Human perception of image quality is a complex process that is still not fully understood. In the specific case of human faces, this quality plays a fundamental role in various processes, such as the effectiveness of facial recognition.
On the other hand, automatic systems based on artificial neural networks perform this evaluation through quantitative metrics, which analyse specific aspects of the image, often without fully capturing the subjective perception of humans. Recent studies indicate that there is a significant discrepancy between human perceptual evaluation, based on cognitive mechanisms, and quantitative metrics, which mainly rely on the pixels of the images, without reflecting the visual experience. Thus, algorithms struggle to align the definition of quality with human perception.
This project seeks to deepen the understanding of these differences by exploring human perception of image quality through the evaluation of average opinions. To do so, different types of distortion, such as JPEG compression, motion blur, among others, will be analysed.
You are about to participate in a research study. The data you provide during this study (gender, age, academic degree, country of origin) will be used for research purposes within the scope of a Bachelor's Project in Biomedical Engineering. Your participation is voluntary, and all information provided will be kept confidential.
In this test, you will evaluate the visual quality of a series of individual images. For each image, you will assign a score based on its perceived quality using a predefined scale. Please read the instructions carefully before starting.