Earticle

Image super resolution reconstruction has important significance in remote sensing image feature extraction and classification etc.. Because the remote sensing image size is larger, it is difficult to super resolution reconstruction using multiple images, the compressed sensing (CS) theory was introduced into the super-resolution reconstruction. Algorithm designed the low pass filter to reduce the sample correlation matrix and wavelet, at the same time, the algorithm selects the partial Hadamard-matrix as the measurement matrix, it has faster reconstruction speed and low storage requirements, which ensure that the image reconstruction keep with the RIP criterion of compressed sensing theory . Finally, this paper realizes the remote sensing image super resolution reconstruction through the improved iterative algorithm. Experiments show that the reconstructed images of the PSNR value has increased, the reconstructed image has a better visual effect.

In this paper we have achieved a comparison between the performances of different types of distances used in the k nearest neighbors classifier for recognition of isolated handwritten Arabic numerals extracted from Mnist database, more precisely these distances are those of Euclid, of Manhathan, of Minkowski, and of Tchebychev, to do this, we have used for pre-processing the image numerals the median filter, the thresholding, the centering and the skeletonization techniques and in order to extract the features from numerals we have employed the zoning method. The simulation results that we obtained demonstrates that all these distances are generally almost equivalents.

In order to measure the dispersion coefficient of glass and other transparent material rapidly and accurately, the paper studies the dispersion coefficient measurement system based on CCD imaging automatic alignment technology. On the basis of consideration of the air refractive index impacting on the measurement accuracy of dispersion coefficient, this paper rebuilds the mathematical model by the traditional dispersion coefficient measurement formula. Using the measuring angle technology of precision grating, the paper realizes the digital measurement of deflection angle of refracted ray. Sub-pixel edge detection algorithm is adopted to realize the automatic alignment of double line to single line, which has reduced artificial error of the dispersion coefficient in the measurement process. Finally, the paper combined the multichannel small collimator designed technology and the modern control technology to achieve the high precision measurement of refractive index. Demarcating the measurement system by known dispersion coefficient of optical glass, testing results and error of standard is less than ±2.3×10-6 absolutely.

Tracking is an important process of computer vision research. But still after so many researches accuracy is still become a bottleneck. Within different tracking techniques covariance based tracking is a new technique which gives more accuracy than other techniques. There are several methods and researches have been done on covariance tracking. The covariance tracking process also uses some distance measures to calculate the dissimilarity between two target regions. Here we have list down some of the most useful distance measurement techniques which provide accurate results. We have also implemented those distance measurement techniques and shown their results with accuracy comparison. Even the distance between the target and the candidate covariance matrix is itself enough track an object, but to get more accurate result some techniques are applied on covariance tracking. Here we have listed some of those techniques which happen to provide better results after applying on covariance tracking and also pointed out the advantages and drawbacks of those techniques.

A trapezoid is generated in screen when the projector is not perpendicular to the screen body in most situations. It is called the keystone distortion. In order to solve the keystone distortion of images, a new algorithm transforming pixel spatial position using edge preserving interpolation is proposed to implement projector keystone correction. First, the scaling factors, the start point positions and the end point positions are calculated according to different rows, then the edge preserving interpolation algorithm are used according to the space positions. Experimental results demonstrate that the algorithm can not only implement keystone correction, but also preserves the edge effectively. This algorithm can be used in the chip of projector video processing to solve the keystone distortion.

An approach to online handwriting word recognition using segmentation-based techniques is presented in this paper. This approach is referred to as lexicon-driven approach because an optimal segmentation is generated for each string in the lexicon. Word recognition problem is transformed into matching optimization problems between the dictionary entry and the handwritten word image. The segmentation processes use these steps such as removing delayed strokes, shape analysis of the stroke trajectory, reconstructing delayed strokes and combining adjacent fragments. Dynamic matching is used to ranking the lexicon entries in order to get best match. A match score is assigned to a segmentation and string by matching each segment to the corresponding character in the string with a character recognition algorithm that returns confidence value for each character class. As a result the performance for lexicons of size 10, 100, 500 and 1000are 93.17%, 70.33%, 59.79%，51.20% and 94.85%, 79.75%, 74.42%, 62.19% for adding distance and normalizing distance respectively.

Ear identification is an important biometric identification technique and has been widely used in many applications. One of the most important components in ear identification system is image preprocessing. The performance of image preprocessing has a significant impact on the accuracy of ear identification system. This paper proposes a L0 gradient based image smoothing method for ear identification. First, ear images are filtered using L0 gradient based method. Then the contrast of the image is enhanced using histogram equalization method in order to make ear edges more discriminative. Comparative experiments with an existing algorithm demonstrate that our method has better performance and is more suitable for ear identification.

