Pub Date : 2020-07-23DOI: 10.1080/17686733.2020.1793284
R. Kidangan, C. Krishnamurthy, K. Balasubramaniam
ABSTRACT The Inner Fixed Structure (IFS) bond panel is a honeycomb sandwich panel with CFRP facesheet and a heat shield on one side, and a perforated CFRP facesheet on the other side, of a jet engine nacelle. It is subjected to extreme temperature on both sides which damages the inner epoxy adhesive bond between the facesheet and the honeycomb core. Accessibility to this layer for non-destructive evaluation is extremely challenging using conventional methods. This work proposes active thermography techniques such as flash thermography and induction thermography for accessing the inner layer. The infrared camera utilises the perforations in the facesheet of the IFS bond panel, which is used for attenuating the engine noise, for imaging the defects. However, flash thermography requires the removal of the thermal insulation layer for the inspection, whereas induction thermography can be performed without any modifications to the structure. The minimum detectable dis-bond size using these techniques is restricted to the spacing between the perforations on the facesheet. A numerical model has developed for induction thermography to optimise the excitation frequency that can produce reasonable thermal contrast at the inner facesheet and minimum temperature rise on the intermediate stainless-steel thin sheet that covers the thermal insulation layer.
{"title":"Detection of dis-bond between honeycomb and composite facesheet of an Inner Fixed Structure bond panel of a jet engine nacelle using infrared thermographic techniques","authors":"R. Kidangan, C. Krishnamurthy, K. Balasubramaniam","doi":"10.1080/17686733.2020.1793284","DOIUrl":"https://doi.org/10.1080/17686733.2020.1793284","url":null,"abstract":"ABSTRACT The Inner Fixed Structure (IFS) bond panel is a honeycomb sandwich panel with CFRP facesheet and a heat shield on one side, and a perforated CFRP facesheet on the other side, of a jet engine nacelle. It is subjected to extreme temperature on both sides which damages the inner epoxy adhesive bond between the facesheet and the honeycomb core. Accessibility to this layer for non-destructive evaluation is extremely challenging using conventional methods. This work proposes active thermography techniques such as flash thermography and induction thermography for accessing the inner layer. The infrared camera utilises the perforations in the facesheet of the IFS bond panel, which is used for attenuating the engine noise, for imaging the defects. However, flash thermography requires the removal of the thermal insulation layer for the inspection, whereas induction thermography can be performed without any modifications to the structure. The minimum detectable dis-bond size using these techniques is restricted to the spacing between the perforations on the facesheet. A numerical model has developed for induction thermography to optimise the excitation frequency that can produce reasonable thermal contrast at the inner facesheet and minimum temperature rise on the intermediate stainless-steel thin sheet that covers the thermal insulation layer.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"19 1","pages":"12 - 26"},"PeriodicalIF":2.5,"publicationDate":"2020-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2020.1793284","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42985598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-22DOI: 10.1080/17686733.2020.1766892
Yahya Moshaei-Nezhad, Juliane Müller, C. Schnabel, M. Kirsch, R. Tetzlaff
ABSTRACT In brain surgery, respiration motion, outliers, and occlusions create artefacts in Infrared Thermography (IRT) imaging. In this paper, we propose a robust method to handle multiple motion, outliers, and occlusions in IRT images which consists of two phases: preprocessing and image motion estimation. In the preprocessing phase, the Region of Interest (RoI) segmentation is employed to extract the brain cortex only. Thereafter, the Phase Correlation method is employed to compensate for large motion followed by occlusion masking based on an approach applying Cellular Nonlinear Networks (CNN). Next, intensity adjustment is made with respect to the reference image. Then, a Gaussian filter is applied. In the following phase, the image motion is estimated by employing Combined Local-Global (CLG) optical flow method. In order to find the best regularization coefficient for the spatial coherency term and the number of iterations for recursive optical flow estimation, we generated ground truth and evaluated the accuracy of the estimated motion vectors based on Average Angular Error (AAE) and Average Magnitude Error (AME). The efficiency improvement of the proposed method was tested on 1024 IRT images based on different comparisons. Thereby, the proposed method shows promising results for motion estimation and correction application in brain surgery.
