Multi-resolution image registration using genetics

Chalermwat, Prachya; El‐Ghazawi, Tarek

doi:10.1109/icip.1999.822937

Cited by 21 publications

(18 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For fast segmentation, we firstly formulate the segmentation approach in a 3-level multi-resolution framework, which has been widely used to increase the speed of the algorithms in the literature [7,8]. For example, the original TRUS image is decomposed into three multi-resolution images, i.e.…”

Section: Methodsmentioning

confidence: 99%

An Efficient Method for Deformable Segmentation of 3D US Prostate Images

Zhan

Shen

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We previously proposed a deformable model for automatic and accurate segmentation of prostate boundary from 3D ultrasound (US) images by matching both prostate shapes and tissue textures in US images [6]. Textures were characterized by a Gabor filter bank and further classified by support vector machines (SVM), in order to discriminate the prostate boundary from the US images. However, the step of tissue texture characterization and classification is very slow, which impedes the future applications of the proposed approach in clinic applications. To overcome this limitation, we firstly implement it in a 3-level multi-resolution framework, and then replace the step of SVMbased tissue classification and boundary identification by a Zernike momentbased edge detector in both low and middle resolutions, for fast capturing boundary information. In the high resolution, the step of SVM-based tissue classification and boundary identification is still kept for more accurate segmentation. However, SVM is extremely slow for tissue classification as it usually needs a large number of support vectors to construct a complicated separation hypersurface, due to the high overlay of texture features of prostate and non-prostate tissues in US images. To increase the efficiency of SVM, a new SVM training method is designed by effectively reducing the number of support vectors. Experimental results show that the proposed method is 10 times faster than the previous one, yet without losing any segmentation accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

An Efficient Method for Deformable Segmentation of 3D US Prostate Images

Zhan

Shen

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…For example, [6,17] employed a down-sampling mechanism. Chalermwat et al produced a low-resolution version of the image with a method inspired by discrete wavelet transforms and reduced the image size to 32 by 32 [6]. In Jacq's work [17], a stochastic sub-sampling of the image space was used.…”

Section: Image Registration Using Evolutionary Computationmentioning

confidence: 99%

“…Experiments were performed using artificial images and X-ray scans. Thereafter, continuous effort has been devoted and successful research on genetic algorithms-based image registration has been reported [6,25,26,36,38]. Jacq et al explored 3D volume-to-volume registration and surface-to-volume registration and proposed a canonical genetic algorithm based approach [17].…”

Section: Image Registration Using Evolutionary Computationmentioning

confidence: 99%

“…To search the transformation function space, previous research was based on weighted absolute error or correlation of the images [6,11,17,25,26,36,38], which, in some cases, resulted in an increasing number of local optima and thus made convergence difficult. The average number of generations needed to achieve convergence was in the hundreds, but in extreme cases [10], it could be thousands.…”

Section: Image Registration Using Evolutionary Computationmentioning

confidence: 99%

See 1 more Smart Citation

Evolution strategies based image registration via feature matching

2004

View full text Add to dashboard Cite

“…Thus the problem becomes that of finding the best among all the possible transformations, each of which is represented by a set of real parameters. Evolutionary Algorithms (EAs) [9,10] are successfully used to face several multivariable optimization tasks and their use has been introduced in Image Registration as well, in particular in the medical [11,12] and in the remote sensing [13][14][15][16] areas. Therefore we employ them to find the optimal combination of the parameter values involved in the affine transformation.…”

Section: Introductionmentioning

confidence: 99%

Distributed Differential Evolution for the Registration of Remotely Sensed Images

Falco¹,

Maisto²,

Scafuri³

et al. 2007

15th EUROMICRO International Conference on Parallel, Distributed and Network-Based Processing (PDP'07)

View full text Add to dashboard Cite

Abstract. This paper deals with the design and implementation of a software system based on Differential Evolution for the registration of images, and in its testing by means of a set of bidimensional remotely sensed images on two problems, i.e. mosaicking and changes in time. Registration is carried out by finding the most suitable affine transformation in terms of maximization of the mutual information between the first image and the transformation of the second one, without any need for setting control points. A comparison is effected against a publicly available tool, showing the effectiveness of our method.

show abstract

Multi-resolution image registration using genetics

Cited by 21 publications

References 10 publications

An Efficient Method for Deformable Segmentation of 3D US Prostate Images

An Efficient Method for Deformable Segmentation of 3D US Prostate Images

Evolution strategies based image registration via feature matching

Distributed Differential Evolution for the Registration of Remotely Sensed Images

Contact Info

Product

Resources

About