Enhanced Mean Load Based Clustering Technique On Dented Image Segments In Reconstruction Of Buildings

The need of an updated clustering technique for rebuilding the damage of available buildings is required and found as a very complicated task for both financial and manpower needs. The new segments does not reach the present segments' potential. So there is a coercion occurs to invent a new clustering technique that suits both construction engineer and the consumers. This effort is one of the destitute fact of usual clustering algorithm. The aim of this research is to produce a better clustering technique for the existing entities from damaged buildings. Finding a new clustering technique from damaged segments of buildings such as bricks and steels and then reutilize them for rebuilding. This process is challenging for engineers to reprocess the damaged segments for construction by the restructuring with the improved potential. This paper proposes a new clustering algorithm that directs the engineers to reutilize the existing damaged units and enables reutilization, cost beneficiary, reduces work pressure of construction. The damaged segments of the images are collected based on load then the firmness of mean load of the segment is identified for clustering according to the nearest firmness in mean load point for restructuring. This paper guides a reorganized clustering of enhanced firmness in mean load and clustering of segments which are formed from damaged building segments. This work enables the improved firmness in mean load clustering method in order to find more clusters on damaged building segments. The destination of nearest segments is considered as midpoint used as a mean point for clustering. The algorithm is designed by means of unsupervised learning process