This paper describes the continuing development of a system for tracking multiple man made objects, (typically vehicles) moving in a natural open world scene, where the detected m...
We present a data-driven approach to predict the importance of edges and construct a Markov network for image analysis based on statistical models of global and local image feature...
In this paper, a colour text/graphics segmentation is proposed. Firstly, it takes advantage of colour properties by computing a relevant hybrid colour model. Then an edge detectio...
Motivated by the observation that coarse and fine resolutions of an image reveal different structures in the underlying visual phenomenon, we present a model based on the Deep B...
In this paper we use concepts from the lattice-based theory of morphological operators and fuzzy sets to develop generalized lattice image operators that can be expressed as nonli...
Petros Maragos, Vassilis Tzouvaras, Giorgos B. Sta...