基于小波分析和神经网络布料瑕疵识别与分类算法研究-控制科学与工程专业论文.docxVIP

万方数据 万方数据 Abstract Recognition and detection of fabric defects is an important step in the production process of textiles. According to the defects and shortcomings of artificial works, this paper based on the existing fabric defect detection theory and method, deeply studied fabric image preprocessing and automatic recognition method based on wavelet analysis of flaws. And the feasibility and validity of this method is verified by experiment. Firstly, in image processing commonly used pre processing method, analyses the respective characteristics, and through the experiment, compared to a variety of pre processing results, choose suitable pretreatment methods, improve the visual effect, highlights the flaw of images and the edge contour feature. Secondly, the automatic defects recognition method is proposed based on wavelet analysis. In order to reduce the environment impact on defect identification and at the same time to improve the speed of defect detection, wavelet transform is used in the segmentation of images. After wavelet decomposition, comparing through gray mean of images, abandon over the flawless windows of that threshold is no more than set. Those whose threshold over set are as a further inspection area, extracted the characteristic values in wavelet analysis method, effectively reduce the image characteristic values of the extraction and calculation of the number of windows. After wavelet decomposition, five feature values energy, entropy, variance, range and deficit moment were extracted from the latitude and longitude sub-images. After normalization, the responsiveness of the different feature values is checked in a unified metric examined, to confirm whether there is a defect and the defect judgment accurate position. Finally, analysis of the structure characteristics, design method and parameters of the method to determine of a neural network, a 3 layer BP neural network is designed according to the characteristic of the fabric flaws. Inputting