Xavier Maldague - Academia.edu (original) (raw)

Papers by Xavier Maldague

Applied Sciences

Finding efficient and less expensive techniques for different aspects of culvert inspection is in... more Finding efficient and less expensive techniques for different aspects of culvert inspection is in great demand. This study assesses the potential of infrared thermography (IRT) to detect the presence of cavities in the soil around a culvert, specifically for cavities adjacent to the pipe of galvanized culverts. To identify cavities, we analyze thermograms, generated via long pulse thermography, using absolute thermal contrast, principal components thermography, and a statistical approach along with a combination of different pre- and post-processing algorithms. Using several experiments, we evaluate the performance of IRT for accomplishing the given task. Empirical results show a promising future for the application of this approach in culvert inspection. The size and location of cavities are among the aspects that can be extracted from analyzing thermograms. The key finding of this research is that the proposed approach can provide useful information about a certain type of problem...

Engineering Proceedings

Thermography has been employed broadly as a corresponding diagnostic instrument in breast cancer ... more Thermography has been employed broadly as a corresponding diagnostic instrument in breast cancer diagnosis. Among thermographic techniques, deep neural networks show an unequivocal potential to detect heterogeneous thermal patterns related to vasodilation in breast cancer cases. Such methods are used to extract high-dimensional thermal features, known as deep thermomics. In this study, we applied convex non-negative matrix factorization (convex NMF) to extract three predominant bases of thermal sequences. Then, the data were fed into a sparse autoencoder model, known as SPAER, to extract low-dimensional deep thermomics, which were then used to assist the clinical breast exam (CBE) in breast cancer screening. The application of convex NMF-SPAER, combining clinical and demographic covariates, yielded a result of 79.3% (73.5%, 86.9%); the highest result belonged to NMF-SPAER at 84.9% (79.3%, 88.7%). The proposed approach preserved thermal heterogeneity and led to early detection of bre...

ArXiv, 2020

Multiscale shape skeletonization on pixel adjacency graphs is an advanced intriguing research sub... more Multiscale shape skeletonization on pixel adjacency graphs is an advanced intriguing research subject in the field of image processing, computer vision and data mining. The previous works in this area almost focused on the graph vertices. We proposed novel structured based graph morphological transformations based on edges opposite to the current node based transformations and used them for deploying skeletonization and reconstruction of infrared thermal images represented by graphs. The advantage of this method is that many widely used path based approaches become available within this definition of morphological operations. For instance, we use distance maps and image foresting transform (IFT) as two main path based methods are utilized for computing the skeleton of an image. Moreover, In addition, the open question proposed by Maragos et al (2013) about connectivity of graph skeletonization method are discussed and shown to be quite difficult to decide in general case.

In this paper, a study is presented indicating that the specimen shape, for orientation smaller t... more In this paper, a study is presented indicating that the specimen shape, for orientation smaller than about 30°, does not affect the blind frequency obtained in Pulsed Phase Thermography processing. Therefore, it makes this measurement suitable for depth inversion in the case of non-flat shaped specimens. Theory and experimental results are discussed.

The temporal change in temperature for the surface of a steel plate under kerosene flame exposure... more The temporal change in temperature for the surface of a steel plate under kerosene flame exposure is measured without contact using the two-colour pyrometry technique. The pyrometric temperatures from room temperature to 600°C were obtained with a multispectral infrared camera equipped with a fast rotating wheel (50x8 to 365/8 frames/seconds) with two ’’through flame filters’’ at 3800 nm and 3950 nm. The calculated pyrometric temperatures were validated with the temperature data of three thermocouples incorporated at three different locations in the back of the steel plate (T1 in the center of the kerosene flame, T2 & T3 are at 5 & 13 cm from center).

We present a method to extract defects automatically by image segmentation. The images used for s... more We present a method to extract defects automatically by image segmentation. The images used for segmentation are the raw thermal images and the resulting images obtained by 5 commonly used data processing techniques in optical pulsed thermography. At the end of this article, probability of detection (PoD) analysis results after automated segmentation of raw/processed images are compared with the results obtained from manual evaluation. False alarm which is an important aspect of reliability evaluation of nondestructive technique is also studied.

