Material Segmentation for Visual Aware Recommender Systems
Darmstadt, TU, Master Thesis, 2021
People nowadays have the possibility to get recommendations for almost anything based on things they previously purchased or liked. These recommendations are often based on categories, simple colors, or other user interactions. This work presents a different approach by using precise material recognition to recommend furniture as well as clothes. These so called visual aware recommender systems are fairly unknown and have only recently gained attention. A visual aware recommender system extracts visual features from its input and uses these features to recommend accordingly. One of the biggest advantages is that these systems do not suffer from the cold start problem that many modern recommender systems have, since they do not require any other information except the visual input. In order to use material information for recommendations, precise semantic segmentation is required. Therefore, the two best performing state-of-the-art neural networks for this task are compared and evaluated, while the better model is then used in the recommender system. Performance is demonstrated by using not just one approach, but two approaches. One uses a user study to evaluate the performance gain compared to a recommender system without material recognition, and the other uses expert data known to be true to evaluate the total precision on a real live task. Both of them confirm the assumption that material recognition not only works, but also substantially improves recommendation performance especially on certain combinations.
Face Presentation Attack Detection in Ultraviolet Spectrum via Local and Global Features
Conference on Biometrics and Electronic Signatures (BIOSIG) <19, 2020, Online>
GI-Edition - Lecture Notes in Informatics (LNI), P-306
The security of the commonly used face recognition algorithms is often doubted, as they appear vulnerable to so-called presentation attacks. While there are a number of detection methods that are using different light spectra to detect these attacks this is the first work to explore skin properties using the ultraviolet spectrum. Our multi-sensor approach consists of learning features that appear in the comparison of two images, one in the visible and one in the ultraviolet spectrum. We use brightness and keypoints as features for training, experimenting with different learning strategies. We present the results of our evaluation on our novel Face UV PAD database. The results of our method are evaluated in an leave-one-out comparison, where we achieved an APCER/BPCER of 0%/0.2%. The results obtained indicate that UV images in presentation attack detection include useful information that are not easy to overcome.
Visually-aware Recommendation System for Interior Design
Darmstadt, TU, Bachelor Thesis, 2020
Suitable recommendations are critical for a successful e-commerce experience, especially for product categories such as furniture. A well thought-out choice of furniture is decisive for the visual appearance and the comfort of a room. Interior design can take much time and not everyone is capable to do it. Some furniture stores offer recommendation systems on their website, which are usually based on collaborative filters that are very restrictive, can be inaccurate and require many data at first. This work aims to develop a method to provide set recommendations that adhere to a cohesive visual style. The method can automatically advise the user on what set of furniture to choose for a room around one seed piece. The proposed system uses a database where learned attributes of the dataset are previously stored. Once the user select a seed, the system extracts the attributes from the image to execute a query in the database. Finally, a visual search performed in the filtered subset will return the best candidates. This way has the advantage to receive the results faster and to reduce the searching space thereby improving efficiency. The system is presented that is both powerful and efficient enough to give useful user-specific recommendations in real-time.