Cotton Image Segmentation Algorithm Based on Fusion Method of Markov Random Field and Quantum Particle Swarm Cluster

[Objective] The aim of this study was to improve the cotton image segmentation accuracy in a picking robot image processing system. [Method] An image segmentation algorithm based on a fusion method of Markov random field and quantum particle swarm optimization clustering was proposed. The process of the proposed algorithm is as follows: first, transform the RGB (red, green, blue) images into grayscale; second, use it to segment these images; finally, the threshold of the connected area is set on the basis of the segmented image to obtain the target area. Then, the cotton front image and the cotton side image are selected from the images collected from different angles. The segmentation experiment was carried out by using this algorithm, and compared with the Otsu algorithm, the fuzzy C-means algorithm, the quantum particle swarm image segmentation algorithm and the Markov random field image segmentation algorithm. [Result] The results showed that the segmentation accuracy and peak signal to noise ratio of the proposed algorithm were 98.94% and 77.48 dB. When compared with the Otsu algorithm, fuzzy C-means algorithm, quantum particle swarm optimization algorithm and Markov random field algorithm, the average segmentation accuracy and peak signal to noise ratio of the proposed algorithm increased by 2.47%–4.56%, and 9.81–13.11 dB, respectively. [Conclusion] The proposed algorithm had higher segmentation accuracy and higher peak signal to noise ratio than the other algorithms tested.     

Design of Vision System Based on Service Robot

A vision system based on the service robot is involved. In the system, picture signal is acquired by the picture sensor OV7635. Frame memory AL422B is used as data buffer memory, while CPLD controlled the time order DSP performed. In the software system of image processing, to accomplish color image segmentation and recognition, the threshold vector judgment and improved seed-fill algorithm is introduced, and the image geometric moment is calculated during the segmenting. In order to achieve a vision servo system which composed of image-based feedback and adaptive compensation, the deduced matrix-based Jacobian from the image moment is taken as image feature. Adopted the TFT LCD is adopted to straightly disolav the result of vision recognition and vision tracing.     

基于U-Net的玉米叶部病斑分割算法

本文旨在提出一种基于U-Net算法模型的玉米病程分级方法,实现对玉米常见4类叶部病害程度的快速、准确、客观分级.该方法以两组U-Net模型并行运算实现对玉米叶部病斑图像的语义分割任务.经测试图像分割试验中病斑分割MIoU值达到93.63％,叶片分割MIoU值达到96.33％,且运算速度均在1秒内完成.试验结果表明,该研...     

Segmentation of Color Image Based on Feature Divergence and Fuzzy Theory

In order to improve general adaptive capability of algorithm,the new color image segmentation algorithm based on feature divergence and fuzzy theory(FDCIS) is proposed.The algorithm introduces feature divergence and fuzzy dissimilarity function into calculation in order to measure the dissimilarity of feature vector,clusters data by means of feature divergence,and accomplishes the merge of image region.The experimental results demonstrate that the color image segmentation result of the proposed approach reduce calculation on large sample of color image,simply and effectively solve over-segmentation of color image,avoid the dependence of the algorithm on initial condition,and hold favorable consistency in terms of human perception.     

基于MATLAB图像处理的大豆颗粒检测方法研究

为解决大豆单株考种过程中人力计数准确率低和数粒仪等光电方法耗时长等问题,采用计算机视觉系统及MATLAB软件开发平台代替人工大豆单株考种进行自动检测的方法。该算法采用对大豆颗粒图像进行空间滤波去除噪声及“Otsu”方法对图像进行最佳全局阈值分割处理,在对图像处理的基础上完成对大豆颗粒个数、颗粒大小两项指标的测定。以六个大豆品种周黑豆、周青豆、周豆11、周豆18、周豆22和周豆23的籽粒为试验对象,探究大豆颗粒计数、大豆颗粒大小分级两项指标的确定。实验结果表明：该算法及程序准确有效,能准确计算大豆单株颗粒个数;该算法及程序判断出的各品种大豆颗粒平均面积大小与百粒重成正相关,且决定系数为0.9141,即可得该算法及程序可准确有效的判断大豆颗粒大小。总之,基于MTALAB图像处理大豆单株颗粒检测方法的研究可相对减轻人力劳动强度及人类视觉的不足,在提高工作效率和准确度等方面有重要意义。     

Improvement and performances of DV hop localization algorithm in wireless sensor networks

In order to improve the node localization precision of Range Free based DV Hop localization algorithm in wireless sensor networks (WSNs) with randomly distributed nodes and dynamic topology, the improved algorithm is proposed. After analyzing the DV Hop algorithm, considering the obvious errors of the estimated node coordinates calculated by Polygon based method in traditional DV Hop algorithm, the numerical iterative algorithm is constructed by employing Taylor series expansion, and simulation studies for the improved DV Hop algorithm are conducted. The selection criteria for the convergent threshold of iterative step is determined, the localization performance of the improved localization algorithm is analyzed by comparing with the traditional DV Hop algorithm under the same condition of selected convergent threshold and simulation parameters, while the calculation amount and convergence rate of the improved algorithm are also measured by the statistic iterations. The simulation results show that by selecting reasonable iterative threshold values and appropriately increasing calculation amount for node localization, the improved DV Hop localization algorithm greatly improves the localization precision and the error stability, which is feasible for node localization in WSNs with both randomly distributed nodes and dynamic topology.     

