{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/132785"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/132785","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Deep learning applications in hyperspectral imaging for agriculture: image reconstruction and model design for quality prediction","abstract":"Non-invasive techniques, such as hyperspectral imaging (HSI), are crucial for analyzing the detailed chemical and structural composition of agricultural products. By capturing both spectral and spatial information simultaneously, HSI enables advanced analysis of key quality attributes in agricultural products. Despite the benefits, the adoption of HSI remains limited due to the high cost and complexity associated with collecting and processing hyperspectral data. To address these challenges, this thesis presents two complementary contributions. The first is Agro-HSR, a large-scale RGB-to-Hyperspectral image reconstruction dataset of sweet potatoes, comprising 1322 RGB-HSI pairs. For a subset of 141 samples, agro-product quality attributes, including Brix, dry matter content, and firmness, are also provided. The goal of this dataset is to promote the use of deep learning models in converting standard RGB images into HSI, thereby reducing the overall cost of data acquisition for HSI. The reconstructed spectra from the best performing reconstruction model had R^2 scores of 0.52, 0.88, and 0.85 in Brix, dry matter content, and firmness, respectively, all of which closely follow the original spectra results. The second contribution is Agro-Net, a Convolution-Attention Fusion model designed to extract complementary features from hyperspectral images for accurate agro-attribute prediction. Agro-Net outperforms traditional approaches in predicting the firmness of potatoes and the fertility of eggs, highlighting the benefits of leveraging both spectral and special features from HSI to improve agro-attribute prediction. Combined, these contributions advance the application of deep learning in agricultural hyperspectral imaging, enabling both practical data accessibility and effective predictive modeling.","abstract_html":"Non-invasive techniques, such as hyperspectral imaging (HSI), are crucial for analyzing the detailed chemical and structural composition of agricultural products. By capturing both spectral and spatial information simultaneously, HSI enables advanced analysis of key quality attributes in agricultural products. Despite the benefits, the adoption of HSI remains limited due to the high cost and complexity associated with collecting and processing hyperspectral data. To address these challenges, this thesis presents two complementary contributions. The first is Agro-HSR, a large-scale RGB-to-Hyperspectral image reconstruction dataset of sweet potatoes, comprising 1322 RGB-HSI pairs. For a subset of 141 samples, agro-product quality attributes, including Brix, dry matter content, and firmness, are also provided. The goal of this dataset is to promote the use of deep learning models in converting standard RGB images into HSI, thereby reducing the overall cost of data acquisition for HSI. The reconstructed spectra from the best performing reconstruction model had R^2 scores of 0.52, 0.88, and 0.85 in Brix, dry matter content, and firmness, respectively, all of which closely follow the original spectra results. The second contribution is Agro-Net, a Convolution-Attention Fusion model designed to extract complementary features from hyperspectral images for accurate agro-attribute prediction. Agro-Net outperforms traditional approaches in predicting the firmness of potatoes and the fertility of eggs, highlighting the benefits of leveraging both spectral and special features from HSI to improve agro-attribute prediction. Combined, these contributions advance the application of deep learning in agricultural hyperspectral imaging, enabling both practical data accessibility and effective predictive modeling.","abstract_has_math":false,"creators":["Monjur, Ocean"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Agricultural & Biological Engr","degree_department":null,"school":null,"contributors":["Kamruzzaman, Mohammed","Rausch, Kent D.","Malvandi, Amir"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12","date_published":"2025-12","updated_at":"2026-07-22T22:25:07Z","subjects":["Hyperspectral imaging reconstruction","Agricultural applications","Computer vision","Hyperspectral dataset"],"languages":["en"],"rights":["Copyright 2025 Ocean Monjur"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/132785","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Kamruzzaman, Mohammed","Rausch, Kent D.","Malvandi, Amir"]},{"key":"dc:creator","label":"Author","values":["Monjur, Ocean"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-12","2025-12-03"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Agricultural & Biological Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Hyperspectral imaging reconstruction","Agricultural applications","Computer vision","Hyperspectral dataset"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Ocean Monjur"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/132785"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Non-invasive techniques, such