基于数字图像技术的西红柿智能分类

Intelligent Classification of Tomatoes Based on Digital Image Technology

针对传统农业中人工水果分级和分类较为困难的问题,提出了一种无损的西红柿智能分拣分级系统。首先,该系统利用微控制器装置采集样本的数字图像来构建物种向量并进行二值分类,以区分西红柿和其他物种。其次,根据颜色属性将西红柿分为成熟和未成熟两类,并利用Gabor小波变换对图像中的病损区域进行分割,识别出果实中的缺陷。最后,根据附加的颜色和几何特征构造的缺陷向量识别出三种类型的缺陷。实验结果表明,与其他分类器模型相比,所提系统在所有性能指标上都表现出较好的性能。

Aiming at the difficulty of artificial fruit classification in traditional agriculture,a nondestructive intelligent sorting and grading system for tomatoes is proposed.Firstly,the system uses microcontroller device to collect digital images of samples to construct species vectors and carry out binary classification to distinguish tomatoes from other species.Secondly,according to the color attribute,tomatoes are divided into mature and immature categories,and Gabor wavelet transform is used to segment the damaged areas in the image and identify the defects in the fruits.Finally,three types of defects are identified according to the defect vectors constructed by additional color and geometric features.The experiment results show that compared with other classifier models,the proposed system has the best performance in all performance indexes.