期刊文献+

一种结合形状与纹理特征的植物叶片分类方法 被引量:17

Plant leaf classification method combining shape and texture features
下载PDF
导出
摘要 根据植物叶片识别植物种类对于生物科学与生态科学具有重要的辅助作用。针对叶片分类,提出了一种基于形状与纹理特征的分类算法。在进行了去噪等预处理后,通过阈值分割和数学形态学方法获取叶片区域;在分割得到的二值区域图像上提取了形状特征,在灰度图像上提取了纹理特征;在所得特征的基础上,利用BP网络对叶片进行分类。在实际图片上的实验结果表明,相比于已有算法,该方法可以达到更高的正确分类率。 Recognition of plants based on plant leaves is of important aid for biological and ecological sciences. An algo-rithm for leaf classification based on shape and texture features is presented. Following the preprocessing of image denoising, the leaf region is obtained through segmentation and mathematical morphological operations. Shape features are extracted from the segmented binary region image, and texture features are extracted from the gray-scale image. A BP for-ward neural network with the features as inputs is adopted for classification. Experimental results on real-world images show that higher classification accuracy can be achieved by the proposed method compared with existing algorithms.
出处 《计算机工程与应用》 CSCD 2014年第23期185-188,共4页 Computer Engineering and Applications
基金 湖南大学青年教师成长计划基金(No.531107040050)
关键词 叶片分类 形状特征 纹理 反向传播(BP)神经网络 leaf classification shape feature texture Back Propagation(BP)neural network
  • 相关文献

参考文献9

二级参考文献80

共引文献354

同被引文献176

引证文献17

二级引证文献150

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部