Prof. Bogdan Smolka Profile

Prof. Bogdan Smolka

at Silesian University of Technology

SPIE Involvement:

Conference Program Committee | Author

Publications (25)

Proceedings Article | 12 April 2021 Presentation + Paper

Defending against sparse adversarial attacks using impulsive noise reduction filters

Krystian Radlak, Michal Szczepankiewicz, Bogdan Smolka

Proceedings Volume 11736, 117360O (2021) https://doi.org/10.1117/12.2587999

KEYWORDS: Detection and tracking algorithms, Denoising, Network security, Image filtering, Image classification, Defense and security, Safety, Neural networks, Machine learning, Unmanned vehicles

Read Abstract +

Proceedings Article | 12 April 2021 Presentation + Paper

Segmentation of hyperspectral images using self-organizing maps

Pawel Sanocki, Michal Kawulok, Bogdan Smolka, Jakub Nalepa

Proceedings Volume 11736, 117360M (2021) https://doi.org/10.1117/12.2586236

Read Abstract +

Proceedings Article | 14 May 2019 Presentation + Paper

Deep learning for impulsive noise removal in color digital images

Krystian Radlak, Lukasz Malinski, Bogdan Smolka

Proceedings Volume 10996, 1099608 (2019) https://doi.org/10.1117/12.2519483

KEYWORDS: Image filtering, Image processing, Denoising, Network architectures, Convolutional neural networks

Read Abstract +

Proceedings Article | 14 May 2019 Paper

Visual front-end for underwater scene change detection and environment monitoring by the autonomous drone

Boguslaw Cyganek, Bogdan Smolka

Proceedings Volume 10996, 109960U (2019) https://doi.org/10.1117/12.2519390

KEYWORDS: Signal detection, Signal processing, Video, Distance measurement, Environmental monitoring, Environmental sensing, Video surveillance, Signal analyzers, Underwater imaging

Read Abstract +

Proceedings Article | 14 May 2019 Presentation + Paper

Deep learning for fast super-resolution reconstruction from multiple images

Michal Kawulok, Pawel Benecki, Krzysztof Hrynczenko, Daniel Kostrzewa, Szymon Piechaczek, Jakub Nalepa, Bogdan Smolka

Proceedings Volume 10996, 109960B (2019) https://doi.org/10.1117/12.2519579

KEYWORDS: Image processing, Super resolution, Image fusion, Convolution, Image registration, Image filtering, Convolutional neural networks

Read Abstract +

Proceedings Article | 14 May 2019 Presentation + Paper

Robust switching technique of impulsive noise removal in color digital images

Bogdan Smolka, Boguslaw Cyganek, Michal Kawulok, Jakub Nalepa

Proceedings Volume 10996, 109960M (2019) https://doi.org/10.1117/12.2519301

KEYWORDS: Digital filtering, Image filtering, Image processing, Switching, Optical filters, Denoising, Image enhancement, Distance measurement, Quality measurement, Video

Read Abstract +

In this paper a novel method of impulsive noise removal in color images is presented. The proposed filtering design is based on a new measure of pixel similarity, which takes into account the structure of the local neighborhood of the pixels being compared. Thus, the new distance measure can be regarded as an extension of the reachability distance used in the construction of the local outlier factor, widely used in the big data analysis. Using the new similarity measure, an extension of the classic Vector Median Filter (VMF) has been developed. The new filter is extremely robust to outliers introduced by the impulsive noise, retains details and has the unique ability to sharpen image edges. Using the structure of the developed filter, a new impulse detector has been constructed. The cumulated sum of smallest reachability distances in the filtering window serves as a robust measure of pixel outlyingness. In this way, a pixel will be treated as corrupted if a predefined threshold is exceeded and will be replaced by the average of pixels which were found to belong to the original, pristine image; otherwise the processed pixel will be retained. This structure is similar to the Fast Averaging Peer Group Filter, however the incorporation of the reachability measure makes this technique more robust. The new filtering design can be applied in real time scenario, as its computational efficiency is comparable with the standard VMF, which is fast enough to be used for the enhancement of video sequences. The new filter operates in a 3×3 filtering window, however the information acquired from a larger window is processed. The source of additional information is the local neighborhood of pixels, which is used for the determination of the novel reachability measure. The experiments performed on a large database of color images show that the new filter surpasses existing designs especially in the case of highly polluted images. The robust reachability measure assures that the clusters of impulses are being removed, as not only the pixels, but also their neighborhoods are considered. The novel measure of dissimilarity can be also used in other tasks whose main goal is the detection of outliers.

