Papers by Keyword: Mathematical Morphology

Abstract: A defect feature extraction algorithm which depends on the separation and subtraction of color image and mathematical morphology is proposed in this paper, based on the defects in trademark printing processes, such as smudges, pin holes, misprints, misting etc. The difference images of each monochrome are operated with morphology methods and then the defect information of high precision printing processes in colorful trademark, such as shape, boundary contour, quantity, size and location etc, are extracted and recognized with suitable structure elements. The defect extraction algorithm is programmed and run by MATLAB and the results validated the high speed and precision of the algorithm about extracting some kinds of defect information in color trademark printing processes. The algorithm has met the real-time requirements of defect feature extraction in trademark printing processes. This research laid a theoretical foundation for researching and developing the color trademark quality detection system.

Abstract: In this paper, we present a leaf vein extracting algorithm frame which deals with contour and interior vein by employing different methods. The interior vein extraction method based on gray scale processing, mathematical morphology and processing in details is presented. We apply gray-scale morphology to process the image and extract the vein information. Through the analysis of the image information, processing in details is adopted to clear the information on the other tissues and insignificant veins. The extracted significant interior vein is overlaid with the leaf contour extracted through edge detection by pixel union operation. Experiment results show the effectiveness of the proposed method.

Abstract: Mathematical morphology can be seen as a special digital image processing method and theory, which has been widely used in various fields. In this paper, the mathematical morphology is applied to the color image processing. In thespace of color image, I have simply expounded the theories and properties of color morphological changes, and defined its morphological operators. According to the application of omni-directional and multi-angle structuring elements composite morphological filter in gray image, I put forward a kind of color morphological filter with omni-directional and multi-angle structuring elements composite. This algorithm has retained its advantages in gray image, however, remaining some drawbacks. Through the optimization of results based on this algorithm, we finally get the relatively ideal denoising effects.Keywords: mathematical morphology;color model;color model; color morphological filter

Abstract: Sobel, Roberts operator is derived based on the differential. As a result of the template and fixed threshold value, it lacks adaptability. Median filter on images of the collected cardiac seeds maturity, use split clustering algorithm on cardiac seeds maturity for the first image gradient value clustering, condensed cluster on the result of the first split the clustering results, then secondly division cluster, and finally work out the image edge based on the second clustering results and realize on the FPGA implementation. At last the method is Applied in Andriod Platform. The experimental results show that it is more delicate to use the hierarchical clustering algorithm to detect the edge and it has stronger ability to suppress noise.

Abstract: Considering in the progress of the power quality detection for disturbance signal, detected signals are often has the problem of random noise and impulse noise, in this paper, by using traditional wavelet de-noising, put forward a detection method of disturbance signal based on mathematical morphology and lifting wavelet, discussed its detection principle and implementation methods. Simulation results show that the method de-noising effect is obvious, can effectively improve the accuracy of the disturbance signal judgment.

Abstract: In this paper, frame differential method will be used to detect moving targets in a static background video file, and pre-contour can be obtained by binarizing the detected targets . However,, the result are not what was expected, so the expansion and corrosion of mathematical morphology are used to extract the final contour of moving targets. in the progress of dealing with massive data , mathematical morphology is not good enough to achieve the need of the real-time in video surveillance. Considering the dilation and erosion is a kind of parallel processing operations, in order to improve the speed of mathematical morphology operations, this paper offers detailed implementation process of the dilation algorithm for parallel computing on GPU. Experimental results showed that GPU parallel processing on mathematical morphology algorithm faster than the CPU serial processing.

Abstract: An automatic counting method for microalgal cells were proposed using digital image processing with characteristics of microalgae microscopic image considered. Firstly, the microalgae image was pretreated with graying, and was then applied the median filtering to remove the noise. Secondly, the image was applied Bot-hat conversion to enhance the contrast. Thirdly, the image was segmented with Otsu algorithm, and was then applied morphological operations. Finally, the binary image segments representing microalgal cells were labeled and counted. The results of experiments showed that this method was simple, efficient and accurate in counting microalgal cells in the microscopic image.

Abstract: Research and identify overhead transmission lines’ transient characteristic which was caused by lightning stroke is significant to develop the protection and improving its reliability based on transient state. A complex signal can be resolved into several parts which have respective physical meanings by mathematical morphology’s multi-scale decomposition and this can reveal the local features of waves. Therefore, the transient current of ±800 kV UHVDC transmission lines, caused by the non-fault lightning stroke, fault lightning stroke and other line short circuit, can be decomposed by the multi-scale morphology decomposition to extract the spectral energy from the high and the low frequency bands, and the ratio of those two spectrum energy forms main criterion to realize the identification between lightening disturbance and the fault states. According to the ratio of the maximum of the current’s amplitudes of decomposition waveform of the first head of current’s second scale and sixth scale, to further distinguish the lightning stroke fault from the line short circuit. Extensive simulations show that the approach is correct and effective.

Abstract: According to restrictions existing in the application of single license plate location algorithm in complicated background. A license plate location algorithm based on mathematical morphology and color characteristics is proposed. Firstly, the new method uses Ostu algorithm to select an optimal threshold, and according to the threshold carries on binary processing, then by using a new method of mathematical morphology for image edge detection. Finally combined mathematical morphology with color characteristic to locate license plate .Experiments show that this new method with higher accuracy and fewer restrictions on background is superior to traditional or a single method and can be widely used.

Abstract: To solve the harmony problem of accuration, real-time with anti-noise capability on edge detection of smokescreen, the edge detection algorithm of smokescreen based on multi-scale mathematical morphological is designed, and the algorithm can effectively reduce the noise of the smokescreen image. Compared with the results of classical edge detection operator: Sobel, Roberts, Prowitt and Canny etc, it is concluded that the algorithm designed has obvious advantages in continuity, smoothness, image recognition, practical complexity, operation time and other related parameters.