• Vinothini K

This paper aims at the implementation of corrosion detection utilising machine algorithms. The system detects corroded image structure from objects. The basis of hue of the images has a significant impact on whether or not an object has rusted. The detection of corroded steel structures is captured through an RPI camera and the images are processed using the proposed Convolutional Neural Network algorithm to detect corroded images automatically through an open CV platform and processed using the Raspberry Pi Microcontroller. The processed image is then compared with the given data set, which is analysed by class value. Here, by classifying the corroded images by numerical class values according to the extent of it affected by rust. The CNN algorithm is used to differentiate and train data according to a given input image. The experimental result shows a proposed system that achieves greater accuracy with minimum training loss when compared with the existing algorithms.

Raspberry Pi, Open CV, ReLu, CNN Algorithm.

"CORROSION DETECTION ON STEEL STRUCTURES USING IMAGE PROCESSING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 8, page no.a677-a682, August-2022, Available :http://www.jetir.org/papers/JETIR2208084.pdf

"CORROSION DETECTION ON STEEL STRUCTURES USING IMAGE PROCESSING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 8, page no. ppa677-a682, August-2022, Available at : http://www.jetir.org/papers/JETIR2208084.pdf