Mageshrangarajank / miniproject

Steel surface defect detection algorithm
0 stars 0 forks source link

Steel surface defect detection algotithm using computer vision #1

Open Mageshrangarajank opened 1 year ago

Mageshrangarajank commented 1 year ago

Time management is essential in the quickly phasing industrial sector. In order to decrease human mistakes and time spent, we have worked and developed an algorithm for steel surface flaw detection. The literature survey helped us to examine the Severe Steel Defect dataset and to explore efficient methods to classify and label the faulty areas pixel by pixel. We train the system using a sizable dataset of annotated photos, and the performance is assessed using a different test set. The research question addressed is to study and use CNN-based algorithms for automatic detection of steel surface flaws, which can have significant applications in quality control and inspection in the steel sector. There are several variables, both intrinsic to the material and external, that can have an impact on the creation of flaws in steel surfaces. It is essential to determine the root causes of faults in order to prevent them and guarantee the caliber of the product, our algorithm will address these problems.

Valderzg commented 4 months ago

Hello, this is a great idea, but I have encountered some problems when trying to run it, I have no way to directly predict the normalized ’x_test‘ array, which will show the error "AttributeError: 'numpy.ndarray' object has no attribute 'columns'", how can I solve it, I hope you can help, thank you!