop is susceptible to a variety of diseases as well as crop-eating insects. Maize leaf diseases mostly result in lower yields and economic losses for farmers. Machine and deep learning are both defined in a layered structure in artificial intelligence. Significant applications [1]-[3] and methods are currently increasing the demand for artificial intelligence (AI) approaches. The use of AI approaches in the health field has shown promising results, such as the identification of malaria cells [4]. The study of plant diseases and their severity