Depth Estimation of a Clay-made Home Using Machine Learning Approach

Abstract

Depth Estimations a crucial technique to get rid of sudden failure of a Clay-Made Home. It can happen for many reasons such as poor construction, temperature changes suddenly, extra loaded etc. Automatic detection of cracks is an important task to maintenance for safety life. It’s a challenging task due to intensity of cracks and complexity of the background. A supervised deep convolutional neural network is trained to detect the cracks. After that Naive Bayes is used to calculate the depth based on height and width .For research here I have taken 600 images of size 720*480, collected by smart phones. Manual crack detection is takes more time and accuracy is low. It is one of the simplest way to detect a crack and estimate the depth. It is very important to detect and estimate the Depth. If we cannot detect the crack, crack will make a serious damage. The objective of this research is to develop a simple model based on crack image. Firstly, Ihave taken cracked images, after that prepressed the images. Prepressed images convert into Gray images and improve contrast.