Cellular neural networks and active contours: a tool for image segmentation

Vilariño, D.L.; Cabello, D.; Pardo, Xosé M.; Brea, V.M.

doi:10.1016/s0262-8856(02)00153-1

Cited by 40 publications

(36 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PLS [2][3][4][5] is an evolved version of the original snake algorithm. In PLS algorithm, two forces from the internal energy and the external potential are calculated, and the motion of the curve is determined at the pixel level by the dominant force between these two forces.…”

Section: Contour-expansion Version Of Ca-based Plsmentioning

confidence: 99%

“…The conventional PLS algorithm [2][3][4][5] is based on a CNN [8]. A CNN is a kind of neural network whose connectivity is only restricted to adjoining cells.…”

Section: Contour-expansion Version Of Ca-based Plsmentioning

confidence: 99%

“…In Ref. [2][3][4][5], PLS was implemented on CNN-dedicated hardware, and this implementation achieved high-speed parallel processing.…”

Section: Contour-expansion Version Of Ca-based Plsmentioning

confidence: 99%

“…The active contour method (or also known as the "snake" algorithm) is one of the methods for object extraction [1]. "Pixel-level snakes" (PLS) [2][3][4][5] is a kind of snake algorithm. As for PLS, the development of the active contours is governed by a balance of two forces: one from an internal energy of the active contours and one from an external potential of a processing image.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Method Using CA-Based Pixel-Level Snakes for Multiple-Contour Expansion

Fujita

Iwanaga

et al. 2014

Journal of Signal Processing

View full text Add to dashboard Cite

One of the variations of the active-contour method, namely, multiple-contour expansion, is realized on cellular automaton (CA)-based pixel-level snakes (CA-based PLS). As for the PLS algorithm, the active contour steps to next pixel one by one. The processing speed of PLS thus depends on image size. In the case of the multiple-contour-expansion method, the contours are successively deformed, their topology is transformed, and objects are extracted from images. The advantage of this method is that the processing speed does not depend on image size. It was experimentally demonstrated that multiple contour expansion is made possible by the CA-based PLS and that the processing speed of PLS does not depend on image size.

show abstract

Section: Contour-expansion Version Of Ca-based Plsmentioning

confidence: 99%

“…The conventional PLS algorithm [2][3][4][5] is based on a CNN [8]. A CNN is a kind of neural network whose connectivity is only restricted to adjoining cells.…”

Section: Contour-expansion Version Of Ca-based Plsmentioning

confidence: 99%

“…In Ref. [2][3][4][5], PLS was implemented on CNN-dedicated hardware, and this implementation achieved high-speed parallel processing.…”

Section: Contour-expansion Version Of Ca-based Plsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Method Using CA-Based Pixel-Level Snakes for Multiple-Contour Expansion

Fujita

Iwanaga

et al. 2014

Journal of Signal Processing

View full text Add to dashboard Cite

show abstract

“…The seminal fully-operational approach (PLSv1) is addressed in [1]. PLSv1 retains the structure of Fig.1.…”

Section: Introductionmentioning

confidence: 99%

Evolution of Pixel Level Snakes towards an efficient hardware implementation

Vilariño

Dudek

2007

2007 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Abstract-Since Pixel Level Snakes (PLS) were introduced, several algorithms implementing this cellular active contour technique have been proposed. In this paper, we review the main features of these algorithms and propose some modifications to optimize the computation performance of PLS when they are executed on fine-grain pixel-parallel processor arrays. The modified algorithm has been implemented on a focal plane cellular processor array (SCAMP-3 vision chip) and tested on several applications of practical interest.

show abstract

Split and shift methodology on cellular processor arrays: area saving versus time penalty

Fernandez

Brea

Cabello

2012

Circuit Theory & Apps

View full text Add to dashboard Cite

This paper addresses the so-called split and shift methodology. This methodology deals with the implementation of kernels of sizes that go above the physically implemented resources (local connections and weighting circuits) on synchronous cellular processor arrays (CPA), including the realization of large neighborhood operations and/or the reduction of the available hardware in order to drop the area consumption. Two main goals are pursued in the development of the methodology, namely: (1) minimum penalty at processing time and (2) absolutely no penalty at functional level. The paper presents different techniques and guidelines for the methodology application and introduces a Figure of Merit to evaluate them by relating area gains with time penalty. This, along with a kernel shape analysis, led us to propose more adequate configurations of weighting circuits and to justify the classical choice of North-East-West-South connectivity. To validate the methodology, we realize several estimates over actual physical implementations, and we propose the realization over CPAs of the spin filters, scale invariant feature transform and speeded-up robust features algorithms. A more in-depth trade-off analysis is realized over the implementation of the pixel level snakes algorithm.but it can interact with separated PEs, thanks to the propagative effects of the array dynamics of kernel application. The basic characteristic of local connectivity and its simple SIMD control makes this kind of systems very suitable for hardware implementation. However, as a consequence, the natural size of the kernels to be applied is limited to the smallest one (3 Â 3). This is, on the other hand, an important limitation in the functionality of a CPA as larger neighborhoods are needed in several image processing primitives as diffusion or low-pass filtering operations [1], halftoning [2], texture analysis [3] or matching and hit&miss operations [4], some of them used in algorithms like modern scale-and rotation-invariant feature extractors like scale invariant feature transform (SIFT) and speeded-up robust features (SURF) [5,6].As indicated, a CPA can realize global processing taking into account the whole image information thanks to the propagative effects of the architecture. According to this we can think in solving the remote neighbors interaction through the recursive application of templates. In fact, a recursive process can be summarized in the application of a large neighborhood (LN) template. Nevertheless, the inverse process, the decomposition of a LN template into minimum-sized templates is not trivial, and different approaches have been developed to deal with this issue.The challenge is then to implement any kind of LN operations while keeping the local connectivity and with affordable penalties in performance. Our goal is to do it, in addition, with the minimum impact in the architecture at hardware level.On the other hand, on focal-plane processors with a pixel-to-PE assignment, the area occupation is not only a matter of cost or h...

show abstract

Cellular neural networks and active contours: a tool for image segmentation

Cited by 40 publications

References 29 publications

A Method Using CA-Based Pixel-Level Snakes for Multiple-Contour Expansion

A Method Using CA-Based Pixel-Level Snakes for Multiple-Contour Expansion

Evolution of Pixel Level Snakes towards an efficient hardware implementation

Split and shift methodology on cellular processor arrays: area saving versus time penalty

Contact Info

Product

Resources

About