2017 Brazilian Conference on Intelligent Systems (BRACIS), 2017

The use of composite materials such as fiber reinforced materials has grown in the recent years. ... more The use of composite materials such as fiber reinforced materials has grown in the recent years. This growth is mainly due to their advantageous properties. They are typically lighter when compared to metals and more resident to corrosion. The resistance and stiffness of this materials are directly related to their fiber orientation. Thus, efficient approaches to assess their fiber orientation are in demand. In this paper, a non-destructive evaluation method is used to assess the fiber orientation on laminates reinforced with continuous fibers and randomly-oriented strands parts. More specifically, a thremography method called pulsed thermal ellipsometry is combined with an artificial neural network in order to estimate the fiber orientation on the surface of inspected parts. Results showed that the method can be efficiently used to inspect potentially large areas, i.e., with accuracy and speed.

In the context of infrared thermographic NDT, the whole acquisition chain is first reviewed inclu... more In the context of infrared thermographic NDT, the whole acquisition chain is first reviewed including the required pre-processing stages needed to r store images from degradations such as vignetting, camera noise and dead pixels. Polynomial conversion to temperature values is next. Secondly, the processing steps ar discussed following two main directions: qualitative imaging which requires im age enhancement and quantitative imaging aimed at defect detection, defect quantif ication and thermal properties assessments. Supporting examples taken from inf rared thermographic NDT are presented to support the varios discussed techniques.

Diagnosis and prognosis of failures for aircrafts’ integrity are some of the most important regul... more Diagnosis and prognosis of failures for aircrafts’ integrity are some of the most important regular functionalities in complex and safety-critical aircraft structures. Further, development of failure diagnostic tools such as Non-Destructive Testing (NDT) techniques, in particular, for aircraft composite materials, has been seen as a subject of intensive research over the last decades. The need for diagnostic and prognostic tools for composite materials in aircraft applications rises and draws increasing attention. Yet, there is still an ongoing need for developing new failure diagnostic tools to respond to the rapid industrial development and complex machine design. Such tools will ease the early detection and isolation of developing defects and the prediction of damages propagation; thus allowing for early implementation of preventive maintenance and serve as a countermeasure to the potential of catastrophic failure. This paper provides a brief literature review of recent research ...

In this paper, shortwave infrared (SWIR), mid-wave infrared (MWIR) thermography, air-coupled ultr... more In this paper, shortwave infrared (SWIR), mid-wave infrared (MWIR) thermography, air-coupled ultrasound (ACU), and X-ray radiography results were combined to retrieve the differences between a painting on the canvas sample constructed following the art master rules and an imitation far from it. Advanced image processing techniques including pulsed phase thermography (PPT), principal component thermography (PCT), and partial least square thermography (PLST) were applied to the MWIR images in order to highlight the shapes of subsurface features. Interestingly, additional defects were also discovered since the samples were handmade. Finally, a comprehensive and comparative study of these techniques was conducted to summarize their advantages and disadvantages.

Manufacturers are constantly looking for more cost-efficient means to produce aircraft components... more Manufacturers are constantly looking for more cost-efficient means to produce aircraft components. An effective way to do this is to reduce the weight, which results in less fuel required to power the aircraft. This has led to an increased use of composite materials. Carbon fibre reinforced polymer (CFRP) composite is used in industries where high strength and rigidity are required in relation to weight. e.g. in aviation – transport. The fibre-reinforced matrix systems are extremely strong (i.e. have excellent mechanical properties and high resistance to corrosion). However, because of the nature of the CFRP, it does not dint or bend, as aluminium would do when damaged, it makes it difficult to locate structural damage, especially subsurface. Non-Destructive Testing (NDT) is a wide group of analysis techniques used to evaluate the properties of a material, component or system without causing damage to the operator or material. Active Thermography is one of the NDT risk-free methods ...

