Defect detection and quantification system to support subjective visual quality inspection via a digital image processing: A tiling work case study

Abstract

Abstract Several areas of the quality inspection on architectural works only use subjective visual inspection, especially those involving aesthetic faults. Because people are limited in what they can detect visually, inspectors are not able to quantify the value of a defect and cannot perform an inspection that includes all possible defects. Subjective evaluations depend on individual experience and are unreliable because they do not have objective standards. Therefore, this paper presents an innovative system of defect detection and quantification. The system is able to augment subjective visual quality inspections in architectural work by specifying defect positions and quantifying defect values. This method uses defect feature analysis and quantifies the defect value from digital images using a digital image processing technique. The inspection of tiling work was chosen as a case study for developing a prototype of the system. This paper describes the conceptual framework of the proposed system's application and the methodology of the system's development. It includes a field verification of the potential and accuracy of developed prototype system by comparing the results of human inspections and those of the proposed system. A potential benefit of the system is an increase in the reliability of visual quality inspection by reducing the subjective human judgment of aesthetic faults.