2021-01-07 python opencv实现车牌识别颜色定位

青旅半醒 2023-01-03 04:25 212阅读 0赞

# python opencv实现车牌识别 颜色定位 #

主要代码参考[https://blog.csdn.net/wzh191920/article/details/79589506][https_blog.csdn.net_wzh191920_article_details_79589506]

GitHub：[https://github.com/yinghualuowu][https_github.com_yinghualuowu]

我们发现有些图片根本就是胡乱定位的，原因在于预处理没有搞好而已，如果不想动预处理的代码的话，我们就换一个方法。

这是我找了很久的黄色和蓝色的大概范围

lower_blue = np.array([100, 110, 110])
    upper_blue = np.array([130, 255, 255])
    lower_yellow = np.array([15, 55, 55])
    upper_yellow = np.array([50, 255, 255])

颜色过滤一下~

hsv = cv2.cvtColor(filename, cv2.COLOR_BGR2HSV)
    mask_blue = cv2.inRange(hsv, lower_blue, upper_blue)
    mask_yellow = cv2.inRange(hsv, lower_yellow, upper_yellow)
    output = cv2.bitwise_and(hsv, hsv, mask=mask_blue+mask_yellow)
    # 根据阈值找到对应颜色
    output = cv2.cvtColor(output, cv2.COLOR_BGR2GRAY)

感觉挺好的，至少看得见一块。

[![753210b1a49dc68a482fba72124247ec.png][]][753210b1a49dc68a482fba72124247ec.png 1]

我们稍微做下预处理开闭操作，把这白色区域糊成一块，哈哈哈哈，还行

Matrix = np.ones((20, 20), np.uint8)
    img_edge1 = cv2.morphologyEx(output, cv2.MORPH_CLOSE, Matrix)
    img_edge2 = cv2.morphologyEx(img_edge1, cv2.MORPH_OPEN, Matrix)

[![a396a879cb7b3fa3e69c767f062c0822.png][]][a396a879cb7b3fa3e69c767f062c0822.png 1]

然后拿去寻找矩形吧~~~找到了哦

[![09c073eb274ec15edbb9b45b7a634565.png][]][09c073eb274ec15edbb9b45b7a634565.png 1]

**千万别去找车身和车牌颜色相近的！！！！！！**

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FpbmdmZW5neGQx_size_16_color_FFFFFF_t_70][]

[https_blog.csdn.net_wzh191920_article_details_79589506]: https://blog.csdn.net/wzh191920/article/details/79589506
[https_github.com_yinghualuowu]: https://github.com/yinghualuowu
[753210b1a49dc68a482fba72124247ec.png]: /images/20221119/7af91b55da2b49b3862297059e0f8472.png
[753210b1a49dc68a482fba72124247ec.png 1]: https://images2018.cnblogs.com/blog/843428/201804/843428-20180418185724185-530694569.png
[a396a879cb7b3fa3e69c767f062c0822.png]: /images/20221119/90cbe8d36f0946d393e7f3f5ee462a5e.png
[a396a879cb7b3fa3e69c767f062c0822.png 1]: https://images2018.cnblogs.com/blog/843428/201804/843428-20180418185909399-821890354.png
[09c073eb274ec15edbb9b45b7a634565.png]: /images/20221119/9e55a0b3c00f4d288ed527caa02a294d.png
[09c073eb274ec15edbb9b45b7a634565.png 1]: https://images2018.cnblogs.com/blog/843428/201804/843428-20180418185956519-76086034.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FpbmdmZW5neGQx_size_16_color_FFFFFF_t_70]: /images/20221119/052b81dc49564d44acc0f722cf0eba54.png