基于数学形态学的植物叶片图像预处理

植物叶片图像的预处理是进行叶形特征提取和识别的重要前提，获得高质量的预处理叶片图像对计算机辅助植物识别十分重要。本文提出了基于数学形态学的植物叶片图像的预处理方法，运用数学形态学中的开运算和闭运算消除图像中的孤立噪声点并填补叶片内部孔洞。该方法保持了原图像的基本形状特征并能获得清晰的边缘，为叶片特征提取创造了良好的前提。

Preprocessing of leaf image based on mathematical morphology

Preprocessing of leaf image is the important precondition for feature extraction and recognition. It is important for computer-aided plant identification to get a high-quality leaf image which is preprocessed. Preprocessing method of leaf image based on mathematical morphology is advanced in this paper. Opening and closing algorithm are used for eliminating isolated points in the image and filling holes in the leaf. By using this method,the basic shape features of original image are preserved and clear edge of leaf is detected. Thus favorable precondition is created for the features extraction of leaf.