{"title":"A robust optical flow motion estimation and correction method for IRT imaging in brain surgery","authors":"Yahya Moshaei-Nezhad, Juliane Müller, C. Schnabel, M. Kirsch, R. Tetzlaff","doi":"10.1080/17686733.2020.1766892","DOIUrl":"https://doi.org/10.1080/17686733.2020.1766892","url":null,"abstract":"ABSTRACT In brain surgery, respiration motion, outliers, and occlusions create artefacts in Infrared Thermography (IRT) imaging. In this paper, we propose a robust method to handle multiple motion, outliers, and occlusions in IRT images which consists of two phases: preprocessing and image motion estimation. In the preprocessing phase, the Region of Interest (RoI) segmentation is employed to extract the brain cortex only. Thereafter, the Phase Correlation method is employed to compensate for large motion followed by occlusion masking based on an approach applying Cellular Nonlinear Networks (CNN). Next, intensity adjustment is made with respect to the reference image. Then, a Gaussian filter is applied. In the following phase, the image motion is estimated by employing Combined Local-Global (CLG) optical flow method. In order to find the best regularization coefficient for the spatial coherency term and the number of iterations for recursive optical flow estimation, we generated ground truth and evaluated the accuracy of the estimated motion vectors based on Average Angular Error (AAE) and Average Magnitude Error (AME). The efficiency improvement of the proposed method was tested on 1024 IRT images based on different comparisons. Thereby, the proposed method shows promising results for motion estimation and correction application in brain surgery.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"18 1","pages":"226 - 251"},"PeriodicalIF":2.5,"publicationDate":"2020-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2020.1766892","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47755944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-13DOI: 10.1080/17686733.2020.1793283
S. Pérez-Buitrago, Sara Tobón-Pareja, Yeraldín Gómez-Gaviria, A. Guerrero-Peña, Gloria Díaz-Londoño
ABSTRACT Multiple sclerosis (MS) is a progressive and degenerative disease that causes nerve conduction blocks due to demyelination in the central nervous system. Most MS patients experience a worsening of clinical signs and neurological symptoms when they are exposed to heat due to a thermoregulatory dysfunction. This paper proposes a novel methodology to understand temperature changes in MS patients by obtaining and evaluating texture features from infrared thermography (IRT) images. For that purpose, images of the legs of a MS patient and a healthy control subject with similar physical characteristics (while at rest and in a standing position) were recorded using a FLIR A655SC infrared camera. In the quantitative analysis of the resulting IRT images, three texture features (average, entropy, and uniformity) were computed, and the results were compared using statistical techniques. The statistical analysis showed that temperatures in the MS patient were not normally distributed, while those in the healthy control subject were normally distributed. In addition, significant differences in average, entropy, and uniformity were found between subjects. This methodology enables a quantitative evaluation of thermal distributions over different regions of the body and can be used in further studies into temperature changes in MS patients.
{"title":"Methodology to evaluate temperature changes in multiple sclerosis patients by calculating texture features from infrared thermography images","authors":"S. Pérez-Buitrago, Sara Tobón-Pareja, Yeraldín Gómez-Gaviria, A. Guerrero-Peña, Gloria Díaz-Londoño","doi":"10.1080/17686733.2020.1793283","DOIUrl":"https://doi.org/10.1080/17686733.2020.1793283","url":null,"abstract":"ABSTRACT Multiple sclerosis (MS) is a progressive and degenerative disease that causes nerve conduction blocks due to demyelination in the central nervous system. Most MS patients experience a worsening of clinical signs and neurological symptoms when they are exposed to heat due to a thermoregulatory dysfunction. This paper proposes a novel methodology to understand temperature changes in MS patients by obtaining and evaluating texture features from infrared thermography (IRT) images. For that purpose, images of the legs of a MS patient and a healthy control subject with similar physical characteristics (while at rest and in a standing position) were recorded using a FLIR A655SC infrared camera. In the quantitative analysis of the resulting IRT images, three texture features (average, entropy, and uniformity) were computed, and the results were compared using statistical techniques. The statistical analysis showed that temperatures in the MS patient were not normally distributed, while those in the healthy control subject were normally distributed. In addition, significant differences in average, entropy, and uniformity were found between subjects. This methodology enables a quantitative evaluation of thermal distributions over different regions of the body and can be used in further studies into temperature changes in MS patients.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"19 1","pages":"1 - 11"},"PeriodicalIF":2.5,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2020.1793283","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47140620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-06DOI: 10.1080/17686733.2020.1771529
