Inspection System for Original Value of Material Decay Based on Image Search Technology

The original value monitoring for material decay is to make use of the video frequency technique, the computer image processing technique and mode identification technique for examination, processing and management of decay image of the material external appearance. In this paper the color characteristic and the veins characteristic of material decay are analyzed and the method and technique to withdraw the characteristic of material decays and to match the image contents are given; thus the search of the material corrosion imagechara cteristic information is realized.     

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.     

Color Image Compression Method Based on Incomplete Scanning Method

In view of color image characteristic, the paper improves the zero algorithm in the application of concrete algorithm, draws a new algorithm-incomplete scanning method, which is applied to color image compression. The authorsconvert color image from the RGB space into luminance-chrominance YUV space, then compress the converted image to encode/decode. Theoretical analysis and simulation experiment indicate that the compression ratio and encoding/decoding speed are increased, at the sase time the quality of restored image is guaranteed.     

基于最小阈值法的棉花幼苗识别研究

 面对纯机械式分苗机构经常出现的漏分和多分的问题,本文提出使用基于最小阈值法的图像识别技术对棉花幼苗进行识别和分离。使用了HSV颜色空间内与光照条件无关的H值将RGB真彩色图像转化为灰度图像,以提高图像处理的实时性。基于最小值阈值法,提出一种能够有效地将处于复杂背景下的棉花幼苗茎部图像提取的方法,使用棉花幼苗茎部图像的面积和长宽比等几何信息能有效识别棉花幼苗,并得到棉花幼苗茎部的重心坐标。本文的研究证明了用图像处理中的最小阈值法识别棉花幼苗是可行的。     

Research and implementation on handwritten numeralrecognition technique based on fuzzy mode

Based on simulation and numeral recognition of the 24-bit bmp images of postal codes obtained by CCD transducer, a binarization method based on coloring matter is proposed, which is employed to extract the binary image of the frame line of postal code and the binary image of the mail character separately. The procedure of image processing is analyzed, which includes detecting and separating borderlines of postal code frames, image binarization, smoothing noise-removal, slant rectification, extraction of postal code numerals, position normalization processing, subdivision of digital image, feature extraction of character recognition, and so on. The pretreatment process of image recognition is described. Then, character feature extraction is conducted for pretreated images, while the angle correctness for postal code frames and characters is performed. Finally, the recognition result is determined. In this method, the difficulty of separating frame line from postal code character line is eliminated. In order to improve recognition rate, the combination of many methods of handwritten numeral is used, resulting in improved recognition rate of postal codes. The experiment shows that this method can obtain higher recognition rate, providing reference for the separation technique in postal system.     

A COLOR IMAGE TERMINAL WITH SUBMARINE ACOUSTIC IMAGING

A color image terminal which can be used for submarine acoustic imaging system is introduced in this paper. Imaging signals, data rate above 375 KB/S, can be in real time processed in this system. It can give an insert processing of the imaging signals produced in both Modes C and B. The coordinate can be transformed quickly and in real time when Mode Bworks The luminace information can be turned into false color information by a color coder. All kinds of imaging parameters are displayed on the screen at the same time. The raster scan system is used for the image terminal. The capacity of the image memory is 512k Bit. The characters, parameters and synchronous control signals are given by a microcomputer TP-805.     

Illumination compensation of color video for driver fatigue monitor

A robust method to compensation illumination of driver video color image to enhance image quality has been proposed. Firstly, the original image is decomposed into high-frequency image and low-frequency image based on spatial image decomposition. The illumination information is completely contained in the low-frequency image. Next, low-frequency image is compensated by using Retinex approach which can brighten the darker area. Then, the compensated low-frequency image and high-frequency image are synthesized. Finally, new image is obtained by illumination balance of synthesized image. Results show that the algorithm has better results compared with the traditional algorithm.     

