基于机器视觉的珍珠分级检测技术研究-机械电子工程专业论文.docxVIP

浙江工业大学硕士学位论文 浙江工业大学硕士学位论文 试，取得了一定的成果，为今后研制商用化的分级系统打下了基础。 实验结果证明，可以在尺寸指标和颜色指标检测中达到较高的准确性 和实时性，在光洁度指标的检测中也可以满足一定的检测要求。 关键词：珍珠分级，机器视觉，加权矢量中值滤波，颜色分类， 光洁度检测 ABSTRACTAt ABSTRACT At present，most of the pearl—producing enterprises in our country adopt the manual way to roughly separate and select pearls．Because pearls are small in size and large in amount，the classification of pearls is a troublesome and inefficient job．After the national classification standard of cultured pearls is brought into force，it is a pressing demand for pearl-producing enterprises to classify pearls accurately and speedily．By the tender requests of a pearl—producing enterprise in Zhuji，this paper does research on the application of machine vision to the classification of pearls． The main points are as follows： 1．Combining the analysis of pearls’physics and chemical property and their optical property with the requests in the national classification standard，this paper makes an overall design of the classi fication system of pearls．The design of image—capturing module is paid special attention to：a) The method of lighting from a high angle and in a single direction is used detected．2．This detected． 2．This paper works out some relevant image processing algorithms according to the requests of the classi fication of pearls：a)A weighted vector median filtering algorithm is proposed，which greatly reduces the operation amount owing to the merits of vector median filtering；b)As the solution to the nonuniform illumination on a pearl’S surface，local threshold segmentation and connected area label are adopted to get a stable and accurate segmentation；C)Colors are classified according to local placement of the hue histogram，which leads to results more stable and accurate than the HSI space；d)The shape and size of pearls are measured by a fast algorithm based of the shape under a hi曲precision condition；e) Surface perfection is detected by boundary descripti011 and color segmentation，and flaws are classified a