Mr. Vladimir A. Franc Profile

Vladimir A. Franc

SPIE Involvement:

Author

Publications (13)

Proceedings Article | 15 June 2023 Poster + Paper

Weather removal with a lightweight quaternion Chebyshev neural network

Vladimir Frants, Sos Agaian

Proceedings Volume 12526, 125260V (2023) https://doi.org/10.1117/12.2664858

KEYWORDS: Rain, Tunable filters, Neural networks, Image processing, Adverse weather, Transformers, Education and training, Convolution, Computer vision technology, Air contamination

Read Abstract +

Proceedings Article | 27 May 2022 Poster + Paper

3D shape object reconstruction with non-Lambertian surface from multiple views based on deep learning

V. Voronin, V. Frantc, E. Semenishchev, M. Zhdanova, A. Zelensky, S. Agaian

Proceedings Volume 12100, 121000S (2022) https://doi.org/10.1117/12.2623130

KEYWORDS: Neural networks, Optical properties, Light sources and illumination, Structured light, Reflection, Reconstruction algorithms

Read Abstract +

The 3-D reconstruction is relative to constructing a mathematical representation of the scene geometric. In most existing approaches, Lambert's law of the object reflectivity in the scene is explicitly or implicitly assumed. In practice, the law of reflectivity of scene objects differs from Lambert's law as, for example, objects with properties: semi-transparent, transparent, specular, with subsurface scattering effects. This paper proposes an algorithm to estimate a surface reflectance model of 3-D shape and parameters from multiple views. The proposed algorithm includes the following steps: 1) determination of the optical properties of the scanned scene by separating the direct and global lighting components using high-frequency templates; 2) generation of a set of patterns of structured light, the structure of which depends on the optical properties of the scanned scene; 3) scanning the scene using the generated structured light patterns for views non- Lambertian surface; 4) construction of a 3-D model of the scene by triangulating methodology. To solve the problem of determining the views non-Lambertian surface, a 3-D reconstruction algorithm based on a convolutional neural network is proposed. To train the neural network, we apply two stages. At the first stage, the encoder is trained for the descriptor description of the input image. In the second step, a fully connected neural network is added to the encoder for regression for choosing the best views. The coder is trained using the generative adversarial methodology to construct a descriptor description that stores spatial information and information about the optical properties of surfaces located in different areas of the image. The codec network is trained to recover the defect map (depends directly on the sensor and scene properties) from a color image. The architecture of the neural network (generator) is based on the U-Net architecture. As a result, this method uses non-Lambertian properties, and it can compensate for triangulation reconstruction errors caused by viewdependent reflections. Experimental results on both synthetic and real objects are given.

Proceedings Article | 23 April 2020 Presentation + Paper

Dermoscopic image segmentation based on modified GrabCut with octree color quantization

Vladimir Frants, Sos Agaian

Proceedings Volume 11399, 113990K (2020) https://doi.org/10.1117/12.2556699

KEYWORDS: Image segmentation, Skin, Image processing algorithms and systems, Quantization, Computing systems, Skin cancer, Light sources, Image processing, Image analysis, Computer aided diagnosis and therapy

Read Abstract +

Proceedings Article | 21 May 2019 Paper

Video quality assessment using generative adversarial network

V. Voronin, V. Franc, A. Zelensky, S. Agaian

Proceedings Volume 10993, 109930S (2019) https://doi.org/10.1117/12.2519575

KEYWORDS: Video, Image quality, Neural networks, Video processing, Convolutional neural networks, Human subjects

Read Abstract +

Video related technology has grown rapidly due to the progress of digital devices such as virtual reality, 3D cameras, 3D films, and 3D display and Internet. During video acquisition and processing (compression, transmission, and reproduction) they may suffer some types of distortions which lead degradation and has a direct effect on the subjective sensation about human eyes. Moreover, the subjective evaluation is boring, time-consuming, and we do not have a specialist to do this kind of work. So, it is necessary to evaluate the quality of the videos by computers. Which means that the video quality evaluation/assessment has become vital. The goal of video quality assessment is to predict the perceptual quality for improving the performance of practical video application systems. In other words, the users’ experience is worse, so we need a metric to measure the distortions. The commonly used videos’ quality assessment methods: a) consider the video as a sequence of two-dimensional images and the videos’ quality assessment (scores) computing by weighted averaging of per frames (2D images) score, which conflicts with the fact that a video signal is a 3D volume and which ignores the movement features, b) are designed for specific distortions (for example blockiness and blurriness). In this paper, we present a novel deep learning architecture for no-reference video quality assessment. It based on a 3D convolutional neural network and generative adversarial network (GAN). We evaluate the proposed approach on the LIVE, ECVQ, TID2013 and EVVQ databases. Computer simulations show that the proposed video quality assessment: a) get convergence on a small amount of data, b) more “universal”- it can be used for different video quality degradation, including denoising, deblocking, deconvolution, and c) outperforms existing no-reference video quality assessment/methods. In addition, we demonstrate how our predicted no-reference quality metric correlates with qualitative opinion in a human observer study.

