extremal region detection guided by maxima of gradient magnitude

thesis
abstract

a problem of computer vision applications is to detect regions of interest under dif- ferent imaging conditions. the state-of-the-art maximally stable extremal regions (mser) detects affine covariant regions by applying all possible thresholds on the input image, and through three main steps including: 1) making a component tree of extremal regions’ evolution (enumeration), 2) obtaining region stability criterion, and 3) cleaning up. mser performs very well, but, it does not consider any information about the boundaries of the regions which are important for detecting repeatable extremal regions. we have shown in this paper that employing prior information about boundaries of regions results in a novel region detector algorithm that not only outperforms mser, but avoids the mser’s rather complicated step of enumeration and the cleaning up. to employ the information about the region boundaries we introduce maxima of gradient magnitudes (mgms) which are shown to be points that are mostly around the boundaries of the regions. having found the mgms, the method obtains a global criterion (gc) for each level of the input image which is used to find extremum levels (els). the found els are then used to detect extremal regions. the proposed algorithm which is called extremal regions of extremum lev- els (erel) has been tested on the public benchmark dataset of mikolajczyk [111]. the obtained experimental results show that the proposed erel method is robust against gaussian noise and outperforms the state-of-the-art methods in terms of the accuracy of the repeatable detected regions.

similar resources

Detection of Iris in Image by Interrelated Maxima of Brightness Gradient Projections*

A method is proposed to detect a human iris location and size in a digital image given some point lying inside the pupil. Method is based on the construction of histogram projections of local brightness gradients, and interrelating local maxima of these histograms as probable positions of pupil and iris borders. The method has a low calculation cost.

full text

Multi - Scale Gradient Magnitude

A partitioning of an nD image is deened as the watersheds of some locally computable inhomogeneity measure. Dependent on the scale of the inhomogeneity measure a coarse or ne partitioning is deened. By analysis of the structural changes (catastrophes) in the measure introduced when scale is increased, an multi-scale linking of segments can be deened. This paper describes the multi-scale linking...

full text

Semiparametric estimation of the extremal index using block maxima∗

The extremal index θ, a measure of the degree of local dependence in the extremes of a stationary process, plays an important role in extreme value analyses. We estimate θ semiparametrically, using the relationship between the distribution of block maxima and the marginal distribution of a process to define a semiparametric model. We show that these semiparametric estimators are simpler and sub...

full text

An efficient semiparametric maxima estimator of the extremal index

Abstract The extremal index θ , a measure of the degree of local dependence in the extremes of a stationary process, plays an important role in extreme value analyses. We estimate θ semiparametrically, using the relationship between the distribution of block maxima and the marginal distribution of a process to define a semiparametric model. We show that these semiparametric estimators are simpl...

full text

Effects of temperature gradient magnitude on bending angle in laser forming process of aluminium alloy sheets

Laser forming is a thermal forming process which uses laser beam irradiation to produce the desired final forms. In this article, the effect of temperature gradient across  Al 6061-T6 aluminum sheets on bending angle is studied. Input parameters including laser power, scan velocity, beam diameter, and sheet thickness are the effective process parameters which influence the temperature gradient....

full text

A survey of K means Clustering with modified gradient magnitude region growing technique for lesion segmentation

Image segmentation is very useful in lesion segmentation which is needed for monitoring and quantifying Lesion. Automated lesion segmentation in CT/MRI poses many challenges with regard to characteristics of an image. Many techniques are involved to detect the lesion in the medical images such watershed, wavelet transform etc. In this paper, we are defining the modified k means cluster to segme...

full text

My Resources

Save resource for easier access later

Save to my library Already added to my library

{@ msg_add @}


document type: thesis

دانشگاه تربیت معلم - تهران - دانشکده فنی

Hosted on Doprax cloud platform doprax.com

copyright © 2015-2023