Majlesi Journal of Electrical Engineering Fire Detection and Verification using Convolutional Neural Networks, Masked Autoencoder and Transfer Learning Volume 16 (2022) Issue 4, December 2022 2024 02 11 Fire Detection and Verification using Convolutional Neural Networks, Masked Autoencoder and Transfer Learning 10.30486/mjee.2023.1977460.1055 EN Zainab Abed Almoussawi College of Islamic Science, Ahl Al Bayt University Raed Khalid Department of Medical Instruments Engineering Techniques, Al-Farahidi University, Baghdad, Iraq Zahraa Salam Obaid Building and Construction Engineering Technology Department, AL-Mustaqbal University College Zuhair I. Al Mashhadani Al-Nisour University College, Baghdad, Iraq Kadhum Al-Majdi Department of Biomedical Engineering, Ashur University College, Baghdad, Iraq Refad E. Alsaddon Department of Prosthetic Dental Technology, Hilla University college, Babylon, Iraq Hassan Mohammed Abed Mazaya University College, Iraq Journal Article 2024 02 11 Wildfire detection is a time-critical application since it can be challenging to identify the source of ignition in a short amount of time, which frequently causes the intensity of fire incidents to increase. The development of precise early-warning applications has sparked significant interest in expert systems research due to this issue, and recent advances in deep learning for challenging visual interpretation tasks have created new study avenues. In recent years, the power of deep learning-based models sparked the researcher’s interests from a variety of fields. Specially, Convolutional Neural Networks (CNN) have become the most suited approach for computer vision tasks. As a result, in this paper we propose a CNN-based pipeline for classifying and verifying fire-related images. Our approach consists of two models, first of which classifies the input data and then the second model verifies the decision made by the first one by learning more robust representations obtained from a large masked auto encoder-based model. The verification step boosts the performance of the classifier with respect to false positives and false negatives. Based on extensive experiments, our approach proves to improve previous state-of-the-art algorithms by 3 to 4% in terms of accuracy.