Darijan Marcetic

Learn More
This paper describes a knowledge-based system for the non-destructive diagnostics of fac ade isolation. The system uses the fusion of information extracted from images obtained from two electromagnetic wavebands: from low-resolution IR images (320 240 pixels; 7.5–13 lm wavelength), and from highresolution visual RGB images (3264 2448 pixels; 0.39–0.75(More)
Many techniques in the area of 3D face recognition rely on local descriptors to characterize the surface-shape information around points of interest (or keypoints) in the 3D images. Despite the fact that a lot of advancements have been made in the area of keypoint descriptors over the last years, the literature on 3D-face recognition for the most part still(More)
Undesired low-frequency self-sustained speed oscillations are encountered in fan, compressor and pump drives utilizing open-loop frequency-controlled induction motor drives. Discontinuous rectifier current at light loads and the dead-time of the inverter switches are the main sources of such oscillations. This paper proposes a concise analytical method to(More)
In this paper, we propose a two-stage model for unconstrained face detection. The first stage is based on the normalized pixel difference (NPD) method, and the second stage uses the deformable part model (DPM) method. The NPD method applied to in the wild image datasets outputs the unbalanced ratio of false positive to false negative face detection when the(More)
In this paper, we propose modifications of deformable part-based models in order to increase the robustness of face detection under occlusion. The modifications are: i) the tree, representing the deformable part-based model of the frontal face, which is partitioned into 11 subtrees representing face components; ii) the weight of each face component which is(More)
This paper presents a hierarchical heterogeneous knowledge-base model. The model is designed to support manipulation with human knowledge about real or abstract concepts from the real world that are uncertain, ambiguous, vague and fuzzy. It has two levels: a lower associative and a higher semantic. It enables processing of novel concepts in the inheritance(More)
This paper describes a model of a hierarchical, heterogeneous knowledge-base. The proposed model consists of an associative level that is implemented by a Kanerva-like sparse distributed memory (SDM) and a semantic level realized by a knowledge-representation scheme based on the Fuzzy Petri Net theory. The levels are interconnected with forward and backward(More)