Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: image feature extraction

Sortuj według:

Ogranicz wyniki do:

Investigation of opacity development in the human eye for estimation of the postmortem interval

Cantürk İ., Çelik S., Feyzi Şahin M., Yağmur F., Kara S., Karabiber F.

Biocybernetics and Biomedical Engineering

2017

Vol. 37, no. 3

559--565

Estimation of the postmortem interval (PMI) has attracted the attention of many researchers. It is generally accepted as a challenging task in forensic medicine. Due to its difficulty, researchers have tried to estimate the PMI using different physical and chemical techniques. Since the PMI estimation accuracies of previous studies are not at the desired level, new methods should be developed to more accurately estimate the PMI. The development of opacity in the eye in the PMI might be an important breakthrough in this field. After death, corneal hydration occurs due to degenerated endothelial cells. The degenerated endothelial barrier of the cornea cannot prevent the flow of aqueous humor to the cornea, which results in opacity. The amount of aqueous humor in the cornea determines the level of opacity. Since the flow of aqueous humor to the cornea will continue for a while, opacity is expected to increase with the PMI. In this study, images of human eyes were investigated using computer-based image analysis. The corneal and non-corneal opacities of the recorded eye images increase during the experiment. The experimental results prove that there is a correlation between the elapsed time after death and the development of opacity in the corneal and non-corneal regions in human cases. Exponential curve fitting is employed to observe the decay of the opacity over time. A repeated ANOVA test is also used to show that the opacity development is statistically significant.

Fast image auto-annotation with discretized feature distance measures

Kwasnicka H., Paradowski M.

Machine Graphics and Vision

2006

Vol. 15, No. 2

123-140

A new model for the image auto-annotation task is presented. The model can be classified as a fast image auto-annotation one. The main idea behind the model is to avoid various problems with feature space clustering. Both the image segmentation and the auto-annotation process do not, use any clustering algorithms. The method presented here simulates continuous feature space analysis with very dense discretization. The paper presents the new approach and discusses the results achieved with it.