基于数码图像的棉花叶片氮含量估测研究

为了探究利用数码图像处理技术诊断棉花氮素营养的最佳图像特征参数和最佳叶位,以‘新陆早53号’为材料,使用智能手机获取棉花不同叶位叶片图像,利用数字图像处理技术提取叶片图像颜色和纹理特征参数,分析叶片氮含量和特征参数的相关性,构建基于不同图像特征参数的氮含量估测模型。结果表明：颜色特征参数r、G/(B+R)、G/B和纹理特征参数COR、ASM与叶片氮含量相关性较好,相关性系数(r)均大于0.55。基于颜色-纹理综合特征参数构建的氮含量估测模型均优于基于颜色或纹理特征参数所建模型,其中倒4叶氮含量估测模型最优,模型决定系数(R²)为0.875、均方根误差(RMSE)为1.324、相对误差(RE)为8.09%。因此,利用数字图像处理进行棉花氮素营养诊断时,应选择的最佳图像特征参数为r、G/(B+R)、G/B、COR、ASM,应选择的最佳叶位为棉花倒4叶。     

Influence of self-produced CO2 on postharvest life of heat-treated strawberries

Strawberries cv. Selva (75 or 90% superficial red color) were packaged with films having different permeability properties, heat-treated in an air oven (45 °C, 3 h), stored at 0 °C for 0, 7 or 14 days and then transferred to 20 °C for 2 days. The percentage of CO₂ in the package atmosphere and the effect of heat treatment on the following parameters were recorded: weight loss, external color, lightness, anthocyanin content, firmness, titratable acidity, pH, total sugar, total phenol and fruit decay. The application of heat treatment alone reduced fungal decay and delayed red color development and fruit softening. When the treatment was performed on fruit in films that allowed retention of part of CO₂ produced during heating, the delay of fruit softening and color development and the reduction of decay were enhanced. The benefit for 90% red fruit was minimal and decay development was only delayed by 1 day. The results of this work indicate that the well-known benefits of heat treatment could be considerably improved by performing the treatment in the presence of low permeability films, with the aim of retaining the CO₂ produced by the temporary increase in fruit respiration during the heating.     

Effect of calcium dips and chitosan coatings on postharvest life of strawberries (Fragaria x ananassa)

Strawberries (Fragaria x ananassa Duch.) were treated either with 1% calcium gluconate dips, 1.5% chitosan coatings or with a coating formulation containing 1.5% chitosan + 1% calcium gluconate and stored at 20 °C for up to 4 days. The effectiveness of the treatments was assessed by evaluating their impact on the following parameters: fungal decay incidence, loss of weight, firmness, external color, pH, titratable acidity and soluble solids content. Calcium dips were effective in decreasing surface damage and delaying both fungal decay and loss of firmness compared to untreated fruit. No sign of fungal decay was observed in fruit coated with 1.5% chitosan which also reduced fruit weight loss. Chitosan coatings markedly slowed the ripening of strawberries as shown by their retention of firmness and delayed changes in their external color. To a lesser extent titratable acidity and pH were also affected by coatings. Whilst addition of calcium gluconate to the chitosan coating formulation did not further extend the shelf-life of the fruit, the amount of calcium retained by strawberries was greater than that obtained with calcium dips alone, thus resulting in increased nutritional value of the strawberries.     

Use of image analysis to estimate anthocyanin and UV-excited fluorescent phenolic compound levels in strawberry fruit

Strawberry is rich in anthocyanins, which are responsible for the red color, and contains several colorless phenolic compounds. Among the colorless phenolic compounds, some, such as hydroxycinammic acid derivatives, emit blue-green fluorescence when excited with ultraviolet (UV) light. Here, we investigated the effectiveness of image analyses for estimating the levels of anthocyanins and UV-excited fluorescent phenolic compounds in fruit. The fruit skin and cut surface of 12 cultivars were photographed under visible and UV light conditions; colors were evaluated based on the color components of images. The levels of anthocyanins and UV-excited fluorescent compounds in each fruit were also evaluated by spectrophotometric and high performance liquid chromatography (HPLC) analyses, respectively and relationships between these levels and the image data were investigated. Red depth of the fruits differed greatly among the cultivars and anthocyanin content was well estimated based on the color values of the cut surface images. Strong UV-excited fluorescence was observed on the cut surfaces of several cultivars, and the grayscale values of the UV-excited fluorescence images were markedly correlated with the levels of those fluorescent compounds as evaluated by HPLC analysis. These results indicate that image analyses can select promising genotypes rich in anthocyanins and fluorescent phenolic compounds.     