The task of image super-resolution is to up sample a low resolution (LR) image while recovering sharp edges and high frequency details. In this paper, a single image super-resolution algorithm via canonical correlation analysis (CCA) is proposed. This method is based on the assumption that the corresponding LR and high resolution (HR) images have high correlation coefficients when transformed into a special space. The proposed approach includes two stages: training and testing. In the training stage, a couple of canonical bases for transformation are calculated with the prepared coupled training sets. In the testing stage, the HR image can be recovered by using the canonical bases obtained in the training stage. In addition, an iterative back projection algorithm is used to further improve the image quality. The experiments demonstrate that our algorithm can reconstruct richer details, with fewer artifacts. Moreover, this algorithm is of less complexity.

Due to improvement in imaging skill and the ease with which digital content can be imitated and operated there is a strong requirement for a digital patent device to be put in place. It requires for authentication of the content as well as the owner. Digital Watermarking is present as a potential key to this problem. Till date several watermarking techniques have been proposed. This paper proposed a comprehensive survey of the current schemes that have been developed and their effectiveness.

Aiming at changing high computational complexity, underdeveloped real time, low recognition rate of dynamic gesture recognition algorithms, this paper present a real-time dynamic gesture trajectory recognition method based on key frame extraction and HMM. Key frames are selected without keeping track of all the details of one dynamic gesture, which is based on difference degree between frames. The trajectory data stream, sorted by the time-warping algorithm, is used to construct the Hidden Markov Method model of dynamic gesture. Finally, optimal transition probabilities are employed to implement dynamic gesture recognition. The result of this experiment implies that this method has high robustness and real time. The average recognition rate of dynamic gesture (0~9) is up to 87.67%, and average time efficiency is 0.46s.

Aiming at the problem of traditional nondestructive testing steel pipe defect, Ultrasonic testing system based on Virtual Instrument was designed. The hardware platform is the signal source which is based on micro-controller, and the HS4 data acquisition card by USB bus. The software platform adopts the LabVIEW to program by using the multithread to acquire all kinds of signal by real-time. The nondestructive feature was found by using the filter, STFT analysis and joint time domain analysis. The designed system has been used to the pipe defect inspection of some company, which is stable and can achieve an anticipant effect.

Due to synchronous rectification based on Phase-shift full bridge converter is difficult to work in a state of soft switch, to solve this problem, this paper sets out an control approach of synchronous rectification based on the ZVZCS phase-shifted full-bridge, and the drive signal of synchronous rectification side uses leading-leg drive waveform after a certain time delay and applies the resonant principle in the switching process，not only keeping full bridge ZVZCS soft switching but also realizing MOSFET of the synchronous rectification ZVS. The simulation of saber and experimental research show that the converter has a good performance.

There are various types of noises that affect quality of an image such as Salt-and-pepper noise, Poison noise, Gaussian noise, Speckle noise etc. Wavelet is a powerful tool for denoising a variety of signals. Here a White Flower image has been taken for denoising purpose with the help of HAAR Transform. The noisy image is first decomposed into five levels to obtain different frequency bands. Then hard thresholding method is used to remove the noisy coefficients by fixing the optimum thresholding value. In this paper, analysis of a colored image is carried out with four different noises at zero mean that are applied on the image to produce noisy images. Residual image is obtained from the original and noisy image & its statistical parameters such as mean, median, mode, standard deviation, mean absolute deviation, median absolute deviation are calculated. In order to enhance the quality of the noisy images, performance parameters of denoised images must be estimated. The comparison between noisy and denoised image is taken in terms of MSE (mean square error), PSNR (peak signal to noise ratio), RMSE (root mean square error), SNR (signal to noise ratio) and SSIM (structural similarity index).

Using 2000-2011 MODIS and 1998-2008 SPOT-4/5 satellites NDVI data, with maximum value composites (MVCs) method and linear regression analysis, the dynamic vegetation monitoring change in 1999-2011 of the vegetation coverage in Shendong coal mining area was analyzed. It is revealed that the NDVI in Shendong increases integrally, and the land vegetation coverage in most of the mining area is improved. The vegetation coverage overall showed an upward trend in using simple linear regression analysis, NDVI from MODIS and SPOT data was analyzed both inter-annual and intra-annual change. The spatial pattern of using NDVI calculated that the increase rate of NDVI average of SPOT and MODIS was 9.90%/10a. Temperature, air pressure, rainfall, solar radiation and other meteorological indicators have similar phenological seasonal variations with vegetation coverage. Moreover, NDVI has an obvious correlation with meteorological factors, such as temperature, rainfall, air pressure.