Proceedings Article | 13 April 2018 Paper

A no-reference image and video visual quality metric based on machine learning

Vladimir Frantc, Viacheslav Voronin, Evgenii Semenishchev, Maxim Minkin, Aliy Delov

Proceedings Volume 10696, 106961Y (2018) https://doi.org/10.1117/12.2309517

KEYWORDS: Video, Visualization, Image quality, Video compression, Machine learning, Roentgenium, Visual compression, Image compression, Image visualization, Convolutional neural networks

Read Abstract +

Proceedings Article | 9 June 2016 Paper

Separate texture and structure processing for image compression

V. Frantc, S. Makov, V. Voronin, V. Marchuk, I. Svirin

Proceedings Volume 9874, 98740T (2016) https://doi.org/10.1117/12.2223628

KEYWORDS: Image compression, Visualization, Wavelet transforms, Associative arrays, Wavelets, Image processing, Image quality standards, Image quality, Quantization, Discrete wavelet transforms

Read Abstract +

Proceedings Article | 26 May 2016 Paper

Simultenious binary hash and features learning for image retrieval

V. Frantc, S. Makov, V. Voronin, V. Marchuk, E. Semenishchev, K. Egiazarian, S. Agaian

Proceedings Volume 9869, 986902 (2016) https://doi.org/10.1117/12.2223605

KEYWORDS: Convolutional neural networks, Binary data, Image retrieval, Neural networks, Feature extraction, Associative arrays, Visualization, Content based image retrieval, Medical imaging, Image processing

Read Abstract +

Proceedings Article | 19 May 2016 Paper

Video stabilization using space-time video completion

V. Voronin, V. Frantc, V. Marchuk, I. Shrayfel, N. Gapon, S. Agaian

Proceedings Volume 9869, 986908 (2016) https://doi.org/10.1117/12.2220378

KEYWORDS: Video, Video processing, Motion estimation, Cameras, Motion models, Point spread functions, Image compression, Image transmission, Digital image processing, Image restoration

Read Abstract +

Proceedings Article | 16 March 2015 Paper

No-reference visual quality assessment for image inpainting

V. Voronin, Vladimir Frantc, V. Marchuk, A. Sherstobitov, K. Egiazarian

Proceedings Volume 9399, 93990U (2015) https://doi.org/10.1117/12.2076507

KEYWORDS: Image quality, Visualization, Molybdenum, Image restoration, Binary data, Machine learning, Databases, Visibility, Feature extraction, Image classification

Read Abstract +

Proceedings Article | 4 March 2015 Paper

A method for ultra fast searching within traffic filtering tables in networking hardware

Sergey Makov, Vladimir Marchuk, Viacheslav Voronin, Vladimir Frantc, Victor Obukhovets

Proceedings Volume 9410, 94100M (2015) https://doi.org/10.1117/12.2083022

KEYWORDS: Switches, Ultrafast phenomena, Distributed computing, Telecommunications, Computing systems, Switching, Information visualization, Bridges, Standards development, Patents

Read Abstract +

Proceedings Article | 22 May 2014 Paper

Machine learning approach for objective inpainting quality assessment

V. Frantc, V. Voronin, V. Marchuk, A. Sherstobitov, S. Agaian, K. Egiazarian

Proceedings Volume 9120, 91200S (2014) https://doi.org/10.1117/12.2063664

KEYWORDS: Image quality, Machine learning, Visual system, Visualization, Image restoration, Visual process modeling, Image processing, Associative arrays, Molybdenum, Feature extraction

Read Abstract +

Proceedings Article | 19 February 2013 Paper

Video inpainting using scene model and object tracking

V. Frantc, V. Voronin, V. Marchuck, K. Egiazarian

Proceedings Volume 8655, 86550V (2013) https://doi.org/10.1117/12.2004719

KEYWORDS: Video, Optical flow, Cameras, Video processing, Image segmentation, Detection and tracking algorithms, Image processing, Visualization, Image filtering, Binary data

Read Abstract +

Proceedings Article | 19 February 2013 Paper

Fast texture and structure image reconstruction using the perceptual hash

V. Voronin, V. Marchuk, V. Frantc, Karen Egiazarian

Proceedings Volume 8655, 86550R (2013) https://doi.org/10.1117/12.2002829

KEYWORDS: Image restoration, Systems modeling, Reconstruction algorithms, Visual process modeling, Electron beam melting, Image processing, Image segmentation, Feature extraction, Image compression, Edge detection

Read Abstract +

Showing 5 of 13 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years