Three registration methods, based on direct matching of pixel intensities, principal axes matching and circular profile matching, were proposed and objectively evaluated on real, large and representative image database (1634 images) of various tablets. Comparing against a gold standard registration and considering execution times, circular profile matching method proved useful for visual quality inspection of imprinted tablets in real time. The paper will be published in a SCI journal with the impact factor of 1.485, which ranks in the 2nd quarter in the field of electrical engineering.
COBISS.SI-ID: 6533972
We proposed three methods for automatic analysis and description of product surfaces, namely by geometrical, statistical and nonparametrical statistical appearance models, which enable classification of defective and nondefective products. The paper was published in a SCI journal with the impact factor of 1.485, which ranks in the 2nd quarter in the field of electrical engineering.
COBISS.SI-ID: 6029140
We developed a novel real-time segmentation method for grey-level images that is based on border tracking. The proposed method was designed to be accurate, robust, and computationally undemanding. The performances of the method were objectively assessed on a large number of simulated and real tablet images. The obtained results indicated high reliability, accuracy, and speed. The paper will be published in a SCI journal with the impact factor of 1.485, which ranks in the 2nd quarter in the field of electrical engineering.
COBISS.SI-ID: 7260500
A new method for accelerated aging and evaluation of temporal degradation of LED intensity and color was developed. The method enables LED lifetime prediction, which is important for long-term stability of LED illuminations and thereby for high-quality dynamic illumination of the inspected objects. The paper was published in a SCI journal with a high impact factor of 1.297, which ranks in the 1st quarter in the field of interdisciplinary applications.
COBISS.SI-ID: 5635412
A thorough analysis of LED quality-affecting factors and methods for their assessments was conducted. These are the methods for the estimation of initial variabilities of optical and electrical properties of LEDs, the methods for estimation of temperature stability of optical and electrical properties, and the methods for spectral degradation prediction, which are assessed in terms of accuracy, applicability and specificity. The paper was published in a SCI journal with a high impact factor of 1.297, which ranks in the 1st quarter in the field of interdisciplinary applications.
COBISS.SI-ID: 6788692