G. Amariei, Anne Schaarup-Kjær, Pernille Klarskov, M. Henriksen, Mogens Hinge
Due to the increasing amount of plastic waste and high-quality demands on recycled plastic interest for in-line composition estimation in plastics has grown the last few years. This study investigates pigment blue 15 : 3 with varying concentrations in LDPE. Samples are investigated with two industrial hyperspectral imaging systems where one has the hyperspectral range from 450 nm to 1050 nm and the other from 950 nm to 1750 nm. A model based on peak ratios of selected bands and model based on a principal component analysis have been tested. The models only predict pigment concentrations between 40.0 wt% and 1.7 × 10–3 wt% if both spectral ranges are combined. Unknown samples containing pigment concentration ranging from 20 wt% to 0.31 wt% were predicted and correlated to the actual pigment concentrations (R2 = :0.977) and the PC-based model outperforms the peak ratio model. The studied approach can be a part of the solution to the plastic challenge and can be transferred to other applications where concentration determination is key.
{"title":"Estimation of pigment concentration in LDPE via in-line hyperspectral imaging and machine learning","authors":"G. Amariei, Anne Schaarup-Kjær, Pernille Klarskov, M. Henriksen, Mogens Hinge","doi":"10.1255/jsi.2023.a2","DOIUrl":"https://doi.org/10.1255/jsi.2023.a2","url":null,"abstract":"Due to the increasing amount of plastic waste and high-quality demands on recycled plastic interest for in-line composition estimation in plastics has grown the last few years. This study investigates pigment blue 15 : 3 with varying concentrations in LDPE. Samples are investigated with two industrial hyperspectral imaging systems where one has the hyperspectral range from 450 nm to 1050 nm and the other from 950 nm to 1750 nm. A model based on peak ratios of selected bands and model based on a principal component analysis have been tested. The models only predict pigment concentrations between 40.0 wt% and 1.7 × 10–3 wt% if both spectral ranges are combined. Unknown samples containing pigment concentration ranging from 20 wt% to 0.31 wt% were predicted and correlated to the actual pigment concentrations (R2 = :0.977) and the PC-based model outperforms the peak ratio model. The studied approach can be a part of the solution to the plastic challenge and can be transferred to other applications where concentration determination is key.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46748662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present a simple, but novel, hybrid approach to hyperspectral data cube reconstruction from computed tomography imaging spectrometry (CTIS) images that sequentially combines neural networks and the iterative expectation maximisation (EM) algorithm. We train and test the ability of the method to reconstruct data cubes of 100 × 100 × 25 and 100 × 100 × 100 voxels, corresponding to 25 and 100 spectral channels, from simulated CTIS images generated by our CTIS simulator. The hybrid approach utilises the inherent strength of the Convolutional Neural Network (CNN) with regards to noise and its ability to yield consistent reconstructions and make use of the EM algorithm’s ability to generalise to spectral images of any object without training. The hybrid approach achieves better performance than both the CNNs and EM alone for seen (included in CNN training) and unseen (excluded from CNN training) cubes for both the 25- and 100-channel cases. For the 25 spectral channels, the improvements from CNN to the hybrid model (CNN + EM) in terms of the mean-squared errors are between 14 % and 26 %. For 100 spectral channels, the improvements between 19 % and 40 % are attained with the largest improvement of 40 % for the unseen data, to which the CNNs are not exposed during the training.
