摘要
采用遗传算法得到描述柑桔形状的最佳拟合椭圆参数.任意椭圆都可以用5个变量描述,经过二进制编码形成初始的基因码,在给定的图形匹配率公式的作用下进行遗传运算可以得到全局最优解.对变量添加了一些约束条件,提高遗传算法收敛速度.试验结果表明该方法可以修复因遮挡和重叠丢失的柑桔形状.相比于传统的圆形Hough变换提取特征的方法,外接矩形面积在64×64(像素数)提取形状特征消耗时间缩短了1/2,消耗空间减少到1/20,当图像尺寸增加时,优势更明显.使用椭圆来描述的柑桔外形也更接近柑桔的真实形状.
Genetic algorithm is used to get approximate elliptical parameters of citrus. Every ellipse can be described by 5 parameters which are encoded as primitive code through binary coding. The formula of graphics matching rate is given for getting the global optimal solutions through genetic operation and some restrictions were added to fit citrus edge rapidly. The experiment results show that it can describe the shape of citrus and is a good solution to the overlapped problem of citrus. The computational time and space wastage are decreased to 1/2 and 1/20 respectively. Compared with circular Hough transform algorithm when area is 64 × 64 （pixels）, the more increasing of image area, the more effective of this algorithm, and the shape of ellipse fitting is more close to the real shape.
出处
《江苏大学学报（自然科学版）》
EI
CAS
北大核心
2007年第6期469-472,共4页
Journal of Jiangsu University：Natural Science Edition
基金
国家863计划项目(2006AA10Z263)
江苏省高校自然科学基金资助项目(05KJB210019)
关键词
柑桔
形状
椭圆拟合
遗传算法
特征提取
citrus
shape
ellipse fitting
genetic algorithm
feature extraction
