Skip to content

Do you recognise me?

Share on facebook
Facebook
Share on twitter
Twitter
Share on linkedin
LinkedIn

By Julia Farrugia

Automatic facial recognition could change the world of law enforcement. Profile photos of suspects are rarely available, so investigators still rely on face sketches based on eyewitness descriptions. Julia Farrugia (supervised by Dr Ing. Reuben Farrugia) implemented an automatic face recogniser that is able to retrieve a photo based on a sketch. This narrows down the number of potential criminals before trails start to go cold.

Photos used with permission: X. Wang and X. Tang, “Face Photo-Sketch Synthesis and Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 31, 2009
Photos used with permission: X. Wang and X. Tang, “Face Photo-Sketch Synthesis and Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 31, 2009

Sketches and photos have different natures (modalities)—photos are generally captured using a digital camera, while sketches may be hand-drawn or computer generated. In order to tackle this problem, Farrugia developed an inter-modal approach to sketch retrieval. Without changing the nature (modality) of the images, common features in the sketch and photo were used as a basis for retrieval. Testing was carried out using the Chinese University of Hong Kong (CUHK) student database, which contains 188 photo-sketch pairs.

The implementation makes use of an Active Orientation Model (AOM), which is freely available. 68 strategic points on a query sketch and suspect photo are plotted. Dots depict features like eyebrows, hairline, and nose. The distance was calculated between the respective points on the sketch and photo. The smaller the difference in distances, the closer the match. 55.85% of tests resulted in a correct match between sketch and photo. To improve these results, texture features of the query sketch and each photo in the dataset were extracted using Local Binary Patterns (LBP). The distance was again calculated but included the texture features. The results were then merged with the distances obtained using the AOM method. Giving a higher priority to the distances obtained using the texture features increased the recognition rate to 60.11%.

Results could be improved by filtering the photos according to gender and by experimenting on larger datasets with subjects from different ethnicities, wearing glasses, or having facial hair. Advancements in computer vision means that soon humans will not be the only eyes narrowing down possible suspects.


This research was carried out as part of a Bachelor of Science in Computer Engineering at the Faculty of ICT, University of Malta.

Author

More to Explore

Fostering Creativity and Community: The ART Connect Project at the University of Malta Library

The Library is, in many ways, the beating heart of the University of Malta (UM). The pulse of intellectual life can be felt most profoundly amongst the quiet shelves lined with books and the many students and academics lining the Library’s work desks with their noses deep in their projects. In this sense, the Library is also symbolic of the University’s overall health and vitality, so it is important to balance serious work with serious play.

The evolution of the ART Connect Project has been a journey of dedication and transformation. Inspired by the vision of new librarians and a desire to revamp the Library’s decor, what was once a seed of an idea has now matured into a vibrant platform for artistic expression, collaboration, and community building.

The ART Connect Project aims to connect people through creativity, foster collaboration, and transform spaces, inviting artists and art enthusiasts to celebrate the power of art.

Meeting Challenges Halfway at the Malta Book Festival 2023

Malta boasts 58 registered publishing entities, hosting hundreds of authors writing books across a wide swathe of genres and formats. These numbers emerge from an NSO survey into the book industry, conducted on the basis of the year 2021. Effectively, we could say that there are ‘more authors than churches’ in Malta, with over 700 authors populating the National Book Council’s database.

This hints at a varied industry, the stakeholders of which all fall under the remit of the National Book Council, which seeks to assist, support, and represent Maltese authors and publishers, as well as related industry stakeholders such as translators and illustrators. While the Maltese context does have its own particularities, neither is it immune to the industry’s wider, global realities, a case in point being the price hike on paper caused by the war in Ukraine, which continues to be felt across the board. Maltese publishers must also bear the brunt of this unfortunate phenomenon.

The National Book Council continues to advocate for increased governmental support to aid publishers, whether in this particular challenge or others, and it also offers direct financial aid through the Malta Book Fund, which last year issued a grand total of €120,000 to various industry stakeholders, targeting projects of high cultural value which may not have a straightforward route to market success.

But while some challenges may be met halfway through financial incentives, others require a systemic — or cultural — shift in attitude from all parties involved, which takes a certain degree of workshopping to be borne out. The slow uptake of ebooks bears pondering (the NSO survey saw 146 new ebooks issued in Malta in 2021, contrasted with printed counterparts of 418 in the same year), as does the worryingly high number of authors published without adequate contracts in place.

Maximising Solar Panel Efficiency: The DustPV Project

The DustPV project, led by Prof. Ing. Joseph Micallef, aims to determine the optimal timing for cleaning solar panels using innovative sensor technology and weather data analysis. By addressing the challenges of dust accumulation on photovoltaic panels, the project seeks to enhance solar panel performance and contribute to Malta’s renewable energy goals.

No comment yet, add your voice below!


Add a Comment