Object comparison using PDE‐based wave metric on cellular neural networks

Szatmári, István

doi:10.1002/cta.361

Cited by 13 publications

(7 citation statements)

References 25 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was shown that the gray-scale wave metric condense both metrics and combines all advantages of the previously mentioned two methods [2]. This in itself would motivate the usage of this method, moreover it has additional benefits.…”

Section: B Hausdorff Distancementioning

confidence: 97%

Topographie metrics for image segmentation

Horváth

Hillier

2010

2010 12th International Workshop on Cellular Nanoscale Networks and Their Applications (CNNA 2010)

View full text Add to dashboard Cite

Algorithms designed for machine vision applications such as medical imaging, surveillance, etc., very often require some kind of comparison between images. While the brain can compare complex objects with ease, the same is usually a very difficult task for algorithm designers. Comparison between objects requires a proper definition of a metric that determines the similarity of the objects. This paper briefly investigates the problems about commonly used metrics (Hamming, Hsausdorff), and shows another method: the nonlinear wave metric, describing its advantages, and its application in practice.

show abstract

Section: B Hausdorff Distancementioning

confidence: 97%

Topographie metrics for image segmentation

Horváth

Hillier

2010

2010 12th International Workshop on Cellular Nanoscale Networks and Their Applications (CNNA 2010)

View full text Add to dashboard Cite

show abstract

“…We set the MCNN parameters according to (21) (trigger wave), as a 0 =1 and a 1 =0.25. We set the MCNN parameters according to (21) (trigger wave), as a 0 =1 and a 1 =0.25.…”

Section: Texture Segmentation Using Twin Wave Principlementioning

confidence: 99%

“…CNN-UM-based wave computing is a new kind of logic or reasoning that is applicable in parallel and allows researchers to study natural phenomena in diverse fields of physics, chemistry, biology, and so on. Using this method, new types of algorithms can be utilized for robot navigation [19], automated detection of a Modular Cellular Neural Network Structure for Wave-Computing-Based Image Processing Mojtaba Karami, Reza Safabakhsh, and Mohammad Rahmati preseizure state [20], target detection [21], object comparison [22], learning of spatiotemporal behavior [23], and auditory scene analysis [24]. Using this method, new types of algorithms can be utilized for robot navigation [19], automated detection of a Modular Cellular Neural Network Structure for Wave-Computing-Based Image Processing Mojtaba Karami, Reza Safabakhsh, and Mohammad Rahmati preseizure state [20], target detection [21], object comparison [22], learning of spatiotemporal behavior [23], and auditory scene analysis [24].…”

Section: Introductionmentioning

confidence: 99%

Modular Cellular Neural Network Structure for Wave-Computing-Based Image Processing

Karami¹,

Safabakhsh²,

Rahmati³

2013

ETRI J

View full text Add to dashboard Cite

This paper introduces the modular cellular neural network (CNN), which is a new CNN structure constructed from nine one-layer modules with intercellular interactions between different modules. The new network is suitable for implementing many image processing operations. Inputting an image into the modules results in nine outputs. The topographic characteristic of the cell interactions allows the outputs to introduce new properties for image processing tasks. The stability of the system is proven and the performance is evaluated in several image processing applications. Experiment results on texture segmentation show the power of the proposed structure. The performance of the structure in a real edge detection application using the Berkeley dataset BSDS300 is also evaluated.

show abstract

“…More complex tasks can be implemented by template algorithms that can be described by UMF diagrams, containing several template and logic instructions [9]. Numerous recent publications have shown the effective use of the cellular wave computer architecture for parallel image-processing tasks [10][11][12][13].…”

Section: Perception and The Analog-logic Cellular Nonlinear Network Vmentioning

confidence: 99%

Cellular wave computer algorithms with spatial semantic embedding for handwritten text recognition

Karacs

PrÃ3szÃ©ky

Roska

2008

Circuit Theory & Apps

View full text Add to dashboard Cite

The recognition of cursive handwritten texts is a complex, in some cases unsolvable, task. One problem is that in most cases it is difficult or impossible to identify each letter, even if the words are separated. In our new method, the identification of letters is not needed due to the extensive and iterative use of semantic and morphological information of a given language. We are using a spatial feature code, generated by a cellular nonlinear network (CNN) based cellular wave computer algorithm, and combine it with the linguistic properties of the given language. Most general-purpose handwriting recognition systems lack the ability to integrate linguistic background knowledge because they use it only for post-processing recognition results. The high-level a priori background knowledge is, however, crucial in human reading and similarly it can boost recognition rates dramatically in case of recognition systems. In our new system we do not treat the visual source as the only input: geometric and linguistic information are given equal importance. On the geometric side we use word-level holistic feature detection without letter segmentation by analogic CNN algorithms designed for cellular wave computers (IEEE Trans. A novel shape coding method is used to interface them, and their interaction is enhanced via an inverse filtering technique based on features that are global or of a low confidence value. A statistical context selection method is also applied to further reduce the output word lists.

show abstract

Object comparison using PDE‐based wave metric on cellular neural networks

Cited by 13 publications

References 25 publications

Topographie metrics for image segmentation

Topographie metrics for image segmentation

Modular Cellular Neural Network Structure for Wave-Computing-Based Image Processing

Cellular wave computer algorithms with spatial semantic embedding for handwritten text recognition

Contact Info

Product

Resources

About