In this paper, the break-lock phenomenon of phase locked loop (PLL) in monopulse radar receiver for missile seeking applications is presented. The continuous wave radar echo and linear frequency modulated (LFM) interference signals are injected into the PLL simultaneously with an assumption that initially, the PLL locks on to the echo signal frequency. The PLL is assumed to be operating at an intermediate frequency (IF) of 50 MHz with a typical bandwidth of 200 kHz. The frequency deviation required to break-lock as a function of interference signal power and modulation rate is analyzed. The simulation results show that break-lock is achieved at a frequency deviation of 0.36 MHz for a typical LFM signal power of -14 dBm and 200 kHz modulation rate. The break-lock in the PLL is also estimated for selected values of LFM signal power and modulation rates, such as 300, 400 kHz, when the echo signal power at the PLL input is -10 and -14 dBm. The PLL with third order passive loop filter is modeled and designed using exact method. The computer simulation is carried out using visual system simulator (VSS) AWR software and potential conclusions are demonstrated.

Coordinated multi-point (CoMP) has been raised to increase the average cell throughput and the cell-edge user throughput. However, the energy consumption of mobile stations (MSs) is a key problem restricting the wide application of CoMP systems. Considering the energy consumption of feeding back channel state information (CSI) by MSs and the influence of CSI accuracy on the throughput of system, it is proposed to measure the relationship between feedback energy consumption and throughput with energy efficiency feedback utility (EEFU) function which can adapt to different application scenes by adjusting utilization coefficient. The feedback utilization of two precoders in CoMP systems is analyzed respectively, including the optimization allocation of feedback bits with utility function. The complete EEFU optimized expression and the optimizing flow path satisfying the actual application demands of CoMP systems are then derived. The simulation results illustrate the practicability and necessity of the EEFU function and verify the performance of EEFU with different precoders.

This paper presents a recognition algorithm combining the vehicle detection and the color difference of RGB color space to recognize the brake-lights state of moving vehicles in order to achieve the intelligent-car’s rear-end collision warning about the vehicle in front of it. Firstly, we train and build AdaBoost cascade classifier by haar features samples and scaling sub-windows are used to detect the target vehicle from the region of interest of the resized image. Then we compare the adjacent frames to recognize brake light status, which including using color, shape, structural features to identify the third brake light; comparing the center of gravity coordinates and the color difference threshold to rear brake lights when vehicles are not red or yellow; according to subtraction of each RGB corresponding channel, binarization, and the color difference threshold of RGB color space to identify the red or yellow vehicles’ brake lights. Finally, experiments show that the algorithm can detect the front vehicle’s braking quickly and accurately.

For the inadequacies of the classical proportional navigation law, the mathematical model of increment proportional navigation law is established in this paper. According to the mathematical model comes to attacking targets uniform linear motion trajectory simulation. The trajectory simulation of classical proportional navigation law and incremental proportional navigation law about attacking high maneuvering target are compared. Simulation results show that incremental proportional navigation law can reduce the meet time, and stabilize the missile desired normal overload beating phenomenon in the end of the curve, also it can hit the high maneuvering target in the design requirements, and its performance is superior to classical proportional navigation law.

The growing demand of securing the online trade and digital content bought the digital watermarking as major tools for protecting copyright, preventing unauthorized distribution, track back the source, confirming the ownership, authentication and many more. This paper proposes a new algorithm which shows better resistance against some common attacks. The SVD-DWT technique is applied here for deconstructing and reconstructing the image. The secret watermark is embedded into the R band using a secret key after separating the host image into three respective bands namely R, G and B. The extracting process is performed by splitting the watermarked image into all the color channels and then applying further process into R plane. The experimental result shown in tabular form indicates the better robustness of the proposed algorithm against various attacks on image.

In this research paper, theoretical analysis and applications of a novel single image super-resolution algorithm through regularization approach and joint learning is introduced. Digital image during the process of obtaining the optical fuzzy, movement deformation and degradation factors such as random noise, the influence of the resulting often degradation image, sometimes its resolution is difficult to meet the actual demand of engineering or military applications. In this paper, we combine the joint learning theory together with the regularization standard, through parameter selection, error estimation with omission and solution analysis steps. The proposed framework is based on modified super-resolution model and novel error estimation metrics. In the experiment section, we compare our proposed algorithm with other state-of-the-art and popularly adopted methodologies and use the well-known test image databases to conduct the experiment. The experimental result shows the feasibility and effectiveness of the algorithm. In the future, we plan to do more in-depth research on the parameter selection part to modify our method.

Aiming at some problems in the process of UPS battery real-time monitoring, on the basis of the cloud terminal technology is proposed in this paper, a new method of remote online monitoring, and based on MSP430 single chip microcomputer, combined with modular guiding ideology, in order to improve the UPS battery remote monitoring automation as the core, through the reasonable design of hardware structure, the implementation of UPS battery on-line real-time monitoring of voltage, current and temperature. At the same time, the system based on ADO database access technology and C++ programming to complete the data management, human-computer interaction, and system control, by the cloud terminal implementation monitoring system data transmission between lower place machine and super-ordination machine. Practice has proved that the technology security and stability, has the very good practical and promotional value.

