Domen Tabernik, BSc
+386 1 479 8245
We propose a novel deep network architecture that combines the benefits of discriminative deep learning and the benefits of compositional hierarchies. As one of the benefits we emphasize the ability to automatically adjust receptive fields to either small or large receptive fields depending on the for problem at hand and the ability to visualize deep features through explicit compositional structure.
We explore deep learning models for industrial quality control. Our focus is on surface-defect detection for which we have developed a novel two-stage architecture that uses segmentation network in the first stage and decision network in the second stage. We also present a novel dataset with real-case scenario for surface defect detection. This research is done in collaboration with the industry partner Kolektor Group d.o.o.
We explore automation of traffic-sign inventory management using deep-learning models. Models such as Faster R-CNN and Mask R-CNN are improved and applied to traffic sign detection. Instead of specializing in automated detection for only several traffic sign categories we explore possibility of automating the detection of over 200 different traffic signs that are needed to automate the traffic-sign inventory management.
ViCoS Eye is an experimental online service that aims to demonstrate a state-of-the-art computer vision object detection and categorization algorithm developed in our laboratory. Web-service is available in a form of a web-page and in a form of an Android application.
As extension to LHOP model we have developed a shape descriptor capable of using compositional parts learnt using LHOP model to provide a descriptor that is compatible with HOG descriptor and can be easily used as direct replacement.
We deal with a problem of Multi-class Object Representation and present a framework for learning a hierarchical shape vocabulary capable of representing objects in hierarchical manner using a statistically important compositional shapes. The approach takes simple oriented contour fragments and learns their frequent spatial configurations. These are recursively combined into increasingly more complex and class specific shape compositions, each exerting a high degree of shape variability