Marbling (intramuscular fat tissue) in beef meat is one of the most important criteria for qualit... more Marbling (intramuscular fat tissue) in beef meat is one of the most important criteria for quality, notably juiciness, in meat grading systems. Visual inspection of the meat surface is the common way to assign quality grading level, which is accomplished by authorized experts called graders. In the last years, several works were proposed in order to introduce computer vision on meat quality evaluation. In these works, meat grading was based exclusively on the analysis of meat surface images. In this paper, a new technique using near-infrared light in transmission mode is used to evaluate the beef meat quality based on the marbling detection. It is demonstrated that using near-infrared light in transmission mode, it is possible to detect the fat not only on the surface, as in traditional methods, but also under the surface. Also, in combining the analysis of the two sides of the meat simple, it is possible to estimate the volumetric marbling. We compared results from traditional tech...

Ndt & E International, 2017

Applied Sciences

Dimensional reduction methods have significantly improved the simplification of Pulsed Thermograp... more Dimensional reduction methods have significantly improved the simplification of Pulsed Thermography (PT) data while improving the accuracy of the results. Such approaches reduce the quantity of data to analyze and improve the contrast of the main defects in the samples contributed to their popularity. Many works have been proposed in the literature mainly based on improving the Principal Component Thermography (PCT). Recently the Independent Component Analysis (ICA) has been a topic of attention. Many different approaches have been proposed in the literature to solve the ICA. In this paper, we investigated several recent ICA methods and evaluated their influence on PT data compared with the state-of-the-art methods. We conducted our evaluation on reference CFRP samples with known defects. We found that ICA outperform PCT for small and deep defects. For other defects ICA results are often not far from the results obtained by PCT. However, the frequency of acquisition and the ICA meth...

In this day and age, parts manufacturers are expected to meet the stringiest quality standards de... more In this day and age, parts manufacturers are expected to meet the stringiest quality standards despite the increasing diversity and complexity of the parts they are making. Traditional inspection techniques are often inadequate or too expensive for mass production, so companies rely on a statistical approach to meet their quality objectives. To help reduce the costs associated with parts inspection and make 100% inspection possible, we propose a new method, based on artificial intelligence, that can perform automated defect recognition (ADR) in a high volume part production environment. In this paper, we will discuss the application of a state of the art deep convolutional network method that has been proven effective in the automated detection and identification of defects through semantic segmentation of radiographic imagery. The performance of a deep convolutional network, which is based on an encoder-decoder architecture called SegNet, are presented using real-life porosity samp...

In pulsed thermography the sample to test is briefly heated with a Dirac δ heat impulse and then ... more In pulsed thermography the sample to test is briefly heated with a Dirac δ heat impulse and then observed through an infrared (IR) camera recording thermal images as the sample is cooling down. The difference of temperature on the IR images between the defective areas and the sound areas is referred to as a thermal contrast [1]. The Signal-to-Noise Ratio (SNR) of such a contrast is strongly affected by the non uniformity of the initial heating impulse over the specimen. This paper describes a way to enhance this SNR by comparing the temperature evolution of each pixel of the image against the temperature evolution of a heat transfer model.

Glass Fiber Reinforced Plastic (GFRP) is a plastic material reinforced by fine fibers of glass. V... more Glass Fiber Reinforced Plastic (GFRP) is a plastic material reinforced by fine fibers of glass. Various defects may appear when manufacturing this product, i.e. delamination, porosity, undesired inserts, material discontinuity, etc. One of the applications of GFRP is in aerospace industry. In this context, the “Centre Technologiqu e en Aérospatiale (CTA)” provided us with some GFRPs including the aforementioned defects in order to find a non-destructive technique, which has the potential of detecting all of the def ects. We used the equipments in our research chair (MiviM) to inspect the specimens with differe nt techniques including Near/Shortwave Infrared, Ultrasound Thermography, and Optical Puls ed/Lock-in Thermography. The experimental results showed that the Near Infrared inspection has the best performance among the other techniques, because of the semi-transpare ncy of GFRP under Near Infrared illumination. Using Near Infrared inspection, we we re able to observe all of the ...

