【正文】 , ) ( , )G x y I x y N x y?? （ 1） I 是我們感興趣的部分 ,N 是高斯白噪聲 ,(x,y)表示一對(duì)坐標(biāo)。進(jìn)一步研究圖像的灰度像素可以看出邊上的孔洞像素最小。一個(gè)標(biāo)準(zhǔn)的容器破裂圖如 (A)所示。 證明了 方法的有效性。 在本文中 ,我們提出了一種改進(jìn)的空間低通濾波器。伯頓適的人臉識(shí)別系統(tǒng)圖像應(yīng)用技術(shù) ,使它能夠識(shí)別變化大面孔。要實(shí)現(xiàn)我們的目標(biāo) ,必須使用四種基本的操作 圖像預(yù)處理、目標(biāo)檢測、特征描述和破裂對(duì)象最終分類。(2) w0 or w1 is zero with certain increasing Para,in which there is also one class finally。. (c) displays an improved mask with a parameter Para. We will later illustrate that tuning Para properly is to facilitate object segmentation. The smoothing function used is shown in equation (3): 1111( , ) 39。( , ) 39。 automated image enhancement。 (2) classes without distinctive grayvalues, but with similar areas. However, when the grayvalue differences among classes are not so distinct, and the object is small relative to backgroud, the separabilities among classes are insufficient. In order to overe the above problem, this paper presents an improved spatial lowpass filter with a parameter and presents an unsupervised method of automatic parameter selection for image enhancement based on Otsu method. This method bines image enhancement with image segmentation as one procedure through a discriminant criterion. The optimal parameter of the filter is selected by the discriminant criterion given to maximize the separability between object and background. The optimal threshold for image segmentation is puted simultaneously. The method is used to detect the surface defect of container. Experiments illustrate the validity of the method. KEYWORDS image processing。( , ) 39。 consists of white noise and the other parts except I39。 C0 denotes pixels with levels [1, … , k], and C1 denotes pixels with levels [k+1, … , L]. Then the probabilities of class occurrence w0,w1 and the class mean levels u0,u1 respectively,are given by 0 1==nii Pk?? ?? ?? （ 6） 1 1= =1niik Pk??? ?? ?? （ 7） 001= ( ) / = /kii iP k k?? ? ?? ? ? ? ?? （ 8） 111= ( ) / = [ /[ 1 Lii iP k k??? ? ? ? ? ? ?? ? ? ??? （ 9） 1=Lii iP? ?? ? （ 10） 220 0 01= [ ( ) ] /Kii ip? ? ? ? ?? （ 11） 221 1 11= [ ( ) ] /Kii ip? ? ? ? ?? （ 12） The procedure of obtaining optimal para is based on obtaining optimal threshold for every filtered image. The optimal threshold is determined by maximizing the separability between object and background using the following discriminant criterion measure as mentioned in [9] : 22=/BT??? （ 13） where 2 2 2 20 0 1 1 0 1 1 0( ) ( ) ( )B T T? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? （ 14） 2B? and 2T? are the between class variance and the total variance of levels,respectively. 221= ( )LT T ii ip? ? ??? （ 15） The optimal threshold k* that maximizes n is selected in the following sequential search by using equation (5)(14): * 1( ) max ( )kLkk??? ? ? （ 16） Equation (16) is a discriminant criterion to select the gray level to maximize the separability between object and background for a given picture. In this paper, a parameter Para is introduced, so the equations (6)~(9), (11)~(14), (16) is parameterized by Para and k and equations (10), (15) is parameterized by Para. Equation (13) can be rewritten as: 22( , ) / ( , )BTp a ra k p a ra k???? （ 17） Where 2T? is not a constant any more and is not negligible, but some putation reducti