M. Groz, A. Sommier, E. Abisset, S. Chevalier, J. Battaglia, J. Batsale, C. Pradère
ABSTRACT The main goal of this paper is the estimation of thermal resistive fields in multilayer samples using the classical front face flash method as excitation and InfRared Thermography (IRT) as a monitoring sensor. The complete inverse processing of a multilayer analytical model can be difficult due to a lack of sensitivity to certain parameters (layer thickness, depth of thermal resistance, etc.) or processing time. For these reasons, our present strategy proposes a Bayesian inference approach. Using the analytical quadrupole method, a reference model can be calculated for a set of parameters. Then, the Bayesian probabilistic method is used to determine the maximum likelihood probability between the measured data and the reference model. To keep the processing method robust and fast, an automatic selection of the calculation range is proposed. Finally, in the case of a bilayer sample, both the thickness and resistive 3D layers are estimated in less than 2 min for a space and time matrix of 50,000 pixels by 4000 time steps with a reasonable relative error of less than 5%.
{"title":"Thermal resistance field estimations from IR thermography using multiscale Bayesian inference","authors":"M. Groz, A. Sommier, E. Abisset, S. Chevalier, J. Battaglia, J. Batsale, C. Pradère","doi":"10.1080/17686733.2020.1771529","DOIUrl":"https://doi.org/10.1080/17686733.2020.1771529","url":null,"abstract":"ABSTRACT The main goal of this paper is the estimation of thermal resistive fields in multilayer samples using the classical front face flash method as excitation and InfRared Thermography (IRT) as a monitoring sensor. The complete inverse processing of a multilayer analytical model can be difficult due to a lack of sensitivity to certain parameters (layer thickness, depth of thermal resistance, etc.) or processing time. For these reasons, our present strategy proposes a Bayesian inference approach. Using the analytical quadrupole method, a reference model can be calculated for a set of parameters. Then, the Bayesian probabilistic method is used to determine the maximum likelihood probability between the measured data and the reference model. To keep the processing method robust and fast, an automatic selection of the calculation range is proposed. Finally, in the case of a bilayer sample, both the thickness and resistive 3D layers are estimated in less than 2 min for a space and time matrix of 50,000 pixels by 4000 time steps with a reasonable relative error of less than 5%.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"18 1","pages":"332 - 343"},"PeriodicalIF":2.5,"publicationDate":"2020-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2020.1771529","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43332871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-02DOI: 10.1080/17686733.2019.1646449
G. Laffaye, V. Epishev, I. Tetin, Y. Korableva, K. Naumova, E. Antonenko, V. Vavilov
ABSTRACT The purpose of this study has been to develop a multivariate model for predicting body fat mass in women by using the technique of infrared (IR) thermography. Sixty-nine healthy women, aged from 16 to 29, were investigated by using a body composition analyser and IR thermographic temperature measurement. The correlation analysis was performed to reveal the problem of multicollinearity. The technique of principal component analysis (PCA) was applied in order to reduce the number of variables. Both the total fat mass and the fat mass in the torso were accepted as the dependent variables. The individual scores were used as independent variables on each component after applying the orthogonal rotation. Two datasets were analysed: the full dataset with anthropometric characteristics (age, body mass, body length) and without anthropometric characteristics. The stepwise model meeting the Akaike information criterion (AIC) was selected to estimate the relative quality of all models. The models obtained on the full dataset were able to explain 73.9% of the fat mass in the torso and 70.4% of the total fat mass. Respectively, the models based on the reduced dataset explained 52.5% of the fat mass in the torso and 51.5% of the total fat mass.
