Ramazan Ozgur Dogan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ramazan Ozgur Dogan has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Hulya Dogan
Karadeniz Teknik Üniversitesi
12 shared publications - Feride Sena Sezen
Karadeniz Technical University
3 shared publications - Fatma Tuana Doğu
KARADENİZ TEKNİK ÜNİVERSİTESİ, FEN BİLİMLERİ ENSTİTÜSÜ, ELEKTRONİK MÜHENDİSLİĞİ (YL) (TEZLİ)
2 shared publications - Sibel Danişmaz
Karadeniz Teknik Üniversitesi
2 shared publications - Sümeyye Nur Emi̇r
Karadeniz Teknik Üniversitesi
2 shared publications Alper Yilmaz
Photogrammetric Computer Vision Laboratory, The Ohio State University, Columbus, USA
1 shared publication
Latest Publications
- 13 August 2026
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 82 (12) , 634
An effective pyramid vision transformer-based extended depth of focus technique for optimally focused microscopic imaging
- 13 August 2026
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 82 (12) , 634
An effective pyramid vision transformer-based extended depth of focus technique for optimally focused microscopic imaging
- Open Access
- 11 June 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (12) , 5934
A Dual-Stage Multimodal Alignment Approach for Robust Breast Cancer Diagnosis via Visual–Textual Computing
Manual classification of breast cancer is resource-intensive, slow, and subject to inter-observer variability, motivating automated deep learning solutions. Most current methods rely on unimodal imaging data and struggle with domain generalization (DG) across varied clinical environments. We propose a Dual-Stage Multimodal Alignment approach that integrates breast ultrasound (US) imagery with clinical text reports to improve diagnostic stability. The method proceeds in two stages: (1) Local Correlation Alignment (LCA), which aligns fine-grained visual features with textual embeddings to capture localized lesion attributes, and (2) Global Attention Alignment (GAA), which applies multi-head self-attention to the joint visual–textual sequence to encourage domain-invariant representations. We evaluate the approach on a harmonized, leakage-free repository of 6880 images aggregated from six public US datasets (BUS-CoT, BrEaST, BUS-BRA, BUS-UCLM, BLUI, BUSI) under three protocols: independent benchmarking on BUS-CoT, pooled cross-dataset evaluation, and zero-shot domain generalization on unseen unimodal target domains. On the BUS-CoT benchmark, the 198M-parameter model reaches 0.8177 accuracy and 0.8852 AUC, on par with the 7-billion-parameter Qwen2.5-VL-7B with chain-of-thought reasoning (0.8064 accuracy, 0.8354 AUC) while using roughly 1/35 the parameter count. In the pooled setting, it is competitive with single-domain state-of-the-art methods on individual subsets (e.g., 0.9576 AUC on BUSI, 0.8741 accuracy on BUS-BRA). Under zero-shot transfer without clinical text, per-domain AUC ranges from 0.7360 to 0.8060 across four unseen targets, providing a lower bound under cross-scanner shift. These results indicate that task-specific multimodal alignment can rival large vision-language models in breast US diagnosis at a fraction of the parameter count.
