With the popularity of information sharing services from Twitter (X), Facebook, Instagram, among others, the use of visual media is becoming a pervasive communication channel that allows expression and active participation. Unfortunately, massive diffusion on social media and its versatility on digital formats offers clear opportunities to manipulate the content.
There is still a tremendous need to automatically verify that the statements accompanying an image or a video are true before the content becomes viral. To add forces to the fact-checking combat, Google contributed the tool About this image that allows to get the WHEN, WHERE (Find Image Source) and HOW of an uploaded photo. This would get us the information whether or not it is original material (something we could trust or not) or the clear alert that it is a fake or manipulated image. This feature can be used directly from Google Image results.
We tested the option using a picture created from our previous blog “Towards Factuality Assessment“, using Google image search. Although it did find similar images, it did not find the exact match of the created image. Furthermore, we explore the use of the option Text.
The Text option allows to select some text in the image, then Google search performs an OCR (optical character recognition) followed by a search of the selected recovered text. To our happy surprise it did find the page of our post.
This open tool offers to all of us the opportunity to get more information about an image to have the information needed to analyze and potentially make a decision on whether or not to continue reading the accompanying content.
Dairazalia Sanchez-Cortes, PhD
Dairazalia Sanchez-Cortes is currently working as a Postdoctoral Researcher at the Idiap Research Institute in Switzerland. She joined the Speech and Audio Processing Group in 2023. She holds a PhD in Sciences from the EPFL’s School of Engineering. Her research interests include machine learning, human activity modeling, nonverbal behavior and applied research.
Sergio Burdisso, PhD
Sergio Burdisso is currently a Postdoctoral Researcher at Idiap research institute in Switzerland. He's actively collaborating with Dr. Petr Motlicek in the Speech and Audio Processing Group. Sergio holds a Ph.D. in Computer Science specialized in Natural Language Processing applied to Early Risk Identification on Social Media. His main research interests include topics such as interpretable machine learning, few-shot learning, and representation learning for dialogue modeling.
Dr. Petr Motlicek
Petr Motlicek has been a research scientist in the Speech and Audio Processing Group since 2005 at the Idiap Research Institute in Switzerland. His research activities are focused on audio and speech processing technologies (voice coding and recognition, and speaker recognition), conversation analysis and machine learning. Many of the designed applications are developed in collaboration with security/government (LEA) bodies in Switzerland, or at the EU level. He has significantly contributed to Kaldi- open-source software developed for speech and speaker recognition tasks, with many new libraries for signal processing being provided by Idiap.
