Krzysztof Okarma

Combined full-reference image quality metric linearly correlated with subjective assessment

In the paper a new combined image quality metric is proposed, which is based on three methods previously described by various researchers. The main advantage of the presented approach is the strong linear correlation with the subjective scores without additional nonlinear mapping. The values and the obtained correlation coefficients of the proposed metric have been compared with some other state-of-art ones using two largest publicly available image databases including the subjective quality scores.

Colour Image Quality Assessment Using Structural Similarity Index and Singular Value Decomposition

In the paper the analysis of the influence of the colour space on the results obtained during image quality assessment using the Structural Similarity index and the Singular Value Decomposition approach has been investigated. Obtained results have been compared to the ones achieved by widely used Normalised Colour Difference (NCD) metric. All the calculations have been performed using the LIVE Image Quality Assessment Database in order to compare the correlation of achieved results with the Differential Mean Opinion Score (DMOS) values obtained from the LIVE database. As a good solution for the further research, also with the use of some other image quality metrics, the application of the HSV colour space is proposed instead of commonly used YUV/YIQ luminance channel or the average of the RGB channels.

Monte Carlo Based Algorithm for Fast Preliminary Video Analysis

In the paper a fast statistical image processing algorithm for video analysis is presented. Our method can be used on colour as well as grayscale or even binary images. The main component of the proposed approach is based on statistical analysis using the Monte Carlo method. A videos statistical information is acquired by specifying a logical condition for the Monte Carlo technique. The results of the algorithm depend on the correct choice of threshold values; thus the application area is limited by the adaptability of the thresholds to videos with large heterogeneity: e.g. videos with objects moving into and out of the scene, rapidly varying illumination, etc.

Fast communication: Polynomial windows with low sidelobes' level

Some of the main advantages of polynomial windows are their low computational complexity and ability to easily change their frequency response modifying the values of their coefficients in the time domain. Kulkarni [Polynomial windows with fast decaying sidelobes for narrow-band signals, Signal Processing 83 (2003) 1145-1149] presented the coefficients obtained for such windows with fastest possible decaying sidelobes but their important limitation is very high level of the first sidelobe especially for windows with narrow mainlobe. In the article the results of the highest sidelobe level optimization for the family of polynomial windows are presented. Frequency characteristics of obtained windows are also compared to some well known ones such as Hann, Hamming, Blackman [On the use of windows for harmonic analysis with discrete Fourier transform, Proc. IEEE 66 (1) (1978) 51-83] and Nuttall [Some windows with very good sidelobe behavior, IEEE Trans. Acoust. Speech Signal Process. ASSP-29 (1) (1981) 84-91] windows.

A Statistical Reduced-Reference Approach to Digital Image Quality Assessment

In the paper a fast method of the digital image quality estimation is proposed. Our approach is based on the Monte Carlo method applied for some classical and modern full-reference image quality assessment methods, such as Structural Similarity and SVD-based measure. Obtained results are compared to the effects achieved using the full analysis techniques. Significant reduction of the number of analysed pixels or blocks leads to fast and efficient estimation of image quality especially in low performance systems where the processing speed is much more important than the accuracy of the quality assessment.

A fast image analysis technique for the line tracking robots

Fast and simplified image processing and analysis methods can be successfully implemented for the robot control algorithms. Statistical methods seem to be very useful for such an approach, mainly because a significant reduction of analysed data is possible. In the paper the use of the fast image analysis based on the Monte Carlo area estimation for the simplified binary representation of the image is analysed and proposed for the mobile robot control. A possible implementation of the proposed method can applied in the line tracking robots and such application has been treated as the basic one for the testing purposes.

Video Quality Assessment Using the Combined Full-Reference Approach

In this paper the new combined video quality metric is proposed, which may be useful for the quality assessment of the compressed video files, especially transmitted using wireless channels. The proposed metric is the weighted combination of three state-of-the-art image quality metrics, which are well correlated with the subjective evaluations. A simple extension of those metrics for the video quality assessment is the averaging of their values for all video frames. Nevertheless, such approach may not lead to satisfactory results for all types of distortions. In this paper the typical distortions introduced during the wireless video transmission have been analyzed using the 160 files available as the LIVE Wireless Video Quality Assessment Database together with the results of subjective quality evaluation. Obtained results are promising and the proposed metric is superior to each of the analyzed ones in the aspect of the linear correlation with subjective scores.

The 3D scanning system for the machine vision based positioning of workpieces on the CNC machine tools

In the paper some algorithms applied for the calibration of the 3D scanning system and image analysis in the experimental system for positioning the workpieces on the CNC machines are discussed. The idea of the scanning is based on the application of photogrammetric algorithms using the fringe patterns approach. An experimental system consisting of three cameras and three structural light projectors has been built in order to acquire the images representing the scanned object with projected light patterns. These images are then analyzed in order to obtain the depth information for each point representing the workpiece or the background. Nevertheless, a good accuracy requires a proper calibration of the system considering the distortions introduced by the optics of the cameras and projectors. After the calibration, the acquisition of image series and their analysis, the 3D model of the object, represented as a point cloud, is obtained as the result, which should be filtered and can be fitted into the known model. The results obtained in the conducted experiments have also been compared to the effects of the application of an available commercial system with similar cameras.

Two-Dimensional Windowing in the Structural Similarity Index for the Colour Image Quality Assessment

This paper presents the analysis of the usage of the Structural Similarity (SSIM) index for the quality assessment of the colour images with variable size of the sliding window. The experiments have been performed using the LIVE Image Quality Assessment Database in order to compare the linear correlation of achieved results with the Differential Mean Opinion Score (DMOS) values. The calculations have been done using the value (brightness) channel from the HSV (HSB) colour space as well as commonly used YUV/YIQ luminance channel and the average of the RGB channels. The analysis of the image resolutions influence on the correlation between the SSIM and DMOS values for varying size of the sliding window is also presented as well as some results obtained using the nonlinear mapping based on the logistic function.

Application of Shape Analysis Techniques for the Classification of Vehicles

One of the main tasks of the statistical traffic analysis is its rating due to the size, type or number of axles. A typical method for measuring the volume of traffic along with the initial classification is based on data derived from inductive sensors and load cells. The possibilities of such a system are however limited, therefore in recent years a great interest in machine vision systems can be observed. An interesting image analysis technique that allows a rapid classification of the types of vehicles observed from the side view is the shape analysis. It can be applied for binary images, for which the values of shape descriptors such as e.g. Feret’s diameter can be calculated, as well as some additional quantities such as the center of gravity determined for greyscale images. The article presents the results of the shape analysis obtained for different types of vehicles observed from the camera placed beside the road.