苹果表面伤痕与果梗和花萼的辨识及检出方法

针对在水果表面品质检测的图像处理中,苹果的果梗和花萼很容易被错误辨识成缺陷,提出一种自动识别出苹果缺陷,并计算其大小的图像处理算法,如图像分割、图像去噪、区域标记与提取、感兴趣区域提取等,设计出一种能将采集到的苹果图片进行正确处理后,识别出果梗和花萼,得到真正缺陷大小的图像处理算法。运用C++语言进行编程,采用MFC基于对话框的非模态形式设计了图像处理软件,处理采集到的苹果样品图片,结果表明,该算法能正确计算缺陷大小,并且能得到果梗和花萼的辨识依据,可用于水果表面品质实时检测中。     

Binary Images Processing Based on Adaptation to Mixture Transform Coding

To enhance quality of image processing, it is demanded that coding algorithm should be simplified and the speed of image processing should be faster,and information loss on image compressed should be minimum.Adaptive segmentation is given for image which to be processed.Region coding is combined with threshold coding.Adaptation to mixture transform coding is fulfilled.Results of simulation shows that with this method coding loss witch images are compressed is mined and quantity of image processing is good.     

A level set based inpainting approach for fragmentary human bodies in binarized infrared images

A number of image segmentation algorithms frequently fragmentize human targets in infrared images, therefore, an inpainting procedure is always needed for further application. The inpainting is transformed to be a segmentation process. Firstly, Schrdinger transform connects fragmentized human parts. Then a level set model integrating image region and boundary information is proposed to extract the connected regions produced by the Schrdinger transform, and finally the inpainting is done when the model converged to complete the segmentation. Experiments show the proposed algorithm recognizes and locates human parts automatically, fills gaps correctly, connects broken human silhouettes smoothly. The objective indictor of shape similarity between inpainting results and relevant ground-truths is above 80%, as well as the internal fragmentary proportion below 4%. With optimized parameters the approach is robust to noise disturbance.     

基于Visual c++矩形标尺智能识别

通过利用图像处理和图像识别领域的边界分割Robert局部边缘检测算子方法及梯度算子区域迭代的阈值图像分割算法相结合来对图像特征进行二次提取,不同于单独采用边界分割与区域分割算法,该算法通过对边缘检测结果的差分结果的迭代分析,有效的增强了识别算法对识别条件的适应性及识别精度,并采用Visual C 编程进行计算机图像辅助设计作为实现手段.     

An algorithm of image processing based on discrete wavelet transform compression and chaotic scrambling

An algorithm was proposed in view of the combination of image compression and encryption. We got the approximate part and three detail parts after transforming the image with discrete wavelet transform (DWT), and compressed the image by modifying the detail parts by a given threshold value based on human visual systems. And then, we encrypted the image by scrambling the approximate part because this part held mostly of the energy. Last, a compressed and encrypted image can be achieved after DWT. Simulation result shows a good effect on the combination of compression and encryption.     

Adaptive Image Segmentation Method Based on Ncut

In order to solve the problem that requires some factors by manual in the traditional Ncut algorithm, limit the generality of the algorithm, an adaptive image segmentation method is proposed by improving the traditional Ncut algorithm. First, instead of the two control parameters on the calculation of weight matrix that influence the segmentation results in the traditional Ncut algorithm by groups of potential theory; then in order to reduce the sensitive to the number of the cluster and the center of the cluster in the K-means algorithm, calculate on the eigenvector of the Ncut algorithm by the minimum spanning tree, to get the final number of cluster and the center, and then uses the K-means clustering algorithm to get the final segmentation result. The experimental results show that the proposed method not only improves the versatility of the algorithm, and the segmentation is good.     

A Non-linear Circuit Model of A Self Scanned Photodiode Array Image Sensor

A non-linear circuit model of photodiode built according to the working principle of self-scanned photodiode array image sensor is presented for improving the property of the sensor. Through the analysis of the non_linear circuit model,we get the state equations, and the equations are resolved with Runge_Kutta algorithm. The Runge_Kutta algorithm is realized in C language, and the numeric result of the circuit is obtained. The analysis of the numeric result of the model shows that the non_linear performance of the sensor can be improved by reducing the capcitor of the PN junction and the dynamic performance of the image sensor can be enhanced by paralleling capacitor C M , and all the analysis is consistent with the real measurement results of the sensor. The circuit model of photodiode is improved over previous model.     