Applied Sciences

Finding efficient and less expensive techniques for different aspects of culvert inspection is in... more Finding efficient and less expensive techniques for different aspects of culvert inspection is in great demand. This study assesses the potential of infrared thermography (IRT) to detect the presence of cavities in the soil around a culvert, specifically for cavities adjacent to the pipe of galvanized culverts. To identify cavities, we analyze thermograms, generated via long pulse thermography, using absolute thermal contrast, principal components thermography, and a statistical approach along with a combination of different pre- and post-processing algorithms. Using several experiments, we evaluate the performance of IRT for accomplishing the given task. Empirical results show a promising future for the application of this approach in culvert inspection. The size and location of cavities are among the aspects that can be extracted from analyzing thermograms. The key finding of this research is that the proposed approach can provide useful information about a certain type of problem...

Engineering Proceedings

Thermography has been employed broadly as a corresponding diagnostic instrument in breast cancer ... more Thermography has been employed broadly as a corresponding diagnostic instrument in breast cancer diagnosis. Among thermographic techniques, deep neural networks show an unequivocal potential to detect heterogeneous thermal patterns related to vasodilation in breast cancer cases. Such methods are used to extract high-dimensional thermal features, known as deep thermomics. In this study, we applied convex non-negative matrix factorization (convex NMF) to extract three predominant bases of thermal sequences. Then, the data were fed into a sparse autoencoder model, known as SPAER, to extract low-dimensional deep thermomics, which were then used to assist the clinical breast exam (CBE) in breast cancer screening. The application of convex NMF-SPAER, combining clinical and demographic covariates, yielded a result of 79.3% (73.5%, 86.9%); the highest result belonged to NMF-SPAER at 84.9% (79.3%, 88.7%). The proposed approach preserved thermal heterogeneity and led to early detection of bre...

ArXiv, 2020

Multiscale shape skeletonization on pixel adjacency graphs is an advanced intriguing research sub... more Multiscale shape skeletonization on pixel adjacency graphs is an advanced intriguing research subject in the field of image processing, computer vision and data mining. The previous works in this area almost focused on the graph vertices. We proposed novel structured based graph morphological transformations based on edges opposite to the current node based transformations and used them for deploying skeletonization and reconstruction of infrared thermal images represented by graphs. The advantage of this method is that many widely used path based approaches become available within this definition of morphological operations. For instance, we use distance maps and image foresting transform (IFT) as two main path based methods are utilized for computing the skeleton of an image. Moreover, In addition, the open question proposed by Maragos et al (2013) about connectivity of graph skeletonization method are discussed and shown to be quite difficult to decide in general case.

In this paper, a study is presented indicating that the specimen shape, for orientation smaller t... more In this paper, a study is presented indicating that the specimen shape, for orientation smaller than about 30°, does not affect the blind frequency obtained in Pulsed Phase Thermography processing. Therefore, it makes this measurement suitable for depth inversion in the case of non-flat shaped specimens. Theory and experimental results are discussed.

The temporal change in temperature for the surface of a steel plate under kerosene flame exposure... more The temporal change in temperature for the surface of a steel plate under kerosene flame exposure is measured without contact using the two-colour pyrometry technique. The pyrometric temperatures from room temperature to 600°C were obtained with a multispectral infrared camera equipped with a fast rotating wheel (50x8 to 365/8 frames/seconds) with two ’’through flame filters’’ at 3800 nm and 3950 nm. The calculated pyrometric temperatures were validated with the temperature data of three thermocouples incorporated at three different locations in the back of the steel plate (T1 in the center of the kerosene flame, T2 & T3 are at 5 & 13 cm from center).

We present a method to extract defects automatically by image segmentation. The images used for s... more We present a method to extract defects automatically by image segmentation. The images used for segmentation are the raw thermal images and the resulting images obtained by 5 commonly used data processing techniques in optical pulsed thermography. At the end of this article, probability of detection (PoD) analysis results after automated segmentation of raw/processed images are compared with the results obtained from manual evaluation. False alarm which is an important aspect of reliability evaluation of nondestructive technique is also studied.