{"title":"The hybrid approach—convolutional neural networks and expectation maximisation algorithm—for tomographic reconstruction of hyperspectral images","authors":"Mads Ahlebæk, Mads Peters, Wei-Chih Huang, Mads Frandsen, René Eriksen, Bjarke Jørgensen","doi":"10.1255/jsi.2023.a1","DOIUrl":"https://doi.org/10.1255/jsi.2023.a1","url":null,"abstract":"We present a simple, but novel, hybrid approach to hyperspectral data cube reconstruction from computed tomography imaging spectrometry (CTIS) images that sequentially combines neural networks and the iterative expectation maximisation (EM) algorithm. We train and test the ability of the method to reconstruct data cubes of 100 × 100 × 25 and 100 × 100 × 100 voxels, corresponding to 25 and 100 spectral channels, from simulated CTIS images generated by our CTIS simulator. The hybrid approach utilises the inherent strength of the Convolutional Neural Network (CNN) with regards to noise and its ability to yield consistent reconstructions and make use of the EM algorithm’s ability to generalise to spectral images of any object without training. The hybrid approach achieves better performance than both the CNNs and EM alone for seen (included in CNN training) and unseen (excluded from CNN training) cubes for both the 25- and 100-channel cases. For the 25 spectral channels, the improvements from CNN to the hybrid model (CNN + EM) in terms of the mean-squared errors are between 14 % and 26 %. For 100 spectral channels, the improvements between 19 % and 40 % are attained with the largest improvement of 40 % for the unseen data, to which the CNNs are not exposed during the training.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135201907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multisensor data fusion has become a hot topic in the remote sensing research community. This is thanks to significant technological advances and the ability to extract information that would have been challenging with a single sensor. However, sensory enhancement requires advanced analysis that enables deep learning. A framework is designed to effectively fuse hyperspectral and lidar data for semantic segmentation in the urban environment. Our work proposes a method of reducing dimensions by exploring the most representative features from hyperspectral and lidar data and using them for supervised semantic segmentation. In addition, we chose to compare segmentation models based on 2D and 3D convolutional operations with two different model architectures, such as U-Net and ResU-Net. All algorithms have been tested with three loss functions: standard Categorical Cross-Entropy, Focal Loss and a combination of Focal Loss and Jaccard Distance—Focal–Jaccard Loss. Experimental results demonstrated that the 3D segmentation of U-Net and ResU-Net with Focal and Focal–Jaccard Loss functions had significantly improved performance compared to the standard Categorical Cross-Entropy models. The results show a high accuracy score and reflect reality by preserving the complex geometry of the objects.
{"title":"Comparison of 2D and 3D semantic segmentation in urban areas using fused hyperspectral and lidar data","authors":"A. Kuras, Anna Jenul, Maximilian Brell, I. Burud","doi":"10.1255/jsi.2022.a11","DOIUrl":"https://doi.org/10.1255/jsi.2022.a11","url":null,"abstract":"Multisensor data fusion has become a hot topic in the remote sensing research community. This is thanks to significant technological advances and the ability to extract information that would have been challenging with a single sensor. However, sensory enhancement requires advanced analysis that enables deep learning. A framework is designed to effectively fuse hyperspectral and lidar data for semantic segmentation in the urban environment. Our work proposes a method of reducing dimensions by exploring the most representative features from hyperspectral and lidar data and using them for supervised semantic segmentation. In addition, we chose to compare segmentation models based on 2D and 3D convolutional operations with two different model architectures, such as U-Net and ResU-Net. All algorithms have been tested with three loss functions: standard Categorical Cross-Entropy, Focal Loss and a combination of Focal Loss and Jaccard Distance—Focal–Jaccard Loss. Experimental results demonstrated that the 3D segmentation of U-Net and ResU-Net with Focal and Focal–Jaccard Loss functions had significantly improved performance compared to the standard Categorical Cross-Entropy models. The results show a high accuracy score and reflect reality by preserving the complex geometry of the objects.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42845522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jaione Echávarri-Dublhán, Miriam Alonso-Santamaría, P. Luri-Esplandiu, María-José Sháiz-Abajo
Moisture content and its distribution is a critical parameter in the production of cereal bars. Inappropriate control of this quality parameter can lead to non-conforming products and excess waste on production lines. In the field of hyperspectral imaging, the search for alternative light sources to stabilised-halogen (cheaper and emitting less heat) is a growing need for the application of this technology in industry. This study compares three different illumination systems for moisture prediction in the visible-near infrared (vis-NIR) range (from 400 nm to 1000 nm). The hyperspectral images were acquired using three illumination systems including two halogen-based systems (stabilised-halogen and conventional-halogen) and an LED-based illumination system. The results showed that halogen-based illumination systems combined with a partial least squares model better predicted moisture in bars. Lower accuracies were obtained when the experiment was performed with an LED-based illumination system, which showed double the error of the halogen-based systems. It was concluded that this is a consequence of the information lost in bands appearing above 850 nm that may be revealing information about the moisture in bars since the second overtone of the water O–H is found at 970 nm. The results demonstrate that conventional halogen-based light systems in the vis-NIR range are a promising method for moisture prediction in cereal bars.