Appoach To Object Semanteme Based Image Segmentation and Classification

There exist potential problems in current region-based image retrievals. This paper proposes a novel approach to object semanteme based image segmentation and classification. First, a hierarchical region growing image segmentation is established using HRGSeg algorithm, which can effectively get rid of weak object semantemes and play down the side effect of over-segmentation. Based on it, low-level features like color, edge and texture are extracted mapped into high-level object semantics hierarchically by using SVM. A fairly good experiment result is achieved and shows the feasibility of our approach.     

Image denoising based on the complex direction of filter banks and blockshrink

A new image denoising algorithm based on the complex direction of filter bands and BlockShrink is proposed. The image is decomposed based on the complex direction of filter bands to obtain the coefficients. Then, according to the coefficient correlation, the block threshold method is used to select the best block size and the threshold. In this way, the unbiased risk estimation of each sub-band is minimized. The algorithm is entirely data-driven easy to implement and with good visual effects. Experiments show that the proposed algorithm increase the PSNR by 0.6 percent compared with the algorithm based on DWT-BlockShrink transform, and the edge and countour information are more clearly.     

Algorithm Based on SVM and Rules for the Disambiguation of Combinatorial Ambiguous Phrases

Ambiguity processing is an essential but difficult problem in word segmentation.The authors combine Support Vector Machines(SVM)with rules to propose a new algorithm(SR algorithm)to deal with the combinatorial ambiguous phrases in Chinese word segmentation.The key idea of the SR algorithm is to solve combinatorial ambiguous phrases making use of the theory of SVM and rules of parts of speech.In a test of several kinds of Chinese corpus,it indicates that the accuracy of segmentation for combinatorial ambiguous phrases reach 83%.It provides a new method for solving Chinese word segmentation problems.     

Detection of Shallow Cracks in the Wall with Digital Image Processing

A new method of image segmentation based on neural network was proposed to extract the cracks image, with which it could overcome, in some extent, the dependence of the background image and reduce the pseudo points and pseudo regions. The measurement accuracy can be improved compared with that from morphological algorithm. Furthermore, the specific methods and processes to measure the walls crack with image digital processing were presented. And with the case study, it was found that this method can measure the cracks accurately with convenient operation.     

Segmentation algorithm for urinary sediment image combiningwavelet transform and 2D Maximum entropy threshold

In order to solve the problem that urine sediment visible components cannot be segmented effectively because of complex components, complicated defocusing in image and poor discrimination between object and background, a method based on combination algorithm wis designed to segment urine sediment. The wavelet transform wis used to erase the effect of defocusing. Then morphology wis utilized to get the subimages that include the particles. The segmentation method combining the wavelet transform based segmentation and the two dimensional entropy threshold based segmentation wis employed to segment urine sediment visible components. Experimental results show that the proposed method can segment urinary sediment images effectively and precisely.     

Design of nondestructive test system for plasma clots

One of the most important measures that are used to guarantee blood transfusion safety is to detect clots in the plasma before transfusion. To overcome the disadvantages of manual detection method, this research designs a nondestructive testing (NDT) system for plasma clots inspection based on machine vision technique and artificial neural networks. The key technology for system design are studied and presented. Image acquisition is performed by custom-designed software based on MATLAB platform, and the methods of image cut, reverse color, median filter as well as gray cutting are adopted to preprocess image. The use of fisher discrimination method, combined with iterative threshold segmentation method and the selection of connected domain, can successfully eliminate the interference of air bubble and correctly extract the image of plasma clots. Plasma clots are discriminated by a recognition model based on artificial neural network BP algorithms. The results of clinical contrast experiment shows that the system can effectively detect whether plasma contains plasma clots and the new system shows a much higher degree of repeatability and stability. From the image acquisition and processing to the recognition of plasma clots, the detecting time of a sample is no more than 1 min.     

Novel Image-adaptive Watermarking Algorithm

Digital watermarking is an effective method to provide copyright protection for digital media. A blind image- adaptive watermarking algorithm based on DCT domain is presented. The algorithm selects adaptively the step size of quantization to embed the watermark bits by modifying DC components via the human visual system model and local characteristics of image; at the same time some AC components of the blocks with less perceptual capacity are also modified to embed the same watermark bits by using quantization. Thus the relation between robustness and imperceptibility can be well balanced. The algorithm recovers the watermark without any reference to the original image. Compared with the similar algorithm reported in the literature, this method can give better image quality and is better robust against noise and commonly used image processing techniques.