利用BP算法实现集装箱编号识别

Recognition of Characters on Containers Using the BP Neural Network Algorithm

  • 摘要: 研究集装箱字符识别,采用数字图像处理,模式识别与神经网络技术及改良BP算法实现集装箱编号的自动识别,该方法有较强的适应性,可在不同的光照条件下工作,在识别倾斜,变形,磨损,污染的集装箱时表现出较强的抗干扰能力,改良BP算法具有分类功能,可以实现字符的识别,并且具有较强的鲁棒性。

     

    Abstract: Techiques of digital image processing, pattern recognition and artificial neural networks are made use of in the recognition of characters marking containers. In particular the method of modified BP neural network algorithm is discussed in more detail. The method is found to be adaptable and works well under various grades of brightness. It is also found to be very robust when recognizing characters when sloped, deformed or dirty. The modified BP neural network algorithm has besides its capability of categorization in recognition.

     

/

返回文章
返回
Baidu
map