{"title":"Comparison of different illumination systems for moisture prediction in cereal bars using hyperspectral imaging technology","authors":"Jaione Echávarri-Dublhán, Miriam Alonso-Santamaría, P. Luri-Esplandiu, María-José Sháiz-Abajo","doi":"10.1255/jsi.2022.a10","DOIUrl":"https://doi.org/10.1255/jsi.2022.a10","url":null,"abstract":"Moisture content and its distribution is a critical parameter in the production of cereal bars. Inappropriate control of this quality parameter can lead to non-conforming products and excess waste on production lines. In the field of hyperspectral imaging, the search for alternative light sources to stabilised-halogen (cheaper and emitting less heat) is a growing need for the application of this technology in industry. This study compares three different illumination systems for moisture prediction in the visible-near infrared (vis-NIR) range (from 400 nm to 1000 nm). The hyperspectral images were acquired using three illumination systems including two halogen-based systems (stabilised-halogen and conventional-halogen) and an LED-based illumination system. The results showed that halogen-based illumination systems combined with a partial least squares model better predicted moisture in bars. Lower accuracies were obtained when the experiment was performed with an LED-based illumination system, which showed double the error of the halogen-based systems. It was concluded that this is a consequence of the information lost in bands appearing above 850 nm that may be revealing information about the moisture in bars since the second overtone of the water O–H is found at 970 nm. The results demonstrate that conventional halogen-based light systems in the vis-NIR range are a promising method for moisture prediction in cereal bars.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45048641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
K. Tamilarasan, S. Anbazhagan, S. Maheswaran, S. Ranjithkumar, K. Kusuma, V. Rajesh
The layered Sittampundi Anorthosite Complex is covered by mafic and ultramafic rocks including anorthosite, gabbro, pyroxenite and other igneous rocks. The ultramafic terrain has frequently undergone metamorphism. In the present study, laboratory spectral measurements were carried out from mafic, ultramafic and felsic rocks in the 350–2500 nm spectral range to characterise their diagnostic spectral features and for further utilisation for rock-type mapping. In 2016, the Sittampundi complex was covered by an AVIRIS-NG airborne survey jointly conducted by the Space Application Centre (SAC-ISRO) and Jet Propulsion Laboratory (NASA). The level-2 AVIRIS-NG data was obtained from SAC and used to interpret various rock types. ENVI 5.3 software was used for digital image processing of the AVIRIS-NG airborne hyperspectral data. The continuum-removed spectra of major rock types including anorthosite, meta-anorthosite, gabbro, meta-gabbro, pyroxenite, pegmatite, granite, gneiss and migmatite were critically analysed and their diagnostic absorption features correlated with chemistry and mineralogy. The AVIRIS-NG data analyses include bad band removal, minimum noise fraction transformation (MNF) and band combination. Out of various band combinations, the MNF composite images B456, B546 and B561 provided an enhanced output for the delineation of various rock types in the ultramafic terrain.
