Conference Paper

Extracting license plates from images with 3-tier filter banks

Sabanci University, ─░stanbul, Istanbul, Turkey
DOI: 10.1109/SIU.2004.1338331 Conference: Signal Processing and Communications Applications Conference, 2004. Proceedings of the IEEE 12th
Source: IEEE Xplore


The purpose of this project is to extract the license plates from images which are taken from a camera system. Nowadays, there are many different applied methods which deal the problem of extracting plates. In this paper, the images are processed with 3- tier filter bank and successful results are taken. Gabor filters which have band-pass characteristics are preferred as filter bank. Instead of single filtering, a 3-tier filtering system with different variances is applied.

Download full-text


Available from: Aytul Ercil, Dec 23, 2013
8 Reads
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Clusters of microcalcifications which appear like small white grains of sand on mammograms are the earliest signs of breast cancer. In this work we employ a Gabor filter bank for texture analysis of mammograms to detect microcalcifications. A subset of the Gabor filter bank with a certain central frequency and different orientations is used to obtain the Gabor-filtered images. The filtered images are then subjected to a histogram based threshold to obtain binary images. Feature vectors are computed using the binary images. A k-means clustering algorithm with a variance scaled Euclidean distance is used for segmentation of the image
    Image Processing, 2000. Proceedings. 2000 International Conference on; 01/2000
  • [Show abstract] [Hide abstract]
    ABSTRACT: The identification of mutations in ABCA1 in patients with Tangier disease and familial HDL deficiency demonstrated that inadequate transport of phospholipid and cholesterol to the extracellular space results in the hypercatabolism of lipid-poor nascent HDL particles. However, the relationship between changes in ABCA1 activity and HDL levels is not clear. To address this question directly in vivo, we have used bacterial artificial chromosome transgenic approaches, which allow for appropriate developmental and cellular localization of human ABCA1 in mouse tissues. Increased expression of ABCA1 is directly associated with an increase in HDL levels, and the relationship between the increase in efflux and HDL is completely linear (r2 = 0.87). Preliminary data have suggested that coronary artery disease (CAD) is increased in heterozygotes for ABCA1 deficiency. These results may have been biased by clinical sampling, and CAD end points are insensitive markers. We have now used surrogate end points of intima-media complex thickness (IMT) and have shown that mean IMT in ABCA1 heterozygotes is indeed increased. A strong correlation between adjusted IMT and HDL cholesterol values and apolipoprotein A-I-driven efflux has been established. These studies suggest that compromised ABCA1 activity leads to accelerated and early atherogenesis and provides a link between the cholesterol deposition in macrophages within the arterial wall and cholesterol efflux in humans.
    The Journal of Lipid Research 12/2001; 42(11):1717-26. · 4.42 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Observational studies provide overwhelming evidence that a low high-density lipoprotein (HDL)-cholesterol level increases the risk of coronary events, both in healthy subjects and in patients with coronary heart disease. Based on in vitro experiments, several mechanistic explanations for the atheroprotective function of HDL have been suggested. However, few of these were verified in vivo in humans or in experiments with transgenic animals. The HDL functions currently most widely held to account for the antiatherogenic effect include participation in reverse cholesterol transport, protection against endothelial dysfunction, and inhibition of oxidative stress. This review summarizes current views on the molecular mechanism underlying these atheroprotective effects of HDL.
    Annual Review of Medicine 02/2003; 54(1):321-41. DOI:10.1146/ · 12.93 Impact Factor
Show more