基于计算机视觉和神经网络检测鸡蛋裂纹的研究

    Crack detection in eggs using computer vision and BP neural network

    • 摘要: 为了提高鸡蛋裂纹检测的准确性和效率,综合运用计算机视觉技术和BP神经网络技术,实现对鸡蛋表面裂纹的无损检测和分级。首先,通过计算机视觉系统获取鸡蛋表面的图像,对图像分析处理,提取了裂纹区域和噪声区域的5个几何特征参数。其次,将5个参数作为输入,建立结构为5-10-2的BP神经网络模型,对裂纹进行识别和鸡蛋的自动分级。试验结果表明模型对裂纹鸡蛋的识别准确率达到了92.9%,对整批鸡蛋的分级准确率达到了96.8%。

       

      Abstract: To improve the accuracy of detection and classification of egg with cracks, computer vision and BP neural network technology were synthetically applied to automatically identify and classify the eggs with cracks. First, the images of eggs with or without cracks were captured through computer vision system, then the images were processed, and five geometrical characteristic parameters of crack areas and noise areas were acquired. Second, with the five parameters as inputs, the best BP neural network (5 input nodes, 10 hidden nodes, 2 output nodes) was employed to detect egg crack and classify eggs. The experimental results show that the rate of testing precision of cracked egg reaches 92.9% and the classification accuracy of total eggs can reach 96.8% by the 5-10-2 BP neural network model.

       

    /

    返回文章
    返回