{"title":"Reflectance spectra and AVIRIS-NG airborne hyperspectral data analysis for mapping ultramafic rocks in igneous terrain","authors":"K. Tamilarasan, S. Anbazhagan, S. Maheswaran, S. Ranjithkumar, K. Kusuma, V. Rajesh","doi":"10.1255/jsi.2022.a9","DOIUrl":"https://doi.org/10.1255/jsi.2022.a9","url":null,"abstract":"The layered Sittampundi Anorthosite Complex is covered by mafic and ultramafic rocks including anorthosite, gabbro, pyroxenite and other igneous rocks. The ultramafic terrain has frequently undergone metamorphism. In the present study, laboratory spectral measurements were carried out from mafic, ultramafic and felsic rocks in the 350–2500 nm spectral range to characterise their diagnostic spectral features and for further utilisation for rock-type mapping. In 2016, the Sittampundi complex was covered by an AVIRIS-NG airborne survey jointly conducted by the Space Application Centre (SAC-ISRO) and Jet Propulsion Laboratory (NASA). The level-2 AVIRIS-NG data was obtained from SAC and used to interpret various rock types. ENVI 5.3 software was used for digital image processing of the AVIRIS-NG airborne hyperspectral data. The continuum-removed spectra of major rock types including anorthosite, meta-anorthosite, gabbro, meta-gabbro, pyroxenite, pegmatite, granite, gneiss and migmatite were critically analysed and their diagnostic absorption features correlated with chemistry and mineralogy. The AVIRIS-NG data analyses include bad band removal, minimum noise fraction transformation (MNF) and band combination. Out of various band combinations, the MNF composite images B456, B546 and B561 provided an enhanced output for the delineation of various rock types in the ultramafic terrain.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42187293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Advancements in optics and miniaturisation have resulted in multi- and hyperspectral imaging systems becoming more approachable in terms of cost, practicality and useability. Globally, the majority of farms are considered to be small farms (<2 hectares). Many spectral imaging applications have been associated with agricultural commodities over the years. However, due to the cost, technology hurdles and complex statistical modelling methods, these applications have mainly been implemented in larger monoculture settings where the method development time required can be met with and substantiated through higher profits gained and reduced labour in the long term. Recent years have seen advancements in spectral imaging technologies as well as open-source systems that have the potential for application on smaller, more diversified farms. There are many hurdles to face before spectral imaging technologies see widespread application on smaller farms, but technologies are advancing rapidly. Here, the current state of spectral imaging in small farm applications is evaluated, along with the potential for low-cost and open-source spectral imaging systems. Emphasis is placed on challenges which require addressing prior to approachable spectral imaging for the small farm.
{"title":"Potential for spectral imaging applications on the small farm: a review","authors":"M. Eady","doi":"10.1255/jsi.2022.a8","DOIUrl":"https://doi.org/10.1255/jsi.2022.a8","url":null,"abstract":"Advancements in optics and miniaturisation have resulted in multi- and hyperspectral imaging systems becoming more approachable in terms of cost, practicality and useability. Globally, the majority of farms are considered to be small farms (<2 hectares). Many spectral imaging applications have been associated with agricultural commodities over the years. However, due to the cost, technology hurdles and complex statistical modelling methods, these applications have mainly been implemented in larger monoculture settings where the method development time required can be met with and substantiated through higher profits gained and reduced labour in the long term. Recent years have seen advancements in spectral imaging technologies as well as open-source systems that have the potential for application on smaller, more diversified farms. There are many hurdles to face before spectral imaging technologies see widespread application on smaller farms, but technologies are advancing rapidly. Here, the current state of spectral imaging in small farm applications is evaluated, along with the potential for low-cost and open-source spectral imaging systems. Emphasis is placed on challenges which require addressing prior to approachable spectral imaging for the small farm.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44218481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Principal components analysis (PCA), maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) models are common factor-based models used for analysis of hyperspectral images. The models can be posed as maximisation problems that result in a symmetric eigenvalue problem (SEP) for each model. The SEPs allow a simple theoretical comparison of the models using a PCA metaphor with MAF, MNF and MDF describable as weighted PCA models. The examples show that the different methods captured different signals in the images that can be examined individually or combined synergistically allowing for additional modelling and extended visualisation. MDF is a factor-based edge detection model that not only allows for additional visualisation but the opportunity to identify and exclude (or highlight) edge signal in the images. An example shows that models can also be used synergistically for finding and elucidating anomalies. In the example, MDF showed the highest sensitivity of the models studied for anomaly detection.
