为快速准确地鉴别羊绒和羊毛,提出一种基于视觉词袋模型的鉴别方法.该方法使用羊绒和羊毛的光学显微镜图像作为实验样本,将纤维鉴别问题转化为图像的分类问题.首先对光学显微镜图像进行预处理以增强特征,然后从纤维形态中提取局部特征并生成视觉单词,再依据视觉单词对纤维图像进行分类,从而达到鉴别纤维的目的.使用了4400幅纤维图像作为数据集,从中选择不同的羊绒和羊毛的混合比作为训练集和测试集,得到的识别率最高为86%,最低为815%,鉴别1000根纤维需要的时间小于100 s,训练好的分类器可保存并用于后期的检测工作.%In order to identify cashmere and wool rapidly and accurately, a method based on bag-of-visual-word was proposed. Optical microscope images of cashmere and wool were taken as experimental samples in this method. The problem of fiber identification was changed to the problem of image classification. Firstly, fiber images were pre-processed to enhance their characteristics. Then, local features were extracted from fiber morphology and these local features were converted to visual words. Fiber images can be classified using visual words mentioned above. The experimental dataset contains 4400 fiber images. Different mixing ratio of cashmere and wool were selected as train set and test set from the dataset. In this experiment, the highest recognition ratio is 86%, and the lowest is 815%. The time required to identify 1000 fibers is shorter than 100 s. The trained classifier can be saved and used for the late detection.
展开▼