2017 Brazilian Conference on Intelligent Systems (BRACIS), 2017

The use of composite materials such as fiber reinforced materials has grown in the recent years. ... more The use of composite materials such as fiber reinforced materials has grown in the recent years. This growth is mainly due to their advantageous properties. They are typically lighter when compared to metals and more resident to corrosion. The resistance and stiffness of this materials are directly related to their fiber orientation. Thus, efficient approaches to assess their fiber orientation are in demand. In this paper, a non-destructive evaluation method is used to assess the fiber orientation on laminates reinforced with continuous fibers and randomly-oriented strands parts. More specifically, a thremography method called pulsed thermal ellipsometry is combined with an artificial neural network in order to estimate the fiber orientation on the surface of inspected parts. Results showed that the method can be efficiently used to inspect potentially large areas, i.e., with accuracy and speed.

In the context of infrared thermographic NDT, the whole acquisition chain is first reviewed inclu... more In the context of infrared thermographic NDT, the whole acquisition chain is first reviewed including the required pre-processing stages needed to r store images from degradations such as vignetting, camera noise and dead pixels. Polynomial conversion to temperature values is next. Secondly, the processing steps ar discussed following two main directions: qualitative imaging which requires im age enhancement and quantitative imaging aimed at defect detection, defect quantif ication and thermal properties assessments. Supporting examples taken from inf rared thermographic NDT are presented to support the varios discussed techniques.

Diagnosis and prognosis of failures for aircrafts’ integrity are some of the most important regul... more Diagnosis and prognosis of failures for aircrafts’ integrity are some of the most important regular functionalities in complex and safety-critical aircraft structures. Further, development of failure diagnostic tools such as Non-Destructive Testing (NDT) techniques, in particular, for aircraft composite materials, has been seen as a subject of intensive research over the last decades. The need for diagnostic and prognostic tools for composite materials in aircraft applications rises and draws increasing attention. Yet, there is still an ongoing need for developing new failure diagnostic tools to respond to the rapid industrial development and complex machine design. Such tools will ease the early detection and isolation of developing defects and the prediction of damages propagation; thus allowing for early implementation of preventive maintenance and serve as a countermeasure to the potential of catastrophic failure. This paper provides a brief literature review of recent research ...

In this paper, shortwave infrared (SWIR), mid-wave infrared (MWIR) thermography, air-coupled ultr... more In this paper, shortwave infrared (SWIR), mid-wave infrared (MWIR) thermography, air-coupled ultrasound (ACU), and X-ray radiography results were combined to retrieve the differences between a painting on the canvas sample constructed following the art master rules and an imitation far from it. Advanced image processing techniques including pulsed phase thermography (PPT), principal component thermography (PCT), and partial least square thermography (PLST) were applied to the MWIR images in order to highlight the shapes of subsurface features. Interestingly, additional defects were also discovered since the samples were handmade. Finally, a comprehensive and comparative study of these techniques was conducted to summarize their advantages and disadvantages.

Manufacturers are constantly looking for more cost-efficient means to produce aircraft components... more Manufacturers are constantly looking for more cost-efficient means to produce aircraft components. An effective way to do this is to reduce the weight, which results in less fuel required to power the aircraft. This has led to an increased use of composite materials. Carbon fibre reinforced polymer (CFRP) composite is used in industries where high strength and rigidity are required in relation to weight. e.g. in aviation – transport. The fibre-reinforced matrix systems are extremely strong (i.e. have excellent mechanical properties and high resistance to corrosion). However, because of the nature of the CFRP, it does not dint or bend, as aluminium would do when damaged, it makes it difficult to locate structural damage, especially subsurface. Non-Destructive Testing (NDT) is a wide group of analysis techniques used to evaluate the properties of a material, component or system without causing damage to the operator or material. Active Thermography is one of the NDT risk-free methods ...