as hyperspectral imaging (HSI), are crucial for analyzing the detailed chemical and structural composition of agricultural products. By capturing both spectral and spatial information simultaneously, HSI enables advanced analysis of key quality attributes in agricultural products. Despite the benefits, the adoption of HSI remains limited due to the high cost and complexity associated with collecting and processing hyperspectral data. To address these challenges, this thesis presents two complementary contributions. The first is Agro-HSR, a large-scale RGB-to-Hyperspectral image reconstruction dataset of sweet potatoes, comprising 1322 RGB-HSI pairs. For a subset of 141 samples, agro-product quality attributes, including Brix, dry matter content, and firmness, are also provided. The goal of this dataset is to promote the use of deep learning models in converting standard RGB images into HSI, thereby reducing the overall cost of data acquisition for HSI. The reconstructed spectra from the best performing reconstruction model had R^2 scores of 0.52, 0.88, and 0.85 in Brix, dry matter content, and firmness, respectively, all of which closely follow the original spectra results. The second contribution is Agro-Net, a Convolution-Attention Fusion model designed to extract complementary features from hyperspectral images for accurate agro-attribute prediction. Agro-Net outperforms traditional approaches in predicting the firmness of potatoes and the fertility of eggs, highlighting the benefits of leveraging both spectral and special features from HSI to improve agro-attribute prediction. Combined, these contributions advance the application of deep learning in agricultural hyperspectral imaging, enabling both practical data accessibility and effective predictive modeling.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-12-01","The student, Ocean Monjur, accepted the attached license on 2025-12-01 at 10:27.","The student, Ocean Monjur, submitted this Thesis for approval on 2025-12-01 at 10:42.","This Thesis was approved for publication on 2025-12-03 at 20:37.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22986 on 2026-02-19 at 20:09:47"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Deep learning applications in hyperspectral imaging for agriculture: image reconstruction and model design for quality prediction"]}]}],"canonical_facts":{"dc:contributor":["Kamruzzaman, Mohammed","Rausch, Kent D.","Malvandi, Amir"],"dc:creator":["Monjur, Ocean"],"dc:date":["2025-12","2025-12-03"],"dc:description":["Non-invasive techniques, such as hyperspectral imaging (HSI), are crucial for analyzing the detailed chemical and structural composition of agricultural products. By capturing both spectral and spatial information simultaneously, HSI enables advanced analysis of key quality attributes in agricultural products. Despite the benefits, the adoption of HSI remains limited due to the high cost and complexity associated with collecting and processing hyperspectral data. To address these challenges, this thesis presents two complementary contributions. The first is Agro-HSR, a large-scale RGB-to-Hyperspectral image reconstruction dataset of sweet potatoes, comprising 1322 RGB-HSI pairs. For a subset of 141 samples, agro-product quality attributes, including Brix, dry matter content, and firmness, are also provided. The goal of this dataset is to promote the use of deep learning models in converting standard RGB images into HSI, thereby reducing the overall cost of data acquisition for HSI. The reconstructed spectra from the best performing reconstruction model had R^2 scores of 0.52, 0.88, and 0.85 in Brix, dry matter content, and firmness, respectively, all of which closely follow the original spectra results. The second contribution is Agro-Net, a Convolution-Attention Fusion model designed to extract complementary features from hyperspectral images for accurate agro-attribute prediction. Agro-Net outperforms traditional approaches in predicting the firmness of potatoes and the fertility of eggs, highlighting the benefits of leveraging both spectral and special features from HSI to improve agro-attribute prediction. Combined, these contributions advance the application of deep learning in agricultural hyperspectral imaging, enabling both practical data accessibility and effective predictive modeling.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-12-01","The student, Ocean Monjur, accepted the attached license on 2025-12-01 at 10:27.","The student, Ocean Monjur, submitted this Thesis for approval on 2025-12-01 at 10:42.","This Thesis was approved for publication on 2025-12-03 at 20:37.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22986 on 2026-02-19 at 20:09:47"],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/132785"],"dc:language":["en"],"dc:rights":["Copyright 2025 Ocean Monjur"],"dc:subject":["Hyperspectral imaging reconstruction","Agricultural applications","Computer vision","Hyperspectral dataset"],"dc:title":["Deep learning applications in hyperspectral imaging for agriculture: image reconstruction and model design for quality prediction"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Agricultural & Biological Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:07Z"}