Due to the overlapped region and image size of the input image pair is unpredictable, it makes the matching procedure more difficult and unstable. For the purpose of finding out the stable and accurate matching algorithm of large images, we give an analysis of different kinds of characters, such as, scale invariant feature transform (SIFT), local maximum gradient descriptor, Harris corners, and the maximum curvature points of the image edges, etc. Based on the experiments of different images, a new stable matching algorithm is proposed in this paper. In our model, the matching procedure is divided into two stages, the rough and accurate matching procedures. To evaluate the matching result, the edge information is combined with the local maximum gradient of the input images as the constraint of our matching algorithm. After the extraction of the local maximum gradient character points, we use the edge information to divide these points into different classes. Then, the searching of the stable and accurate matching problem becomes to find out the best matching results which agree to the edge constraints. The experimental results show that the proposed algorithm is more efficient and stable than the other kinds of matching algorithms especially in the proposing of large size images.

This article introduces a new adaptive local image enhancement method and a graphical user. The algorithm for image enhancement will correct contrast for some certain areas of an image which is based on edges contained in the image and some statistical properties; variance of the whole image and mean value of an image block. A contrast correction gain is chosen for each image tile based on statistical properties. The algorithm improves the visual quality of an image and also restricts noise amplification. The algorithm is tested with grayscale images and results are compared with histogram equalization and adaptive histogram equalization techniques by image quality metrics parameters.

Weld seam recognition is the key technique in visual tracking research. Based on the weld image features, the image preprocessing and the linear feature extraction method of the weld seam recognition are designed. The extended adaptive median filtering method and modified Otsu adaptive threshold selection method for image segmentation are used in the image pre-processing process, to remove the noise and compress the image data. Through comparing with several other edge operators, the Roberts operator is chosen to achieve the goal of detecting the welding edge. Finally, the weld seam information is extracted through Hough transform and a satisfied result can be acquired. The study provides a theoretical support for the following designing of the weld tracking system.

In today’s time, the requirement of content based image retrieval technique is more and more because of diverse areas such as Data Mining, Remote Sensing and Management of Earth Resources, , Crime Prevention, Weather forecasting, E-commerce, Medical Imaging. The proposed paper presents the content based image retrieval, using features like color and texture, called WBCHIR (Wavelet Based Color Histogram Image Retrieval).The shape and shade features are extracted in the course of wavelet transformation and color histogram and the arrangement of these features is vigorous to scaling and conversion of objects in an image. It is the first time to present segmentation and grid, feature extraction, K-means module and k-nearest neighbor clustering algorithms and bring in the neighborhood module to build the CBIR system. It is the hybrid method of global and local features with k-means clustering algorithm.

The analysis of dissemination information and sources of information in social network services creates an urgent need with the explosive growth of the number of users and serious situation for false information and privacy leakage detection. Observe that the characteristics of randomness and uncontrollability makes malicious users manufacture and spread false malicious information, it is very difficult to find sources of information. A new information dissemination model based on probabilistic hyper-graph (IDMPH) is proposed. The method focuses on randomness for information dissemination process, introduces probabilistic hyper-graph to calculate the value of probability, find the most likely path and the leadership qualities for source nodes. Experimental results show that the conclusions are consistent with actual complex networks, have better ability to identify the path and leader nodes, can be used as basis for analysis of information control and information sources.

Superresolution image reconstruction technique uses single or a series of low-resolution images to reconstruct a high resolution image without changing the hardware devices, while improving image quality and the spatial resolution of the image. High resolution means the image with a higher pixel density, can provide more details. In this paper, a novel image superresolution algorithm based on sparse representation is studied. During over-complete dictionary of the training phase, the proposed method improves two aspects including feature extraction and dimension reduction. In the feature extraction process, combining the second derivative with the gradient direction, we construct a new descent direction to improve gradient method. The convergence speed of the new algorithm is faster than the gradient method and can get better results. Then improved two-dimensional Principal Component Analysis (2DPCA) algorithm is used to reduce the dimension, it could eliminate the correlation of the image lines and column. Experiment results show that this method of image reconstruction is better and faster for high resolution image reconstruction.

Due to the existing image quality assessment algorithm does not take the visual information and the essential features of the image into account and cannot meet the actual need, a new method of objective quality assessment which related to both cases was proposed in this paper. The singular value information of the image shows the essential information of image and human eyes are sensitive to the edge information of image. Theoretically, the algorithm of image quality assessment based on edge information and Singular Value Decomposition is better than traditional methods. The simulation experiment results show the proposed algorithm is more consistent with human subject scores and has greater stability than traditional methods. Through comparison with the time efficiency, the proposed algorithm can basically be able to meet the practical demand, and the algorithm is more usability.