Decoding the Visual Realm: Machine Learning Approaches for Discriminating AI-Generated and Real Fruits
Keywords:
Image classification, AI-generated images, Real fruits, Transfer learning, InceptionV3, Data augmentation, Stratified data splitting, Model evaluation, Accuracy, Precision, Recall, Confusion matrix, Qualitative analysis, Visual interpretation, Machine learning in computer vision, Data preprocessing, Data augmentation, Model training Model checkpointing, TensorFlow, Kera’s, Neural network architecture, Convolutional Neural Network (CNN), ImageDataGenerator, Training history, Checkpointing, Evaluation metrics, Test set, Validation set, Training set, Deep learning, Image recognition, Data splitting, Model performance, Classification report, Confusion matrix, Random image sampling, Interpretability, Research paper, Code implementation, Collab notebook.Abstract
In recent years, the (AI) has witnessed a surge in applications across various domains. This research paper focuses on the classification of images depicting AI-generated fruits and real fruits, exploring the potential techniques in distinguishing between the two categories. The dataset used in this study comprises. images of AI-generated fruits and their real counterparts. To address this classification task, we leverage transfer learning with the InceptionV3 architecture as a feature extractor. The model is. trained on a carefully curated dataset, encompassing diverse classes and variations of both AI-generated. and real fruits. A robust data augmentation strategy is employed during training to enhance the models. generalization capabilities. The dataset is split into training, testing, and validation sets using a stratified. approach, ensuring a balanced distribution of classes across each subset. The trained model is evaluated on. the test set, and its performance is assessed using metrics such as accuracy, precision, recall, and the confusion matrix. Additionally, the research presents a detailed analysis of the model's predictions by visualizing randomly selected images from the test dataset. This qualitative assessment aims to provide. insights into the model's decision-making process and its ability to correctly classify AI-generated and real. fruit images. The experimental results showcase the effectiveness of the proposed approach in accurately. discriminating between AI-generated and real fruits. The classification performance is discussed in terms of both quantitative metrics and qualitative interpretations of model predictions. The research contributes to the understanding of AI-generated images' distinct characteristics and the challenges associated with their classification. In conclusion, this study sheds light on the applicability of machine learning models, specifically InceptionV3, in distinguishing between AI-generated and real fruits. research can find applications in image classification tasks involving synthetic and authentic visual data, paving the way for advancements in the field of AI generated content analysis.
Downloads
References
Meyer, David Wayne. "Find the Real: A Study of Individuals’ Ability to Differentiate Between Authentic Human Faces and Artificial-Intelligence Generated Faces." International Conference on Human-Computer Interaction. Cham: Springer Nature Switzerland, 2022.
Köbis, Nils, and Luca D. Mossink. "Artificial intelligence versus Maya Angelou: Experimental evidence that people cannot differentiate AI-generated from human-written poetry." Computers in human behavior 114 (2021): 106553.
Gao, Catherine A., et al. "Comparing scientific abstracts generated by ChatGPT to original abstracts using an artificial intelligence output detector, plagiarism detector, and blinded human reviewers." BioRxiv (2022): 2022-12.
An, Ruopeng, et al. "Use prompt to differentiate text generated by ChatGPT and humans." Machine Learning with Applications 14 (2023): 100497.
Partadiredja, Reza Arkan, Carlos Entrena Serrano, and Davor Ljubenkov. "AI or human: the socio-ethical implications of AI-generated media content." 2020 13th CMI Conference on Cybersecurity and Privacy (CMI)-Digital Transformation-Potentials and Challenges (51275). IEEE, 2020.
Chen, Junyu, et al. "Learning to Evaluate the Artness of AI-generated Images." arXiv preprint arXiv:2305.04923 (2023).
Göring, Steve, et al. "Analysis of Appeal for realistic AI-generated Photos." IEEE Access (2023).
Brynjolfsson, Erik, and A. N. D. R. E. W. Mcafee. "Artificial intelligence, for real." Harvard business review 1 (2017): 1-31.
Gao, Catherine A., et al. "Comparing scientific abstracts generated by ChatGPT to real abstracts with detectors and blinded human reviewers." NPJ Digital Medicine 6.1 (2023): 75.
Maerten, Anne-Sofie, and Derya Soydaner. "From paintbrush to pixel: A review of deep neural networks in AI-generated art." arXiv preprint arXiv:2302.10913 (2023).
Chen, Junyu, et al. "How Art-like are AI-generated Images? An Exploratory Study." Proceedings of the 1st International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice. 2023.
Ragot, Martin, Nicolas Martin, and Salomé Cojean. "Ai-generated vs. human artworks. a perception bias towards artificial intelligence?" Extended abstracts of the 2020 CHI conference on human factors in computing systems. 2020.
Clune, Jeff. "AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence." arXiv preprint arXiv:1905.10985 (2019).
Ma, Yongqiang, Jiawei Liu, and Fan Yi. "Is this abstract generated by ai? research for the gap between ai-generated scientific text and human-written scientific text." arXiv preprint arXiv:2301.10416 (2023).
Balacheff, Nicolas. "Artificial intelligence and real teaching." Learning from computers: Mathematics education and technology. Berlin, Heidelberg: Springer Berlin Heidelberg, 1993. 131-158.
Gragnaniello, Diego, Francesco Marra, and Luisa Verdoliva. "Detection of AI-Generated Synthetic Faces." Handbook of Digital Face Manipulation and Detection: From DeepFakes to Morphing Attacks. Cham: Springer International Publishing, 2022. 191-212.
Gu, Jinjin, et al. "AI-enabled image fraud in scientific publications." Patterns 3.7 (2022).
Fei, Jianwei, et al. "Exposing AI-generated videos with motion magnification." Multimedia Tools and Applications 80 (2021): 30789-30802.
Saponara, Sergio, Abdussalam Elhanashi, and Alessio Gagliardi. "Implementing a real-time, AI-based, people detection and social distancing measuring system for Covid-19." Journal of Real-Time Image Processing (2021): 1-11.
Yang, Zuhao, et al. "AI-Generated Images as Data Source: The Dawn of Synthetic Era." arXiv preprint arXiv:2310.01830 (2023).
Mindner, Lorenz, Tim Schlippe, and Kristina Schaaff. "Classification of Human-and AI-Generated Texts: Investigating Features for ChatGPT." International Conference on Artificial Intelligence in Education Technology. Singapore: Springer Nature Singapore, 2023.
Bird, Jordan J., and Ahmad Lotfi. "CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images." arXiv preprint arXiv:2303.14126 (2023).
Elkhatat, Ahmed M., Khaled Elsaid, and Saeed Almeer. "Evaluating the efficacy of AI content detection tools in differentiating between human and AI-generated text." International Journal for Educational Integrity 19.1 (2023): 17.
Dugan, Liam, et al. "Real or fake text? Investigating human ability to detect boundaries between human-written and machine-generated text." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 37. No. 11. 2023.
Nguyen, Trung T., Amartya Hatua, and Andrew H. Sung. "How to Detect AI-Generated Texts?." 2023 IEEE 14th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON). IEEE, 2023.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