Proceedings Article | 14 May 2019 Presentation + Paper

On data augmentation for segmenting hyperspectral images

Jakub Nalepa, Michal Myller, Michal Kawulok, Bogdan Smolka

Proceedings Volume 10996, 1099609 (2019) https://doi.org/10.1117/12.2519517

KEYWORDS: Data modeling, Hyperspectral imaging, Statistical modeling, Image segmentation, Principal component analysis, Neural networks, Convolutional neural networks, Statistical analysis

Read Abstract +

Proceedings Article | 14 May 2018 Paper

Real-time stereovision framework for underwater drone maneuvering

Bogusław Cyganek, Bogdan Smołka

Proceedings Volume 10670, 106700L (2018) https://doi.org/10.1117/12.2305096

KEYWORDS: Cameras, Video, Imaging systems, Signal processing, Navigation systems, Water, Calibration, Light sources and illumination, Image acquisition, Atmospheric propagation

Read Abstract +

Proceedings Article | 14 May 2018 Presentation + Paper

Robust enhancement technique for color images corrupted by impulsive noise

Bogdan Smolka, Jakub Nalepa, Michal Kawulok, Boguslaw Cyganek

Proceedings Volume 10670, 1067003 (2018) https://doi.org/10.1117/12.2303717

KEYWORDS: Image filtering, Image enhancement, Digital filtering, Denoising, Gaussian filters, Optical filters, Image processing, Contamination, Roads, Image quality

Read Abstract +

Proceedings Article | 14 May 2018 Presentation + Paper

Evolutionary cortical surface segmentation

Maksym Walczak, Jakub Nalepa, Michal Kawulok, Wojciech Dudzik, Bogdan Smolka

Proceedings Volume 10670, 106700D (2018) https://doi.org/10.1117/12.2304549

KEYWORDS: Brain, Image segmentation, Neuroimaging, Magnetic resonance imaging, Algorithm development, Image processing, Image processing algorithms and systems, Anisotropic diffusion, Genetic algorithms, Evolutionary algorithms

Read Abstract +

Proceedings Article | 29 April 2016 Paper

Real-time framework for tensor-based image enhancement for object classification

Bogusław Cyganek, Bogdan Smołka

Proceedings Volume 9897, 98970Q (2016) https://doi.org/10.1117/12.2227797

KEYWORDS: Image enhancement, Image quality, Super resolution, Image enhancement, Image classification, Electronic filtering, Nonlinear filtering, Image processing, Pattern recognition, Object recognition, Digital imaging, Multidimensional signal processing, Matrices, Classification systems, Prototyping, Video

Read Abstract +

Proceedings Article | 29 April 2016 Paper

Application of the local similarity filter for the suppression of multiplicative noise in medical ultrasound images

Damian Kusnik, Bogdan Smolka, Boguslaw Cyganek

Proceedings Volume 9897, 989704 (2016) https://doi.org/10.1117/12.2227650

KEYWORDS: Anisotropic filtering, Ultrasonography, Speckle, Medical imaging, Image quality, Image processing, Digital filtering, Linear filtering, Visualization, Cameras

Read Abstract +

Proceedings Article | 29 April 2016 Paper

Automatic finger joint synovitis localization in ultrasound images

Karolina Nurzynska, Bogdan Smolka

Proceedings Volume 9897, 98970N (2016) https://doi.org/10.1117/12.2227638

KEYWORDS: Bone, Skin, Image analysis, Statistical analysis, Optical inspection, Tissues, Binary data, Visualization

