Estimate the aesthetic quality of images in order to predict their impact


Image search engines receive huge volumes of images every day, but very few of these have any impact on the internet. Of course, the aesthetics and technique of images are key to ensuring they have an impact on the internet and are not overlooked. The challenge of this project is therefore to develop tools for analysing and predicting the technical and aesthetic quality of images.


An international company and GCD@UB are working on the design of a system to estimate the technical and aesthetic quality of images. This project is being carried out using deep learning networks and large volumes of data with tags related to aesthetics.



Advertising and marketing companies, as well as individual users, are constantly seeking the best images for their projects. Automatically estimating the quality of an image and predicting its impact can help us make decisions about marketing and the economic value of images.

Related Articles

Predictive model of biomechanical pathologies diagnosis

cat. Projects

Invalcor is a center specialized in the functional assessment of the locomotor system that by means of advanced technology objective aspects such as the measure of the mobility, strength, power, resistance, or fatigue of a damaged body region. The company is interested in designing a prediction system that, based on the historical data of its activity, attends the diagnosis work to doctors.

Measuring collaboration in organisations

cat. Consulting

This project consisted of the development of a tool for learning about the different relationships between the members of an organisation and their areas of work. The group-level analysis provides a real-time diagnosis and makes it possible to take actions to improve and streamline processes.

Price forecasting model

cat. Consulting

People who manage services aimed at the general public have the option of designing a demand-driven pricing policy, but this design is usually based on the personal experience of each manager.