Marbling (intramuscular fat tissue) in beef meat is one of the most important criteria for qualit... more Marbling (intramuscular fat tissue) in beef meat is one of the most important criteria for quality, notably juiciness, in meat grading systems. Visual inspection of the meat surface is the common way to assign quality grading level, which is accomplished by authorized experts called graders. In the last years, several works were proposed in order to introduce computer vision on meat quality evaluation. In these works, meat grading was based exclusively on the analysis of meat surface images. In this paper, a new technique using near-infrared light in transmission mode is used to evaluate the beef meat quality based on the marbling detection. It is demonstrated that using near-infrared light in transmission mode, it is possible to detect the fat not only on the surface, as in traditional methods, but also under the surface. Also, in combining the analysis of the two sides of the meat simple, it is possible to estimate the volumetric marbling. We compared results from traditional tech...

Ndt & E International, 2017

Applied Sciences

Dimensional reduction methods have significantly improved the simplification of Pulsed Thermograp... more Dimensional reduction methods have significantly improved the simplification of Pulsed Thermography (PT) data while improving the accuracy of the results. Such approaches reduce the quantity of data to analyze and improve the contrast of the main defects in the samples contributed to their popularity. Many works have been proposed in the literature mainly based on improving the Principal Component Thermography (PCT). Recently the Independent Component Analysis (ICA) has been a topic of attention. Many different approaches have been proposed in the literature to solve the ICA. In this paper, we investigated several recent ICA methods and evaluated their influence on PT data compared with the state-of-the-art methods. We conducted our evaluation on reference CFRP samples with known defects. We found that ICA outperform PCT for small and deep defects. For other defects ICA results are often not far from the results obtained by PCT. However, the frequency of acquisition and the ICA meth...

In this day and age, parts manufacturers are expected to meet the stringiest quality standards de... more In this day and age, parts manufacturers are expected to meet the stringiest quality standards despite the increasing diversity and complexity of the parts they are making. Traditional inspection techniques are often inadequate or too expensive for mass production, so companies rely on a statistical approach to meet their quality objectives. To help reduce the costs associated with parts inspection and make 100% inspection possible, we propose a new method, based on artificial intelligence, that can perform automated defect recognition (ADR) in a high volume part production environment. In this paper, we will discuss the application of a state of the art deep convolutional network method that has been proven effective in the automated detection and identification of defects through semantic segmentation of radiographic imagery. The performance of a deep convolutional network, which is based on an encoder-decoder architecture called SegNet, are presented using real-life porosity samp...

In pulsed thermography the sample to test is briefly heated with a Dirac δ heat impulse and then ... more In pulsed thermography the sample to test is briefly heated with a Dirac δ heat impulse and then observed through an infrared (IR) camera recording thermal images as the sample is cooling down. The difference of temperature on the IR images between the defective areas and the sound areas is referred to as a thermal contrast [1]. The Signal-to-Noise Ratio (SNR) of such a contrast is strongly affected by the non uniformity of the initial heating impulse over the specimen. This paper describes a way to enhance this SNR by comparing the temperature evolution of each pixel of the image against the temperature evolution of a heat transfer model.

Glass Fiber Reinforced Plastic (GFRP) is a plastic material reinforced by fine fibers of glass. V... more Glass Fiber Reinforced Plastic (GFRP) is a plastic material reinforced by fine fibers of glass. Various defects may appear when manufacturing this product, i.e. delamination, porosity, undesired inserts, material discontinuity, etc. One of the applications of GFRP is in aerospace industry. In this context, the “Centre Technologiqu e en Aérospatiale (CTA)” provided us with some GFRPs including the aforementioned defects in order to find a non-destructive technique, which has the potential of detecting all of the def ects. We used the equipments in our research chair (MiviM) to inspect the specimens with differe nt techniques including Near/Shortwave Infrared, Ultrasound Thermography, and Optical Puls ed/Lock-in Thermography. The experimental results showed that the Near Infrared inspection has the best performance among the other techniques, because of the semi-transpare ncy of GFRP under Near Infrared illumination. Using Near Infrared inspection, we we re able to observe all of the ...