# Detecting Welding Defects in Steel Plates using Computer Vision Algorithms
In practice, it is practically impossible to obtain a perfect weld and, in most circumstances, it is not necessary to provide the adequate service functions required. However early detection and segregation is always preferred to mishaps.
Using our algorithms, we can easily detect faults in welding by the images and also measure the severity of each fault precisely. This will further help in faster image recognition and avoid adverse situations from arising. It was found, using Convolutional Neural Networks algorithm and U-Net architecture making the process much more efficient. Resulting in an accuracy of 98.3% by the end of the work.
The following is one such sample:
### Raw Input:
![img](Code/dataset/images/W0001_0007.png)
### Ground Truth:
![img](Code/dataset/labels/W0002_0007.png)
### Sample Output:
![img](Resources/0007.png)
To better understand the project click *[here](https://medium.com/@malakar_soham/detecting-welding-defects-in-steel-plates-using-computer-vision-algorithms-98b1fb0da5e9)*
## Co-Authors
Soham Malakar:
[GitHub](https://github.com/malakar-soham/) | [LinkedIn](https://www.linkedin.com/in/malakar-soham/)
Swastik Malakar:
[Github](https://github.com/malakar-swastik/) | [LinkedIn](https://www.linkedin.com/in/malakar-swastik/)
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
welding dect.rar (27个子文件)
welding dect
Code
save
end_W0001_0004.png 1.41MB
end_W0001_0003.png 1.73MB
end_W0001_0007.png 1.65MB
dataset
labels
W0002_0004.png 3KB
W0002_0003.png 3KB
W0002_0007.png 7KB
images
W0001_0003.png 721KB
W0001_0004.png 601KB
W0001_0007.png 677KB
my_model
assets
keras_metadata.pb 33KB
saved_model.pb 229KB
variables
variables.index 3KB
variables.data-00000-of-00001 997KB
variables.data-00001-of-00002 981KB
variables.data-00000-of-00002 12KB
train.py 2KB
test.py 2KB
.idea
cnn-in-welding-master.iml 408B
workspace.xml 9KB
misc.xml 298B
modules.xml 301B
encodings.xml 138B
Resources
0003.png 186KB
0004.png 163KB
0007.png 340KB
README.md 1KB
read_me.txt 133B
共 27 条
- 1
资源评论
网易独家音乐人MikeZhou
- 粉丝: 3w+
- 资源: 70
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功