Recognition multifrequency microwave images of simple objects behind dielectric wall using neural networks

Drobakhin, O. O.; Sherstyuk, G. G.

doi:10.1109/msmw.2013.6622099

Cited by 5 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A key problem is discrimination with size estimation. Neural networks are a powerful tool for object recognition [3][4][5]. The problem is to obtain a reflected signal for a set of objects with various diameters with small step in a comparatively simple way for network training.…”

Section: Introductionmentioning

confidence: 99%

Dielectric cylinder discrimination with ANN using phase information of synthesized time-domain response

Drobakhin,

Chuchva

2023

J. Phys. Electron.

View full text Add to dashboard Cite

The application of the three-component stacked artificial neural network (ANN) for discrimination of dielectric cylinders of different diameters using phase information of synthesized time-domain response is considered. The network consists of two sparse autoencoders and the softmax unit. Neural networks are not tied to the frequency range, unlike many well-known methods based on the resonant properties of objects, and they are a powerful tool for object recognition. In contrast to well-known results, information about the phase of the time-domain signal, which is synthesized from multi-frequency data, is used for discrimination. For ANN training, phase images for cylinders with the radius of 15 to 35 mm are obtained using the method of auxiliary sources (MAS) The possibility of successful recognition was confirmed for the case of the diameter deviation of 1 mm and the presence of additive Gaussian noise with SNR of up to 0 dB.

show abstract

Section: Introductionmentioning

confidence: 99%

Dielectric cylinder discrimination with ANN using phase information of synthesized time-domain response

Drobakhin,

Chuchva

2023

J. Phys. Electron.

View full text Add to dashboard Cite

show abstract

“…The multifrequency approach allows for each transverse position x to obtain a distance portrait of the object scanned along the longitudinal coordinate y. Application of recognition technologies based on neural networks can provide additional possibilities for object discrimination [3]. Some sources of noise and distortion are uncontrolled [5].…”

Section: Introductionmentioning

confidence: 99%

Improvement of resolution in aperture synthesis in near zone of radiation based on the application of the Prony’s method

Drobakhin

Olevskyi

2018

JPhysElectron

View full text Add to dashboard Cite

Applicability of inverse filtering with evolution control for reconstruction of images obtained by aperture synthesis technique is considered. A horn antenna, which is moved in the transversal direction, is used in order to obtain a 2-dimensional image. Scanned structure consists of one or two similar metaplates. In the latter case the plates are coplanar and their common plane is parallel to the aperture of the antenna. Regularisation coefficients are found with the help of trial and error method. The image of a single plate was used to tune the software. The Prony’s method is tested as a separate way of estimation of the distance between the plates. Both methods are tested for a range of different distances between the plates and between the plates’ common plane and aperture of the antenna. It is shown that inverse filtration tends to provide better results if the scanned object is situated further from the antenna. Said method was proven to be precise enough to distinguish closely-spaced plates. The Prony’s method was proven to provide reliable distance measurements if it was tuned correctly.

show abstract

Verification of applicability in space domain of the inverse filtering with evolution control for reconstruction of images obtained by radar scanning

Drobakhin¹,

Olevskyi²

2018

AIP Conference Proceedings

View full text Add to dashboard Cite

Recognition multifrequency microwave images of simple objects behind dielectric wall using neural networks

Cited by 5 publications

References 3 publications

Dielectric cylinder discrimination with ANN using phase information of synthesized time-domain response

Dielectric cylinder discrimination with ANN using phase information of synthesized time-domain response

Improvement of resolution in aperture synthesis in near zone of radiation based on the application of the Prony’s method

Verification of applicability in space domain of the inverse filtering with evolution control for reconstruction of images obtained by radar scanning

Contact Info

Product

Resources

About