- 11 June 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (12) , 5934
Open AccessA Dual-Stage Multimodal Alignment Approach for Robust Breast Cancer Diagnosis via Visual–Textual Computing
Manual classification of breast cancer is resource-intensive, slow, and subject to inter-observer variability, motivating automated deep learning solutions. Most current methods rely on unimodal imaging data and struggle with domain generalization (DG) across varied clinical environments. We propose a Dual-Stage Multimodal Alignment approach that integrates breast ultrasound (US) imagery with clinical text reports to improve diagnostic stability. The method proceeds in two stages: (1) Local Correlation Alignment (LCA), which aligns fine-grained visual features with textual embeddings to capture localized lesion attributes, and (2) Global Attention Alignment (GAA), which applies multi-head self-attention to the joint visual–textual sequence to encourage domain-invariant representations. We evaluate the approach on a harmonized, leakage-free repository of 6880 images aggregated from six public US datasets (BUS-CoT, BrEaST, BUS-BRA, BUS-UCLM, BLUI, BUSI) under three protocols: independent benchmarking on BUS-CoT, pooled cross-dataset evaluation, and zero-shot domain generalization on unseen unimodal target domains. On the BUS-CoT benchmark, the 198M-parameter model reaches 0.8177 accuracy and 0.8852 AUC, on par with the 7-billion-parameter Qwen2.5-VL-7B with chain-of-thought reasoning (0.8064 accuracy, 0.8354 AUC) while using roughly 1/35 the parameter count. In the pooled setting, it is competitive with single-domain state-of-the-art methods on individual subsets (e.g., 0.9576 AUC on BUSI, 0.8741 accuracy on BUS-BRA). Under zero-shot transfer without clinical text, per-domain AUC ranges from 0.7360 to 0.8060 across four unseen targets, providing a lower bound under cross-scanner shift. These results indicate that task-specific multimodal alignment can rival large vision-language models in breast US diagnosis at a fraction of the parameter count.
- Open Access
- 17 March 2026
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 33 (3) , 4609-4623
From Handcrafted Focus Measurement Operators to Deep Learning: A Comprehensive Review of Shape from Focus Strategies
Shape from Focus (SFF) is a critical passive optical measurement technique used to reconstruct the 3D shape of objects from a sequence of 2D images captured at varying focal planes. This review provides a comprehensive and systematic analysis of the evolution of SFF strategies, tracing the transition from classical handcrafted focus measurement operators to contemporary deep learning-based architectures. We categorize traditional methods into spatial and transform-domain operators, evaluating their performance in terms of sharpness extraction and noise resilience. The paper further investigates the impact of convolutional neural networks and transformer-based models, which have redefined state of the art performance by learning hierarchical feature representations. In addition to algorithmic advancements, we examine the role of pre-processing, post-processing, and approximation frameworks in enhancing 3D reconstruction accuracy. The practical utility of these strategies is demonstrated across diverse high precision fields, including semiconductor inspection, digital morphology in healthcare. Lastly, we outline future research potential in autonomous 3D vision systems by discussing the unresolved issues in this field, such as the scarcity of ground truth data and the computational needs of real time processing.
- 17 March 2026
- Published by Springer Nature in Archives of Computational Methods in Engineering
- Vol. 33 (3) , 4609-4623
Open AccessFrom Handcrafted Focus Measurement Operators to Deep Learning: A Comprehensive Review of Shape from Focus Strategies
Shape from Focus (SFF) is a critical passive optical measurement technique used to reconstruct the 3D shape of objects from a sequence of 2D images captured at varying focal planes. This review provides a comprehensive and systematic analysis of the evolution of SFF strategies, tracing the transition from classical handcrafted focus measurement operators to contemporary deep learning-based architectures. We categorize traditional methods into spatial and transform-domain operators, evaluating their performance in terms of sharpness extraction and noise resilience. The paper further investigates the impact of convolutional neural networks and transformer-based models, which have redefined state of the art performance by learning hierarchical feature representations. In addition to algorithmic advancements, we examine the role of pre-processing, post-processing, and approximation frameworks in enhancing 3D reconstruction accuracy. The practical utility of these strategies is demonstrated across diverse high precision fields, including semiconductor inspection, digital morphology in healthcare. Lastly, we outline future research potential in autonomous 3D vision systems by discussing the unresolved issues in this field, such as the scarcity of ground truth data and the computational needs of real time processing.
