基于小波矩的大豆外观品质特征提取方法的研究

Study on the Method of Extracting the Appearance Quality of Soybean Based on Wavelet Moment

应用机器视觉技术对大豆的外观品质进行检测成为近年来的研究热点,大豆的外观特征提取是检测的重要内容之一。为提高大豆样本的识别率,减少噪声对特征提取造成的污染,提出了一种基于小波矩的大豆外观品质特征提取方法。该方法对大豆样本图像进行基于小波变换的不变矩特征提取,有效地解决了由于大豆本身存在的大小不同、移动等造成的特征不明的问题。试验证明:此方法不仅能够精确地描述大豆外观品质特征而且对噪声不敏感,此方法识别精度高,正确识别率达到99%。

Using of machine vision technology in detecting the appearance quality of soybean has become a hot spot in recent years. It is one of the important contents for the extraction of soybean sample image. In order to improve the recognition rate and reduce the noise pollution, a new method of extracting the appearance quality of soybean based on wavelet moment has been proposed. The algorithm is based on the wavelet transform of the image of the soybean sample, which can effectively solve the problem of the size and movement of the soybean itself. Results showed that this method can not only accurately describe the characteristics of the appearance quality of soybeans, but also is not sensitive to the noise. This method achieved high recognition accuracy and correct recognition rate reached 99%.