Read Abstract +

Proceedings Article | 27 February 2015 Paper

Real-time object recognition in multidimensional images based on joined extended structural tensor and higher-order tensor decomposition methods

Boguslaw Cyganek, Bogdan Smolka

Proceedings Volume 9400, 94000T (2015) https://doi.org/10.1117/12.2083367

KEYWORDS: Object recognition, Prototyping, Visualization, Multidimensional signal processing, Distance measurement, Anisotropic filtering, Nonlinear filtering, Classification systems, Matrices, Pattern recognition

Read Abstract +

Proceedings Article | 27 February 2015 Paper

Impulsive noise suppression in color images based on the geodesic digital paths

Bogdan Smolka, Boguslaw Cyganek

Proceedings Volume 9400, 94000R (2015) https://doi.org/10.1117/12.2081831

KEYWORDS: Image filtering, Digital filtering, Image visualization, Image processing, Distance measurement, Digital imaging, Image quality, Quality measurement, Image compression, Image restoration

Read Abstract +

Proceedings Article | 28 December 2007 Paper

Parametric approach to the retrieval of lossy compressed color images

Maria Luszczkiewicz, Bogdan Smolka

Proceedings Volume 6937, 69372L (2007) https://doi.org/10.1117/12.784770

KEYWORDS: Image compression, Databases, Distance measurement, Expectation maximization algorithms, Internet, Image retrieval, Image processing, RGB color model, Systems modeling, Visualization

Read Abstract +

Proceedings Article | 28 December 2007 Paper

Digital image colorization based on distance transformation

Przemyslaw Lagodzinski, Bogdan Smolka

Proceedings Volume 6937, 69372R (2007) https://doi.org/10.1117/12.784782

KEYWORDS: Image segmentation, Image processing, RGB color model, Digital imaging, Image processing algorithms and systems, Image quality, 3D image processing, Video, Image filtering, Binary data

Read Abstract +

Proceedings Article | 9 October 2003 Paper

Robust retrieval of fine art paintings

Bogdan Smolka, Rastislav Lukac, Konstantinos Plataniotis, Anastasios Venetsanopoulos

Proceedings Volume 5146, (2003) https://doi.org/10.1117/12.504101

KEYWORDS: Image retrieval, Image compression, Databases, Digital imaging, Visualization, Image processing, Roentgenium, RGB color model, Statistical analysis, Multimedia

Read Abstract +

Proceedings Article | 9 October 2003 Paper

A variety of multichannel sigma filters

Rastislav Lukac, Bogdan Smolka, Konstantinos Plataniotis, Anastasios Venetsanopoulos

Proceedings Volume 5146, (2003) https://doi.org/10.1117/12.500263

KEYWORDS: Digital filtering, Image filtering, Nonlinear filtering, Image processing, Smoothing, Optical filters, Distance measurement, Electronic filtering, Interference (communication), Switching

Read Abstract +

The smoothing function of widely used vector filters such as vector median (VMF), basic vector directional filter (BVDF) and directional distance filter (DDF) is designed to perform the fixed amount of smoothing. It may become the undesired property, because in some image areas these filters introduce too much smoothing and blur thin details and image edges. In general, the common problem is how to preserve some desired signal features while the noise elements are removed. An optimal situation would arise if the filter could be designed so that the desired features were invariant to the filtering operation and only noise would be affected. In case of the impulsive noise corruption, the problem is stated often as searching for the switching function that allows to reduce the filter effect only to noisy samples. In this paper, a new nonlinear filtering scheme for the removal of impulsive noise in multichannel digital images is presented. A new class of multichannel sigma filters is based on the combination of the standard sigma-filter concept provided by Lee and the robust order-statistics theory. With respect to a variety of the measures (e.g. vector distance expressed through Minkowski metric, angular distance or their combination) for quantification of the distance between multichannel samples, we provide a rich class of adaptive vector sigma filters taking advantages of the threshold structure with the approximation of the standard deviation and also the fully adaptive filter structure. Thus, by adaptive switching between the smoothing function and the identity operation, the behavior of the proposed method is attractive for filtering of image environments degraded by impulsive noise, bit errors and outliers. The new filtering scheme is computationally efficient and able to achieve excellent balance between the image detail preservation and the noise suppression. The achieved results show that the new filtering class has excellent preservation capabilities and provides significant improvement in comparison with well-known vector filters such as VMF, BVDF and DDF in terms of all commonly used quality measures.