{"title":"A comparison of common factor-based methods for hyperspectral image exploration: principal components analysis, maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors","authors":"Neal Gallagher","doi":"10.1255/jsi.2022.a6","DOIUrl":"https://doi.org/10.1255/jsi.2022.a6","url":null,"abstract":"Principal components analysis (PCA), maximum autocorrelation factors (MAF), minimum noise factors (MNF) and maximum difference factors (MDF) models are common factor-based models used for analysis of hyperspectral images. The models can be posed as maximisation problems that result in a symmetric eigenvalue problem (SEP) for each model. The SEPs allow a simple theoretical comparison of the models using a PCA metaphor with MAF, MNF and MDF describable as weighted PCA models. The examples show that the different methods captured different signals in the images that can be examined individually or combined synergistically allowing for additional modelling and extended visualisation. MDF is a factor-based edge detection model that not only allows for additional visualisation but the opportunity to identify and exclude (or highlight) edge signal in the images. An example shows that models can also be used synergistically for finding and elucidating anomalies. In the example, MDF showed the highest sensitivity of the models studied for anomaly detection.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44159350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hyperspectral remote sensing is known to suffer from wavelength bands blocked by atmospheric gases. Short-wave infrared hyperspectral imaging at in situ installations is shown to be affected by water vapour even if the pathlength of light through air is only hundreds of centimetres. This impact is especially noticeable with large variations of relative humidity, the coefficient of variation reaching 5 % in our test case. Using repeated calibrations of imaging system at the same relative humidity as in the measurement, we were able to reduce the coefficient of variation to 1 %. The measurement variations are also shown to induce significant error in material classification. Polymer type identification was selected as the test case for material classification. The measurement variations due to the change in relative humidity are shown to result in 20 % classification error at its minimum. With repeated calibrations or by eliminating the most affected wavelength bands from measurements, we were able to reduce the classification error to less than 1 %. Such improvement of measurement and classification precision may be important for industrial applications such as waste sorting, polymer classification etc.
{"title":"Impact of water vapour on polymer classification using in situ short-wave infrared hyperspectral imaging","authors":"Muhammad Shaikh, Benny Thörnberg","doi":"10.1255/jsi.2022.a5","DOIUrl":"https://doi.org/10.1255/jsi.2022.a5","url":null,"abstract":"Hyperspectral remote sensing is known to suffer from wavelength bands blocked by atmospheric gases. Short-wave infrared hyperspectral imaging at in situ installations is shown to be affected by water vapour even if the pathlength of light through air is only hundreds of centimetres. This impact is especially noticeable with large variations of relative humidity, the coefficient of variation reaching 5 % in our test case. Using repeated calibrations of imaging system at the same relative humidity as in the measurement, we were able to reduce the coefficient of variation to 1 %. The measurement variations are also shown to induce significant error in material classification. Polymer type identification was selected as the test case for material classification. The measurement variations due to the change in relative humidity are shown to result in 20 % classification error at its minimum. With repeated calibrations or by eliminating the\u0000most affected wavelength bands from measurements, we were able to reduce the classification error to less than 1 %.\u0000Such improvement of measurement and classification precision may be important for industrial applications such as waste\u0000sorting, polymer classification etc.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46301702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hyperspectral unmixing (HU) is one of the most active emerging areas in image processing that estimates the hyperspectral image’s endmember and abundance. HU enhances the quality of both spectral and spatial dimensions of the image by modifying the endmember and abundance parameters of the hyperspectral images. There are several HU algorithms available in the literature based on the linear mixing model (LMM) that deals with the microscopic contents of the pixels in the images. Non-negative matrix factorisation (NMF) is the prominent method widely used in LMMs that simultaneously estimates both the endmembers and abundances parameters along with some residual factors of the image to improve the quality of unmixing. In addition to this, the quality of the image is enhanced by incorporating some constraints to both endmember and abundance matrices with the NMF method. However, all the existing methods apply any of these constraints to the endmember and abundance matrices by considering the linearity features of the images. In this paper, we propose an unmixing model called joint extrinsic and intrinsic priors with L1/2 norms to non-negative matrix factorisation (JEIp L1/2-NMF) that applies multiple constraints simultaneously to both endmember and abundance matrices of the hyperspectral image to enhance its quality. Three main external and internal constraints such as minimum volume, sparsity and total variation are applied to both the endmembers and abundance parameters of the image. In addition, a L1/2-norms is imposed to extract good quality spectral data. Therefore, the proposed method enhances spatial as well as spectral data and considers the non-linearity of the pixels in the image by adding a residual term to the model. Performance of our proposed model is measured by using different quality measuring indexes on four benchmark public datasets and found that the proposed method shows outstanding performance compared to all the conventional baseline methods. Further, we also evaluated the performance of our method by varying the number of endmembers empirically and concluded that less than five endmembers provides high-quality spectral and spatial data during the unmixing process.
