Object recognition in image sequences with cellular neural networks

Milanova, Mariofanna; Büker, Ulrich

doi:10.1016/s0925-2312(99)00177-0

Cited by 22 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In application, u l;k usually comes from the initialization of the CNN, and always keeps its value without any change all the time. For instance, it is initialized using the grey-scale values of the pixels in the image processing [23]. Similarly, in the alignment algorithm of this paper it will be initialized using the numerical codes of the DNA sequences.…”

Section: The Designed One-dimensional Pairwise Cnnmentioning

confidence: 99%

“…During the past decades, most research work on CNNs focused on two main fields. One is on CNN theories, such as the stability analysis [3][4][5][6][7], the convergence analysis [8], the chaos [9,10] and the improved CNN models [11][12][13][14][15]; another is on CNN applications, such as the hardware implementations [16][17][18], the image processing [19][20][21], the pattern recognition [22,23] and the associative memories [24][25][26].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

One-dimensional pairwise CNN for the global alignment of two DNA sequences

et al. 2015

Neurocomputing

View full text Add to dashboard Cite

Section: The Designed One-dimensional Pairwise Cnnmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

One-dimensional pairwise CNN for the global alignment of two DNA sequences

et al. 2015

Neurocomputing

View full text Add to dashboard Cite

“…Successful applications of CNNs have been presented in many scientific fields such as image processing, associative memory and medical science [2][3][4][5], etc. In the design of CNNs for these applications, it is sometimes necessary to ensure the asymptotic stability of equilibrium points.…”

Section: Introductionmentioning

confidence: 99%

Guaranteed Cost Stabilization of Time-varying Delay Cellular Neural Networks via Riccati Inequality Approach

2011

Neural Process Lett

View full text Add to dashboard Cite

This letter deals with the guaranteed cost stabilization of time-varying delay cellular neural networks (DCNNs). Based on the Razumikhin theorem and via applying the zoned discussion and maximax synthesis method in DCNNs, the quadratic Riccati matrix inequality criterion for the guaranteed cost stabilization controller is designed to stabilize the given chaotic DCNNs. The minimization of the guaranteed cost of stabilization for the DCNNs is also given. Finally, numerical examples are given to show the effectiveness of proposed guaranteed cost stabilization control and its corresponding minimization problem.

show abstract

“…A CNN consists of a network of first order nonlinear circuits, locally interconnected by linear (resistive) connections. CNNs have been extensively used in image processing applications (Matsumoto & Yokohama, 1990) such as filtering, edge detection, character recognition (Szirànyi & Csicsvàri, 1993) and object recognition (Milanova & Buker, 2000). Thanks to their architecture they can be applied to inherently parallel problems in which traditional methods cannot achieve a high throughput (Manganaro et al, 1999).…”

Section: Introductionmentioning

confidence: 99%