A New Image-Based Model For Predicting Cracks In Sewer Pipes
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2013, Vol 4, Issue 12
Abstract
Visual inspection by a human operator has been mostly used up till now to detect cracks in sewer pipes. In this paper, we address the problem of automated detection of such cracks. We propose a model which detects crack fractures that may occur in weak areas of a network of pipes. The model also predicts the level of dangerousness of the detected cracks among five crack levels. We evaluate our results by comparing them with those obtained by using the Canny algorithm. The accuracy percentage of this model exceeds 90% and outperforms other approaches.
Authors and Affiliations
Iraky Khalifa, Amal Aboutabl, Gamal AbdelAziz Barakat
Keywords
Related Articles
- EP ID EP157527
- DOI 10.14569/IJACSA.2013.041210
- Views 112
- Downloads 0
A Feasible Rural Education System
The education system in rural and semi-rural areas of developing and underdeveloped countries are facing many challenges. The limited accessibility and challenges to the education are attributed mainly to political...
Modeling Smart Agriculture using SensorML
IoT is transforming the physical world into a digital world by connecting people and things. This paper describes state of the art domains where IoT is playing a key role. Smart agriculture is selected as a case study of...
Automated Detection Method for Clustered Microcalcification in Mammogram Image Based on Statistical Textural Features
Breast cancer is the most frightening cancer for women in the world. The current problem that closely related with this issue is how to deal with small calcification part inside the breast called micro calcification (MC)...
Computer Science Approach to Information-Like Artifacts as Exemplified by Memes
Providing information can be expanded to include systems that deliver information-like artifacts. They provide such “things” as advertisements, propaganda pieces, and meme artifacts. Memes are the subject of extensive in...
A Method for Implementing Probabilistic Entity Resolution
Deterministic and probabilistic are two approaches to matching commonly used in Entity Resolution (ER) systems. While many users are familiar with writing and using Boolean rules for deterministic matching, fewer are as...