In order to ensure the reliability of image data of irregular products similar to rectangular or oval, a general method is proposed to evaluate the capability of this kind of machine vision system (MVS) for shooting such products. The original image data is processed by the image processing technology to obtain the target area where the product is located. The number of pixels and the number of pixels at the boundary of the target region are considered as quality characteristics to determine whether the product is qualified or not. Then the capability of MVS is evaluated by analyzing the possible factors affecting its quality characteristics. A case is given to illustrate the efficiency and accuracy of this method.%为保证形似矩形或形似椭圆形的不规则形状产品图像数据的可靠性,提出了拍摄该类不规则产品的机器视觉系统的一般性能力评价方法.通过图像处理技术对获取的原始图像数据进行处理,获取产品所在的目标区域,以目标区域所在像素点的个数S及区域边界像素点个数C,作为判断该产品是否合格的质量特性,并分析影响产品质量特性的各影响因素,评价机器视觉系统的能力.通过案例分析表明,该方法能有效且准确评价机器视觉系统能力.
展开▼