Proceedings Article | 9 October 2003 Paper

Nonparametric technique of noise reduction in color images

Bogdan Smolka, Rastislav Lukac, Konstantinos Plataniotis, Anastasios Venetsanopoulos

Proceedings Volume 5146, (2003) https://doi.org/10.1117/12.504102

KEYWORDS: Image filtering, Digital filtering, Nonlinear filtering, Denoising, Optical filters, Image processing, Color image processing, Quality measurement, Image quality, Image enhancement

Read Abstract +

Proceedings Article | 9 October 2003 Paper

Selection vector filter framework

Rastislav Lukac, Konstantinos Plataniotis, Bogdan Smolka, Anastasios Venetsanopoulos

Proceedings Volume 5146, (2003) https://doi.org/10.1117/12.499643

KEYWORDS: Digital filtering, Filtering (signal processing), Image filtering, Nonlinear filtering, Electronic filtering, Optical filters, Optimization (mathematics), Image processing, Interference (communication), Distance measurement

Read Abstract +

Proceedings Article | 23 June 2003 Paper

Modified anisotropic diffusion framework

Bogdan Smolka, Rastislav Lukac, Konstantinos Plataniotis, Anastasios Venetsanopoulos

Proceedings Volume 5150, (2003) https://doi.org/10.1117/12.503213

KEYWORDS: Diffusion, Anisotropic diffusion, Image processing, Image enhancement, Denoising, Nonlinear filtering, Anisotropic filtering, Image filtering, Signal processing, Control systems

Read Abstract +

Proceedings Article | 23 June 2003 Paper

Three-dimensional entropy vector median filter for color video filtering

Rastislav Lukac, Bogdan Smolka, Konstantinos Plataniotis, Anastasios Venetsanopoulos

Proceedings Volume 5150, (2003) https://doi.org/10.1117/12.503178

KEYWORDS: Digital filtering, Image filtering, Optical filters, Nonlinear filtering, Image processing, Video, Error analysis, Interference (communication), Video processing, Telecommunications

Read Abstract +

Proceedings Article | 23 June 2003 Paper

Application of kernel density estimation for color image filtering

Bogdan Smolka, Rastislav Lukac, Konstantinos Plataniotis, Anastasios Venetsanopoulos

Proceedings Volume 5150, (2003) https://doi.org/10.1117/12.503191

KEYWORDS: Image filtering, Digital filtering, Optical filters, Statistical analysis, Image processing, Image analysis, Image quality, Interference (communication), Distance measurement, Automatic control

Read Abstract +

SPIE Journal Paper | 1 June 2001

On the reduction of impulsive noise in multichannel image processing

Bogdan Smolka, Andrzej Chydzinski, Konrad Wojciechowski, Konstantinos Plataniotis, Anastasios Venetsanopoulos

OE, Vol. 40, Issue 06, (June 2001) https://doi.org/10.1117/12.10.1117/1.1367347

KEYWORDS: Image filtering, Digital filtering, Optical filters, Nonlinear filtering, Signal to noise ratio, Image processing, Denoising, RGB color model, Color image processing, Image enhancement

Showing 5 of 25 publications

Conference Committee Involvement (9)

Real-Time Image Processing and Deep Learning 2024

22 April 2024 | National Harbor, Maryland, United States

Real-Time Image Processing and Deep Learning 2023

1 May 2023 | Orlando, Florida, United States

Real-Time Image Processing and Deep Learning 2022

4 April 2022 | Orlando, Florida, United States

Real-Time Image Processing and Deep Learning 2021

12 April 2021 | Online Only, Florida, United States

Real-Time Image Processing and Deep Learning 2020

27 April 2020 | Online Only, California, United States

Showing 5 of 9 Conference Committees

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