{"title":"Predicting body fat mass by IR thermographic measurement of skin temperature: a novel multivariate model","authors":"G. Laffaye, V. Epishev, I. Tetin, Y. Korableva, K. Naumova, E. Antonenko, V. Vavilov","doi":"10.1080/17686733.2019.1646449","DOIUrl":"https://doi.org/10.1080/17686733.2019.1646449","url":null,"abstract":"ABSTRACT The purpose of this study has been to develop a multivariate model for predicting body fat mass in women by using the technique of infrared (IR) thermography. Sixty-nine healthy women, aged from 16 to 29, were investigated by using a body composition analyser and IR thermographic temperature measurement. The correlation analysis was performed to reveal the problem of multicollinearity. The technique of principal component analysis (PCA) was applied in order to reduce the number of variables. Both the total fat mass and the fat mass in the torso were accepted as the dependent variables. The individual scores were used as independent variables on each component after applying the orthogonal rotation. Two datasets were analysed: the full dataset with anthropometric characteristics (age, body mass, body length) and without anthropometric characteristics. The stepwise model meeting the Akaike information criterion (AIC) was selected to estimate the relative quality of all models. The models obtained on the full dataset were able to explain 73.9% of the fat mass in the torso and 70.4% of the total fat mass. Respectively, the models based on the reduced dataset explained 52.5% of the fat mass in the torso and 51.5% of the total fat mass.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"17 1","pages":"192 - 209"},"PeriodicalIF":2.5,"publicationDate":"2020-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2019.1646449","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44623476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-02DOI: 10.1080/17686733.2019.1646464
J. Suchan, G. Hendorfer
ABSTRACT We present a new imaging approach to determine porosity in carbon fibre-reinforced polymers by active thermography in the reflection mode. The infrared radiation is excited with help of a semiconductor laser. We use rectangular pulses for the excitation light – either single pulses or a sequence of a couple of pulses – and measure the succeeding temperature transients. These signals are transferred to the frequency domain by means of a discrete Laplace transformation. The evaluation of the thermal effusivity is done by a linear fitting process which gives unequivocal results with comparatively small error bars. The method is fast and robust, and the results compare well with prior experiments carried out with ultrasonic-testing, X-ray computed tomography or other approaches of thermography, where the thermal diffusivity has been determined.
{"title":"Thermal effusivity determination of carbon fibre-reinforced polymers by means of active thermography","authors":"J. Suchan, G. Hendorfer","doi":"10.1080/17686733.2019.1646464","DOIUrl":"https://doi.org/10.1080/17686733.2019.1646464","url":null,"abstract":"ABSTRACT We present a new imaging approach to determine porosity in carbon fibre-reinforced polymers by active thermography in the reflection mode. The infrared radiation is excited with help of a semiconductor laser. We use rectangular pulses for the excitation light – either single pulses or a sequence of a couple of pulses – and measure the succeeding temperature transients. These signals are transferred to the frequency domain by means of a discrete Laplace transformation. The evaluation of the thermal effusivity is done by a linear fitting process which gives unequivocal results with comparatively small error bars. The method is fast and robust, and the results compare well with prior experiments carried out with ultrasonic-testing, X-ray computed tomography or other approaches of thermography, where the thermal diffusivity has been determined.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"17 1","pages":"210 - 222"},"PeriodicalIF":2.5,"publicationDate":"2020-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2019.1646464","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48818612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-02DOI: 10.1080/17686733.2019.1639112
B. Chakraborty, B. K. Sinha
ABSTRACT Ladle breakout is a risky affair which is always present in steel making. The ladle breakout involves equipment damage and loss of production and sometimes loss of life. The present article describes the method of automatic detection of hotspot on the cold side of a ladle shell with the help of a group of infrared camera and subsequent processing of the infrared images in the LabVIEW platform. The system layout as implemented in the steel plant along with various pitfalls likely to be encountered during operation is discussed. Finally, the result of the trial run in the steel plant is presented. The system is found to be very effective as a preventive maintenance program to stop or minimise the ladle breakout.