{"title":"Hyperspectral image non-linear unmixing using joint extrinsic and intrinsic priors with L1/2-norms to non-negative matrix factorisation","authors":"K. Priya, K. Rajkumar","doi":"10.1255/jsi.2022.a4","DOIUrl":"https://doi.org/10.1255/jsi.2022.a4","url":null,"abstract":"Hyperspectral unmixing (HU) is one of the most active emerging areas in image processing that estimates the hyperspectral image’s endmember and abundance. HU enhances the quality of both spectral and spatial dimensions of the image by modifying the endmember and abundance parameters of the hyperspectral images. There are several HU algorithms available in the literature based on the linear mixing model (LMM) that deals with the microscopic contents of the pixels in the images. Non-negative matrix factorisation (NMF) is the prominent method widely used in LMMs that simultaneously estimates both the endmembers and abundances parameters along with some residual factors of the image to improve the quality of unmixing. In addition to this, the quality of the image is enhanced by incorporating some constraints to both endmember and abundance matrices with the NMF method. However, all the existing methods apply any of these constraints to the endmember and abundance matrices by considering the linearity features of the images. In this paper, we propose an unmixing model called joint extrinsic and intrinsic priors with L1/2 norms to non-negative matrix factorisation (JEIp L1/2-NMF) that applies multiple constraints simultaneously to both endmember and abundance matrices of the hyperspectral image to enhance its quality. Three main external and internal constraints such as minimum volume, sparsity and total variation are applied to both the endmembers and abundance parameters of the image. In addition, a L1/2-norms is imposed to extract good quality spectral data. Therefore, the proposed method enhances spatial as well as spectral data and considers the non-linearity of the pixels in the image by adding a residual term to the model. Performance of our proposed model is measured by using different quality measuring indexes on four benchmark public datasets and found that the proposed method shows outstanding performance compared to all the conventional baseline methods. Further, we also evaluated the performance of our method by varying the number of endmembers empirically and concluded that less than five endmembers provides high-quality spectral and spatial data during the unmixing process.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44731046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hannah Carruthers, D. Clark, F. Clarke, K. Faulds, D. Graham
Vibrational spectroscopic chemical imaging is a powerful tool in the pharmaceutical industry to assess the spatial distribution of components within pharmaceutical samples. Recently, the combination of vibrational spectroscopic chemical mapping with serial sectioning has provided a means to visualise the three-dimensional (3D) structure of a tablet matrix. There are recognised knowledge gaps in current tablet manufacturing processes, particularly regarding the size, shape and distribution of components within the final drug product. The performance of pharmaceutical tablets is known to be primarily influenced by the physical and chemical properties of the formulation. Here, we describe the data processing methods required to extract quantitative domain size and spatial distribution statistics from 3D vibrational spectroscopic chemical images. This provides a means to quantitatively describe the microstructure of a tablet matrix and is a powerful tool to overcome knowledge gaps in current tablet manufacturing processes, optimising formulation development.
{"title":"Data processing of three-dimensional vibrational spectroscopic chemical images for pharmaceutical applications","authors":"Hannah Carruthers, D. Clark, F. Clarke, K. Faulds, D. Graham","doi":"10.1255/jsi.2022.a3","DOIUrl":"https://doi.org/10.1255/jsi.2022.a3","url":null,"abstract":"Vibrational spectroscopic chemical imaging is a powerful tool in the pharmaceutical industry to assess the spatial distribution of components within pharmaceutical samples. Recently, the combination of vibrational spectroscopic chemical mapping with serial sectioning has provided a means to visualise the three-dimensional (3D) structure of a tablet matrix. There are recognised knowledge gaps in current tablet manufacturing processes, particularly regarding the size, shape and distribution of components within the final drug product. The performance of pharmaceutical tablets is known to be primarily influenced by the physical and chemical properties of the formulation. Here, we describe the data processing methods required to extract quantitative domain size and spatial distribution statistics from 3D vibrational spectroscopic chemical images. This provides a means to quantitatively describe the microstructure of a tablet matrix and is a powerful tool to overcome knowledge gaps in current tablet manufacturing processes, optimising formulation development.","PeriodicalId":37385,"journal":{"name":"Journal of Spectral Imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44814317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：