The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In order to improve the accuracy and efficiency of weed recognition, an identification method based on ant colony optimization (ACO) algorithm and support vector machine (SVM) is proposed. Firstly, shape feature parameters are extracted from the plant leaves after a series of image processing such as threshold segmentation, smooth processing and edge detection etc., and five geometric parameters and...
In this paper, an algorithm in TIG welding based on image processing is proposed. Firstly we achieve two binary images by two different thresholds from image captured by camera, one is for welding torch detecting and the other is for welding line detecting. Secondly the image is segmented by means of region growing and the target area including welding torch, welding pool and welding line is get....
The process of recognizing the image of log end by the way of image processing technique was involved in this study, according to the features of the log end images, removed internal hole noises and external band noises of the image by combining the area threshold method and mathematical morphology. Processed the image by the method of homomorphic enhancement, transformed the image to the logarithm...
It is known that digital images are frequently corrupted by impulse noise due to errors generated in camera sensors, analog-to-digital conversion and communication channels. Therefore, it is imperative to remove impulse noise in order to facilitate the subsequent processing such as edge detection, segmentation, analysis, and pattern recognition etc. Many linear and nonlinear filtering techniques have...
Wood defect with rot reduces wood quality badly. X-ray is selected to be the testing source for nondestructive testing. Wood rot image obtained by testing was done gray transformation. The contrast of the image after gray transformation can be enhanced obviously and the position of rot can be highlighted. Binary processing was adopted for the image after gray transformation. Then the edge of the binary...
In order to predict gas-liquid-solid multiphase mixing effect in the gas-liquid-solid three-phase reactors, a novel method based on image processing technology, fractal dimension and CFD technology is introduced in this work. Each pattern produced by phase transition in the stirred reactor are continuously eroded and binarized five times. Evolution profile of the fractal dimension slope value P of...
This paper presents a design of a kind of high speed image acquisition card based on PCI Express bus. The program uses FPGA to decode Cameralink image data, using on-chip resources to achieve the FIFO and off-chip SDRAM control logic, making a high-speed connection with the host pc through the PEX8311 based on PCI EXPRESS bus. After testing, the speed is satisfying the needs of high- speed raw image...
Robots can be as flexible and smart as human beings, which has been the dream of a number of scientists and science fiction writers. The emergence of humanoid robots and the research of artificial intelligence and related technologies are the major step to realize the dream. This paper presents a framework design of autonomous humanoid robot soccer system based on the analysis of autonomous humanoid...
In this paper, a new method of inspecting fruit quality is proposed based on color image processing. After an image of fruits is taken, white balance is performed. Then the image is transferred from the RGB color model to the HSI color model. Its simplified histograms of hue H and saturation S are calculated as the input of a designed BP network. The output of the BP network is the quality description...
In this paper, a new method of inspecting fruit quality is proposed based on color image processing. After an image of fruits is taken, white balance is performed. Then the image is transferred from the RGB color model to the HSI color model. Its simplified histograms of hue H and saturation S are calculated as the input of a designed BP network. The output of the BP network is the quality description...
Due to the high demands for productivity and quality of bearing and the shortage of traditional detection methods, this paper proposes an automatic detection system based on machine vision technique. The detection system uses digital image processing technology to process the images collected by CCD camera and finish identification for the surfaces of bearing quickly and accurately. Firstly, least...
It is extremely challenging to binarize 2D barcode image under the condition of both nonuniform illumination and cluttered background. Neither global nor local thresholding method can yield an ideal binary result. In this paper, we propose a novel 2D barcode image binarization method. The contribution of the method is that it can remove the unnormalized illumination especially in the cluttered background...
As accurate identification of weeds from crops is the prerequisite for precise herbicides spraying, this paper proposes a multi-feature fusion method based on neutral network and D-S evidential theory to improve the accuracy of weed recognition. Firstly, three kinds of single features such as color, shape and texture are extracted from the weed and crop leaves after a series of image processing. Secondly,...
Atmospheric correction can eliminate radiation distortion of remote sensing images caused by atmospheric effects and is the basis of data processing for dynamic monitoring of quantitative indicators. In this paper, 6S and FLAASH based on radiation transfer model are applied to atmospheric correction of SPOT4 image. Judging from the results of correction, atmospheric correction can obtain features...
Due to the disadvantageous effects of rain and snow on image processing, this paper proposed a new removal algorithm of rain and snow based on fuzzy connectedness. Since the distribution of rain and snow was scattered in the image, a single seed point could not recognize all the rain and snow regions. Therefore, according to the impact of rain and snow on the pixel brightness, multiple seed points...
This paper introduces the method of on-line measurement of the yarn evenness using double CCD image sensors. The double sensors are mounted on a movable bracket of the small car. The obtained yarn coefficients of variation in the diameter through computer and digital image processing techniques are compared with those of using off-line USTERII evenness tester. Meanwhile, the CCD sensors, avoiding...
Due to the advantages of multi-wavelet transformation in image processing, this paper presents a image watermarking algorithm based on stationary multiwavelet. The simulation results show that relative to general watermarking algorithm based on scalar wavelet or multiwavelet transformation, this algorithm can not only resist noise pollution better, but also embed watermark content as much as possible...
Colony number in many colony calculating experiments is counted by manual method at present, therefore it is difficult to get the result quickly and accurately when the number of experimental sample is large. A new automatic colony counting system was developed, which makes use of image-processing technology to feasibly count white bacterial colonies in clear plates according to the RGB color theory...
Super-resolution image reconstruction is a technique to reconstruct high resolution image or video from a sequence of low resolution images. The super resolution method is summarized in this paper. The frequency domain method, non-uniform interpolation, POCS method, iterative back projection method, Bayesian approach, regularization method are both discussed for super-resolution image reconstruction.
The concept of beamlet was first introduced by Donoho and Xiaoming Huo. As an efficient tool for multi-scale image analysis, beamlet dyadically organized the collection of line segments which exhibits a certain range of lengths, positions and orientations. The role played by line segments in beamlet analysis is analogous to which points play in wavelet analysis. This paper describes a multi-scale...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.