AI Cannot Understand Memes: Experiments with OCR and Facial Emotions

Author(s)Priyadarshini, Ishaani
Author(s)Cotton, Chase
Date Accessioned2021-12-13T19:57:39Z
Date Available2021-12-13T19:57:39Z
Publication Date2021-05-11
DescriptionThis article was originally published in Computers, Materials & Continua. The version of record is available at:
AbstractThe increasing capabilities of Artificial Intelligence (AI), has led researchers and visionaries to think in the direction of machines outperforming humans by gaining intelligence equal to or greater than humans, which may not always have a positive impact on the society. AI gone rogue, and Technological Singularity are major concerns in academia as well as the industry. It is necessary to identify the limitations of machines and analyze their incompetence, which could draw a line between human and machine intelligence. Internet memes are an amalgam of pictures, videos, underlying messages, ideas, sentiments, humor, and experiences, hence the way an internet meme is perceived by a human may not be entirely how a machine comprehends it. In this paper, we present experimental evidence on how comprehending Internet Memes is a challenge for AI. We use a combination of Optical Character Recognition techniques like Tesseract, Pixel Link, and East Detector to extract text from the memes, and machine learning algorithms like Convolutional Neural Networks (CNN), Region-based Convolutional Neural Networks (RCNN), and Transfer Learning with pre-trained denseNet for assessing the textual and facial emotions combined. We evaluate the performance using Sensitivity and Specificity. Our results show that comprehending memes is indeed a challenging task, and hence a major limitation of AI. This research would be of utmost interest to researchers working in the areas of Artificial General Intelligence and Technological Singularity.en_US
SponsorThe authors received no specific funding for this study.en_US
CitationPriyadarshini, Ishaani, and Chase Cotton. "AI Cannot Understand Memes: Experiments with OCR and Facial Emotions." CMC-COMPUTERS MATERIALS & CONTINUA 70, no. 1 (2022): 781-800.en_US
PublisherComputers, Materials & Continuaen_US
KeywordsTechnological singularityen_US
Keywordsoptical character recognitionen_US
Keywordstransfer learningen_US
Keywordsconvolutional neural networks (CNN)en_US
Keywordsregion-based convolutional neural networks (RCNN)en_US
TitleAI Cannot Understand Memes: Experiments with OCR and Facial Emotionsen_US
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
AI Cannot Understand Memes Experiments with OCR and Facial Emotions.pdf
1.33 MB
Adobe Portable Document Format
Main article
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
124 B
Item-specific license agreed upon to submission