A Character Recognition Based on Feature Extraction

This thesis analyzes the theory of image processing and feature extraction, character feature is investigated in this thesis, including width, intersection, chain-code, the way of structure of character is used, a hand-written character recognition and entry system is developed. It is proved feature is simple and definite.     

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.     

Automatic head recognition by integrating mean shift with multiple features

To improve the head detection accuracy in video sequences captured with fixed vertical monocular camera, a novel method of head recognition based on mean shift and multiple features is proposed. Firstly, mean shift based image segmentation algorithm with color information and spatial information is suggested to derive the candidate head components in images. Furthermore, by referring to two features that the contour of human head regions are approximate round and the hair color distribution is clustered, the evaluation models based on the contour information and inside color information of candidate head components are presented for head recognition. The experimental results show that the proposed algorithm can effectively reduce the light interfere and eliminate fake target whose color information is similar to hair color distribution. The detection rate for static images can reach about 89.4%.     

桔黄大牛角椒的果皮色遗传及雄性不育系的转育研究

为选育黄果皮牛角新品种,利用本课题组转育成的牛角椒红果皮雄性不育系、红果皮保持系、美国大牛角高代自交系探讨生理成熟时牛角椒果皮颜色的遗传规律、牛角椒雄性不育性与果皮颜色的遗传规律。结果表明：牛角椒的果皮颜色的遗传,由1对等位基因控制,红色对黄色为显性遗传;牛角椒雄性不育性与果皮颜色的遗传属独立遗传。以此为依据提出了以黄果皮保持系材料为轮回亲本,转育黄果皮牛角椒雄性不育系的遗传模式,为转育黄果皮牛角椒新品种打下理论基础。     

Application and Research on Fuzzy Cluster with Sintering Quanlity

The sintering parameters, such as sinter trolley speed, stuff thickness and ignition temperature etc. have important influence on sinter section image character distribution, and the sinter chemical ingredient have complicated nolinear relation with sintering section image characters. The paper applied Mixed-F statistic analysis to determine the optimal class number of Fuzzy cluster of sintering section radiant image, and fuzzy partition entropy analysis to verify whether the class number is optimal. It is be proved that the algorithm is right and effective, and its application is helpful for the online forecasting sintering FeO range.     

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.     

Creation of Spatial Visual Relationship

This paper probes into the way and the character of creation of spatial visual relationship from the factors as follows: specific signs, proper material, light and color and inner displays. A conclusion has been drawn that such relationship with specific spatial meaning must be realized by relative visual stings aroused by specific spatial formative factors.     

利用神经网络提取棉花叶片数字图像氮素含量的初步研究

选取6种输入向量组合，利用线性网络、BP网络以及径向基网络等3种神经网络模型进行比较研究，筛选最适宜网络模型和最佳输入组合，建立叶片数字图像彩色信息和叶片氮含量的关系模型，探索利用神经网络技术获取叶片数字图像信息的方法。结果表明，径向基网络在利用数字图像(B，H，G-R，G/R)指标作为网络输入向量时，能够实现获取棉花叶片数字图像氮含量的目标。径向基网络训练的180组样本的训练精度均达到极显著水平（r = 0.9022**），30组测试样本的预测值与实测值也达到极显著相关（r = 0.8674**），径向基网络和(B，H，G-R，G/R)向量是一种适合本研究的数学模型。对利用神经网络提取棉花叶片数字图像氮含量技术的初步探索，拓展了神经网络和数字图像技术在农业生产中的应用。     

Visualization of the FEM Analysis Data by the Object-oriented Programming

The results of Finite Element Method are a lang of data A general method is presented which can be applied to generate color contour image for elements with arbitrary shape by the object oriented programming. The authors give Visualization of the Elements of triangle Element with 3 Points, triangle Element with 6 Points, quadrilateral Element with 4 Points, quadrilateral Element with 8 Points, quadrilateral Element with 9 Points and the example by the MFC of Visual C++ R6.