{"title":"Process-integrated steel ladle monitoring, based on infrared imaging – a robust approach to avoid ladle breakout","authors":"B. Chakraborty, B. K. Sinha","doi":"10.1080/17686733.2019.1639112","DOIUrl":"https://doi.org/10.1080/17686733.2019.1639112","url":null,"abstract":"ABSTRACT Ladle breakout is a risky affair which is always present in steel making. The ladle breakout involves equipment damage and loss of production and sometimes loss of life. The present article describes the method of automatic detection of hotspot on the cold side of a ladle shell with the help of a group of infrared camera and subsequent processing of the infrared images in the LabVIEW platform. The system layout as implemented in the steel plant along with various pitfalls likely to be encountered during operation is discussed. Finally, the result of the trial run in the steel plant is presented. The system is found to be very effective as a preventive maintenance program to stop or minimise the ladle breakout.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"17 1","pages":"169 - 191"},"PeriodicalIF":2.5,"publicationDate":"2020-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2019.1639112","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45555790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-07-01DOI: 10.1080/17686733.2020.1786640
Tong Zhang, Xuxu Zhang
ABSTRACT Due to the narrow thermal window of infrared (IR) image sensor array, the represented image becomes dim and its details become blurred. Different contrast and detail enhancement technologies were deployed to improve image quality. An enhancement algorithm with bilateral filter is a state of art method, which first transforms an infrared image into a base part and a detail part, and then expands the detail part and suppresses the base part to enhancement the contrast of the IR image. However, this method cannot efficiently distinguish the background and objectives of the detail part. As a result, the noise information gets amplified when the detail part is expanded, leading to increase noise and to obstruct the sharpening of the detail part. To solve these problems, a novel enhancement algorithm based on the neutrosophic sets is proposed, which transforms the detail part into the neutrosophic domain. Our method utilises three membership functions of pixels in the neutrosophic domain: T (True), F (False) and I (Indeterminacy), which correspond to objective, background and transitional regions of image, respectively. The proposed algorithm is verified and compared with other existing algorithms. The experiment results show that the proposed algorithm can effectively enhance the contrast and preserve the details of an infrared image.
{"title":"A novel algorithm for infrared image contrast enhancement based on neutrosophic sets","authors":"Tong Zhang, Xuxu Zhang","doi":"10.1080/17686733.2020.1786640","DOIUrl":"https://doi.org/10.1080/17686733.2020.1786640","url":null,"abstract":"ABSTRACT Due to the narrow thermal window of infrared (IR) image sensor array, the represented image becomes dim and its details become blurred. Different contrast and detail enhancement technologies were deployed to improve image quality. An enhancement algorithm with bilateral filter is a state of art method, which first transforms an infrared image into a base part and a detail part, and then expands the detail part and suppresses the base part to enhancement the contrast of the IR image. However, this method cannot efficiently distinguish the background and objectives of the detail part. As a result, the noise information gets amplified when the detail part is expanded, leading to increase noise and to obstruct the sharpening of the detail part. To solve these problems, a novel enhancement algorithm based on the neutrosophic sets is proposed, which transforms the detail part into the neutrosophic domain. Our method utilises three membership functions of pixels in the neutrosophic domain: T (True), F (False) and I (Indeterminacy), which correspond to objective, background and transitional regions of image, respectively. The proposed algorithm is verified and compared with other existing algorithms. The experiment results show that the proposed algorithm can effectively enhance the contrast and preserve the details of an infrared image.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"18 1","pages":"344 - 356"},"PeriodicalIF":2.5,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2020.1786640","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45326054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-15DOI: 10.1080/17686733.2020.1768497
Vartika Mishra, S. K. Rath
ABSTRACT The patients having malignant breast tumours if detected in early stage have a better chance of survival. It is observed that the analysis of the texture features of the breast thermograms helps in providing the right information for diagnosis to a greater extent. In this study, the breast thermograms of 56 subjects having temperature recordings available at Database Mastology Research (DMR), visual labs are considered. Further, the texture features in the Gray level Run Length Matrix (GLRLM) and Gray level Co-occurrence Matrix (GLCM) are extracted from these images. The correlation of features gives a linear relationship between the variables that help to analyse the quantitative relationship between the variables. The features are selected by using unsupervised feature reduction techniques, i.e. Principal Component Analysis (PCA) and Autoencoder (AE). The features selected are observed to be relevant in detecting the abnormality between healthy and unhealthy breast. Different classifiers viz. support vector machine, decision tree, random forest, K-NN, linear Regression, and fuzzy logic are then applied to the selected features for detecting the presence of malignancy in breast. Among all the classifiers, Random Forest (RF) with PCA has been observed to yield an accuracy of 95.45% in classifying the benign and malignant tumours.
