Ikhlas Abdel-Qader

PCA-Based algorithm for unsupervised bridge crack detection

Abstract Principal Component Principles (PCA) based algorithm to extract cracks in concrete bridge decks for the purpose of automating inspection is presented. PCA will be used to identify clusters using a database of bridge images. Results from three different PCA approaches are presented in this work. The first approach employs PCA by itself on raw data. In the second approach, a linear structure modeling is implemented prior to PCA processing in an effort to enhance the results since cracks can be detected as linear structures. Several convolution-processes with masks designed to identify linear structure in the data are used. In both cases, attempts to detect cracks in a global framework were used. The third approach, on the other hand, used local information (neighborhoods) instead of global. That is, each image is segmented into small blocks where each block is processed as an individual entity. Experimental results show enhancement in the local detection with linear modeling over the global.

Energy minimization approach to motion estimation

Abstract In this paper, we cast motion estimation as a problem in energy minimization. This is achieved by modeling the displacement field as a Markov random field. The equivalence of a Markov random field and a Gibbs distribution is then used to convert the problem into one of defining an appropriate energy function that describes the motion and any constraints imposed on it. The energy function is then minimized using the Mean Field Annealing algorithm, a technique which finds the global or near global minima in nonconvex optimization problems. An analysis of the algorithm and experiment results are presented.

Symmetrical pattern and PCA based framework for fault detection and classification in power systems

An important attribute of an electrical power system is the continuity of service with a high level of reliability. This motivated many researchers to investigate power systems in an effort to improve reliability by focusing on fault detection and classification. In this work, a new electrical protective relaying framework to detect and classify any fault type in an electrical power system is presented. This work will use readings of the phase current only during the first (1/4)th of a cycle in an integrated method that combines symmetrical components technique with the principal component analysis (PCA) to declare, identify, and classify a fault. Furthermore, our approach also distinguishes a real fault from a transient one and can be used in either a transmission or a distribution system. Implementation results using PSCAD are also presented.

A computer-aided diagnosis system for breast cancer using independent component analysis and fuzzy classifier

Screening mammograms is a repetitive task that causes fatigue and eye strain since for every thousand cases analyzed by a radiologist, only 3-4 are cancerous and thus an abnormality may be overlooked. Computer-aided detection (CAD) algorithms were developed to assist radiologists in detecting mammographic lesions. In this paper, a computer-aided detection and diagnosis (CADD) system for breast cancer is developed. The framework is based on combining principal component analysis (PCA), independent component analysis (ICA), and a fuzzy classifier to identify and label suspicious regions. This is a novel approach since it uses a fuzzy classifier integrated into the ICA model. Implemented and tested using MIAS database. This algorithm results in the classification of a mammogram as either normal or abnormal. Furthermore, if abnormal, it differentiates it into a benign or a malignant tissue. Results show that this system has 84.03% accuracy in detecting all kinds of abnormalities and 78% diagnosis accuracy.

An image segmentation algorithm for the detection of rebar in bridge decks from GPR scans

Ground penetrating radar (GPR) scans of rebar embedded in concrete structures produce distinct hyperbolic signatures. These signatures can be removed from the data as a preprocess to the identification of other embedded objects. This work is a step towards achieving an unsupervised detection of defects in concrete bridge decks. The proposed algorithm detects the signature of rebar(s) in a GPR scan through image segmentation, arc detection, and a thresholding process. The position and depth of the rebar(s) and the dielectric properties of the concrete are derived.

Hybrid mammogram classification using rough set and fuzzy classifier

We propose a computer aided detection (CAD) system for the detection and classification of suspicious regions in mammographic images. This system combines a dimensionality reduction module (using principal component analysis), a feature extraction module (using independent component analysis), and a feature subset selection module (using rough set model). Rough set model is used to reduce the effect of data inconsistency while a fuzzy classifier is integrated into the system to label subimages into normal or abnormal regions. The experimental results show that this system has an accuracy of 84.03% and a recall percentage of 87.28%.

Bayesian classifier with simplified learning phase for detecting microcalcifications in digital mammograms

Detection of clustered microcalcifications (MCs) in mammograms represents a significant step towards successful detection of breast cancer since their existence is one of the early signs of cancer. In this paper, a new framework that integrates Bayesian classifier and a pattern synthesizing scheme for detecting microcalcification clusters is proposed. This proposed work extracts textural, spectral, and statistical features of each input mammogram and generates models of real MCs to be used as training samples through a simplified learning phase of the Bayesian classifier. Followed by an estimation of the classifiers decision function parameters, a mammogram is segmented into the identified targets (MCs) against background (healthy tissue). The proposed algorithm has been tested using 23 mammograms from the mini-MIAS database. Experimental results achieved MCs detection with average true positive (sensitivity) and false positive (specificity) of 91.3% and 98.6%, respectively. Results also indicate that the modeling of the real MCs plays a significant role in the performance of the classifier and thus should be given further investigation.

Road sign detection and shape recognition invariant to sign defects

This paper proposes an automated method for road sign detection and shape recognition based on the color of the road sign and its geometric attributes. Our proposed shape recognition algorithm can be part of a driver assistant system (DAS), autonomous vehicles, or road sign maintenance system to improve both recognition and processing time efficiency by categorizing road sign database to smaller groups according to their colors and shapes. The method consists of three stages: 1) the color based segmentation stage; 2) the detection of the region of interest (ROI) using geometric means; and 3) the shape recognition of the road sign stage using geometric dimensions of symmetrical sign shape outlines. Our results show that this method has the ability to detect and recognize rectangular, octagonal, triangular, diamond, and pentagonal shapes. The significance of this work is in its ability to detect and recognize the shapes of signs that are defective such as when the sign is partially occluded, scaled, or tilted.

Ground-Penetrating Radar, Chain Drag, and Ground Truth : Correlation of Bridge Deck Assessment Data

Determining the degree of degradation of a bridge can be one of the most difficult problems that infrastructure inspectors face. While traditional bridge inspection methods such as visual and chain drag will always play a role in bridge condition assessment, more sophisticated and accurate techniques such as ground-penetrating radar (GPR) are gradually gaining acceptance by departments of transportation. GPR is a nondestructive evaluation method that can be used to assess the integrity of roads, pavements, bridges, and buildings. It uses high-frequency electromagnetic waves at the microwave or radio frequency range to examine the subsurface condition. This technique is used to detect features, such as cracks, voids, and delamination. An evaluation was made of GPR effectiveness in condition assessment compared with effectiveness of chain drag and ground truth method (cores) of two concrete bridge decks. Results show that the GPR method has potential as a practical and economically viable means for bridge assessment.

USING NON-DESTRUCTIVE TECHNOLOGIES AND METHODS IN BRIDGE MANAGEMENT SYSTEMS

There are over 570,000 bridges in the United States, with 12% of those located in urban areas. Of the urban bridges, 10% are structurally deficient and 22% are functionally deficient. As the thousands of bridges are an important component of the automotive transportation infrastructure, their maintenance is of utmost importance. This paper has emphasizes the importance of bridge maintenance systems (BMS) in keeping the U.S. inventory of bridges well maintained and functional. Also highlighted is the value of non-destructive evaluation technologies and methods, and the role they can play in BMS. Some of the issues and concerns associated with using NDS methods to assess the condition of bridges are highlighted.