Automatic design of pulse coupled neurons for image segmentation

Berg, Henrik; Olsson, Roland; Lindblad, Thomas; Chilo, José

doi:10.1016/j.neucom.2007.10.018

Cited by 41 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of recent papers had been proposed an algorithm for automatically parameter setting [20] [21]. One of these algorithms is based on the evaluation of PCNN's output and reflects its evaluation to the parameters.…”

Section: Automatic Adjustment Methods For the Parameters In Pcnnmentioning

confidence: 99%

See 1 more Smart Citation

An Automatic Parameter Adjustment Method of Pulse Coupled Neural Network for Image Segmentation

Yonekawa

Kurokawa

2009

Artificial Neural Networks – ICANN 2009

View full text Add to dashboard Cite

Abstract.A Pulse Coupled Neural Network (PCNN) is proposed as a numerical model of cat visual cortex, and it has been applied to the engineering fields especially in an image processing, e.g., segmentation, edge enhancement, and so on. The PCNN model consists of neurons with two kind of inputs, namely feeding input and linking input and they each have a lot of parameters. The Parameters are used to be defined empirically and the optimization of parameters has been known as one of the remaining problem of PCNN. According to the recent studies, parameters in PCNN will be able to be given using parameter learning rule or evolutionary programming. However these methods require teaching images for the learning. In this study, we propose a parameter adjustment method of PCNN for the image segmentation. The proposed method changes the parameters through the iterations of trial of segmentation and the method doesn't require any teaching signal or teaching pattern. The successful results are obtained in the simulations, and we conclude that the proposed method shows good performance for the parameter adjustment of PCNNs.

show abstract

Section: Automatic Adjustment Methods For the Parameters In Pcnnmentioning

confidence: 99%

“…Also, in recent studies, automatically parameter setting algorithm has been proposed using a scheme of evolutionary programming [21]. These parameters and structure adaptation algorithm achieve successful results for the aim of parameter setting.…”

Section: Introductionmentioning

confidence: 99%

An Automatic Parameter Adjustment Method of Pulse Coupled Neural Network for Image Segmentation

Yonekawa

Kurokawa

2009

Artificial Neural Networks – ICANN 2009

View full text Add to dashboard Cite

show abstract

“…However, original PCNN suffers from massive feedback iterations, various parameter adjustments and computational complexity [7][8] . Visual saliency, being closely related to how visual system focuses attention on important parts and processes visual stimulus, is investigated by multiple disciplines including cognitive psychology, neurobiology and computer vision [9][10] .…”

Section: Sm-pcnn Modelmentioning

confidence: 99%

Saliency motivated pulse coupled neural network for underwater laser image segmentation

Wang

Wan

2016

J. Shanghai Jiaotong Univ. (Sci.)

View full text Add to dashboard Cite

The detection range of underwater laser imaging technology achieves 4-6 times of detection range of conventional camera in intervening water medium, which makes it very promising in oceanic research, deep sea exploration and robotic works. However, the special features in underwater laser images, such as speckle noise and non-uniform illumination, bring great difficulty for image segmentation. In this paper, a novel saliency motivated pulse coupled neural network (SM-PCNN) is proposed for underwater laser image segmentation. The pixel saliency is used as external stimulus of neurons. For improvement of convergence speed to optimal segmentation, a gradient descent method based on maximum two-dimensional Renyi entropy criterion is utilized to determine the dynamic threshold. On the basis of region contrast in each iteration step, the real object regions are effectively distinguished, and the robustness against speckle noise and non-uniform illumination is improved by region selection. The proposed method is compared with four other state-of-the-art methods which are watershed, fuzzy C-means, meanshift and normalized cut methods. Experimental results demonstrate the superiority of our proposed method to allow more accurate segmentation and higher robustness. Key words: underwater laser image, pulse coupled neural network, pixel saliency, region contrast CLC number: TP 183 Document code: A IntroductionThere are quite limited means of detecting objects in underwater environment. Acoustic and optical imaging technologies are conventional methods. However, the spatial resolution of acoustic images is pretty low, while light is severely scattered and absorbed by water medium, and optical images often degrade seriously [1] . One of the most effective solutions to above problems is to apply underwater laser imaging technology.The attenuation of blue-green light, whose spectrum wavelength is between 470 and 580 nm, is much less than that of light in other bands. Underwater laser imaging technology takes advantage of this phenomenon, adopts blue-green pulsed laser generator as an illuminator and range gated charge-coupled device (CCD) camera, effectively suppresses the backscattering and achieves a detection range of 4-6 times of conventional camera in intervening water medium [2] . However, due to absorption and scattering of water medium, as well as the laser pulse stretching, the characteristics in underwater laser images, such as speckle noise [3] , blur effect and non-uniform illumination [4] , have brought great difficulty for underwater laser image segmentation. Conventional segmentation algorithms, such as statistical, graph-based and morphological methods, show high sensitivity to these characteristics and always give inaccurate segmentation results. For instance, the fuzzy C-means and watershed methods are sensitive to speckle noise; the mean-shift method shows robustness against noise, but its performance is seriously decreased by non-uniform illumination. The uncertainty in weighted undirected graph (WUG) of norm...

show abstract

“…THE ADATE SYSTEM FOR AUTOMATIC PROGRAMMING ADATE (Automatic Design of Algorithms Through Evolution) [27] is a system for evolving programs in a purely functional subset of the programming language Standard ML [28]. It is a general system that has successfully been applied to a wide variety of programming tasks, like evolving standard textbook algorithms from scratch [29], learning simple natural languages [30], improving existing classification algorithms [31] and evolving better neurons for automatic image segmentation [32]. To evolve a solution to a problem, the system needs a specification file that defines data types and auxiliary functions, a number of training and validation input examples, and an evaluation function that is used to grade and select potential solutions during evolution.…”

Section: Related Workmentioning

confidence: 99%

“…We showed the potential use of this approach in [32], where neurons used for image segmentation were automatically evolved based on a standard neuron model from the literature. It is likely that such an approach would also yield good results for problems within the field of automatic control.…”

Section: Conclusion and Further Workmentioning

confidence: 99%

Automated synthesis of control algorithms from first principles

Berg

Olsson

Rusås

et al. 2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

A variety of machine learning techniques have been employed to automatically create control algorithms for autonomous vehicles. Much research has focused on various "black box" approaches, in which the synthesized or learned control algorithms perform well when tested, but are difficult or impossible to analyze and understand. This paper presents the use of the ADATE system to evolve a control algorithm based on a racing car simulator. The system evolved compact and analyzable yet sophisticated control algorithms capable of driving millions of randomly generated tracks at high speeds without ever driving off the road. The approach presented is likely to be applicable to most automatic control problems, given a set of training examples and a suitable software simulator.

show abstract

Automatic design of pulse coupled neurons for image segmentation

Cited by 41 publications

References 17 publications

An Automatic Parameter Adjustment Method of Pulse Coupled Neural Network for Image Segmentation

An Automatic Parameter Adjustment Method of Pulse Coupled Neural Network for Image Segmentation

Saliency motivated pulse coupled neural network for underwater laser image segmentation

Automated synthesis of control algorithms from first principles

Contact Info

Product

Resources

About