{"title":"Detection of breast cancer tumours based on feature reduction and classification of thermograms","authors":"Vartika Mishra, S. K. Rath","doi":"10.1080/17686733.2020.1768497","DOIUrl":"https://doi.org/10.1080/17686733.2020.1768497","url":null,"abstract":"ABSTRACT The patients having malignant breast tumours if detected in early stage have a better chance of survival. It is observed that the analysis of the texture features of the breast thermograms helps in providing the right information for diagnosis to a greater extent. In this study, the breast thermograms of 56 subjects having temperature recordings available at Database Mastology Research (DMR), visual labs are considered. Further, the texture features in the Gray level Run Length Matrix (GLRLM) and Gray level Co-occurrence Matrix (GLCM) are extracted from these images. The correlation of features gives a linear relationship between the variables that help to analyse the quantitative relationship between the variables. The features are selected by using unsupervised feature reduction techniques, i.e. Principal Component Analysis (PCA) and Autoencoder (AE). The features selected are observed to be relevant in detecting the abnormality between healthy and unhealthy breast. Different classifiers viz. support vector machine, decision tree, random forest, K-NN, linear Regression, and fuzzy logic are then applied to the selected features for detecting the presence of malignancy in breast. Among all the classifiers, Random Forest (RF) with PCA has been observed to yield an accuracy of 95.45% in classifying the benign and malignant tumours.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"18 1","pages":"300 - 313"},"PeriodicalIF":2.5,"publicationDate":"2020-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2020.1768497","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48165130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-12DOI: 10.1080/17686733.2020.1771528
Xingwang Guo, Liang Zhu
ABSTRACT Ultrasound excited vibro-thermography is based on the local heat generation due to the friction between the opposite surfaces of the defect, the plastic deformation around the defect, and/or the viscoelastic loss. This paper presents vibro-thermography applied to hybrid plates containing viscoelastic material when the viscoelastic heat generation mechanism alone is considered. The debonding-like calibrated defects without friction surfaces in the hybrid plate are detected. The dynamic temperature field is obtained by both experiment and numerical simulation. The influence of excitation frequency on the temperature increase over the defects is analysed by modelling the thermo-mechanical coupled field. The results show that the viscoelastic loss of the non-metal material is the leading factor of the local temperature increase over defects; an excitation frequency has its selective heating character to defects; a defect has a so-called defect characteristic frequency which can act as the optimal excitation frequency for this defect to be detected; the defect characteristic frequency is between the two local defect resonance frequencies corresponding to the simply supported boundary and the clamped boundary, respectively.
{"title":"Vibro-thermography of calibrated defects in hybrid plates focusing on viscoelastic heat generation","authors":"Xingwang Guo, Liang Zhu","doi":"10.1080/17686733.2020.1771528","DOIUrl":"https://doi.org/10.1080/17686733.2020.1771528","url":null,"abstract":"ABSTRACT Ultrasound excited vibro-thermography is based on the local heat generation due to the friction between the opposite surfaces of the defect, the plastic deformation around the defect, and/or the viscoelastic loss. This paper presents vibro-thermography applied to hybrid plates containing viscoelastic material when the viscoelastic heat generation mechanism alone is considered. The debonding-like calibrated defects without friction surfaces in the hybrid plate are detected. The dynamic temperature field is obtained by both experiment and numerical simulation. The influence of excitation frequency on the temperature increase over the defects is analysed by modelling the thermo-mechanical coupled field. The results show that the viscoelastic loss of the non-metal material is the leading factor of the local temperature increase over defects; an excitation frequency has its selective heating character to defects; a defect has a so-called defect characteristic frequency which can act as the optimal excitation frequency for this defect to be detected; the defect characteristic frequency is between the two local defect resonance frequencies corresponding to the simply supported boundary and the clamped boundary, respectively.","PeriodicalId":54525,"journal":{"name":"Quantitative Infrared Thermography Journal","volume":"18 1","pages":"314 - 331"},"PeriodicalIF":2.5,"publicationDate":"2020-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17686733.2020.1771528","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47643363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：