- Open Access
- 23 October 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (21) , 11368
A Video-Based Mobile Palmprint Dataset and an Illumination-Robust Deep Learning Architecture for Unconstrained Environments
The widespread adoption of mobile devices has made secure and user-friendly biometric authentication critical. However, widely used modalities such as fingerprint and facial recognition show limited robustness under uncontrolled illumination and on heterogeneous devices. In contrast, palmprint recognition offers strong potential because of its rich textural patterns and high discriminative power. This study addresses the limitations of laboratory-based datasets that fail to capture real-world challenges. We introduce MPW-180, a novel dataset comprising videos of 180 participants recorded on their own smartphones in everyday environments. By systematically incorporating diverse illumination conditions (with and without flash) and natural free-hand movements, MPW-180 is the first dataset to adopt a bring-your-own-device paradigm, providing a realistic benchmark for evaluating generalization in mobile biometric models. In addition, we propose PalmWildNet, an SE-block-enhanced deep learning architecture trained with Triplet Loss and a cross-illumination sampling strategy. The experimental results show that conventional methods suffer over 50% performance degradation under cross-illumination conditions. In contrast, our method reduces the Equal Error Rate to 1–2% while maintaining an accuracy above 97%. These findings demonstrate that the proposed framework not only tolerates illumination variability but also learns robust illumination-invariant representations, making it well-suited for mobile biometric authentication.
- 23 October 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (21) , 11368
Open AccessA Video-Based Mobile Palmprint Dataset and an Illumination-Robust Deep Learning Architecture for Unconstrained Environments
The widespread adoption of mobile devices has made secure and user-friendly biometric authentication critical. However, widely used modalities such as fingerprint and facial recognition show limited robustness under uncontrolled illumination and on heterogeneous devices. In contrast, palmprint recognition offers strong potential because of its rich textural patterns and high discriminative power. This study addresses the limitations of laboratory-based datasets that fail to capture real-world challenges. We introduce MPW-180, a novel dataset comprising videos of 180 participants recorded on their own smartphones in everyday environments. By systematically incorporating diverse illumination conditions (with and without flash) and natural free-hand movements, MPW-180 is the first dataset to adopt a bring-your-own-device paradigm, providing a realistic benchmark for evaluating generalization in mobile biometric models. In addition, we propose PalmWildNet, an SE-block-enhanced deep learning architecture trained with Triplet Loss and a cross-illumination sampling strategy. The experimental results show that conventional methods suffer over 50% performance degradation under cross-illumination conditions. In contrast, our method reduces the Equal Error Rate to 1–2% while maintaining an accuracy above 97%. These findings demonstrate that the proposed framework not only tolerates illumination variability but also learns robust illumination-invariant representations, making it well-suited for mobile biometric authentication.
- 2 September 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (14) , 1-27
Two-phase deep learning method for image fusion-based extended depth of focus
- 2 September 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (14) , 1-27
Two-phase deep learning method for image fusion-based extended depth of focus
- 30 May 2025
- Published by Elsevier in Optics and Lasers in Engineering
- Vol. 193
Swin transformer-based shape-from-focus technique for accurate 3D shape estimation
- 30 May 2025
- Published by Elsevier in Optics and Lasers in Engineering
- Vol. 193
Swin transformer-based shape-from-focus technique for accurate 3D shape estimation
- 3 December 2024
- Published by Kahramanmaras Sutcu Imam University Journal of Engineering Sciences in Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi
- Vol. 27 (4) , 1465-1476
KAN HÜCRELERİNİN OPTİMUM ODAKLI GÖRÜNTÜLENMESİ İÇİN DERİN ÖĞRENME TABANLI YAKLAŞIMIN GELİŞTİRİLMESİ
Mikroskobik sistemlerde var olan odaklama derinliği sebebiyle kan hücreleri bulunan numuneler tamamıyla odaklı görüntülenememektedir. Bu durum yapay zeka ve görüntü işleme algoritmalarının performans kaybına sebep olabilmektedir. Bunu çözmek için odaklama derinliğinin artırılması yaklaşımları kullanılmakta ve numunenin optimum odaklı görüntüsü elde edilmektedir. Literatürde birçok odaklama derinliğinin artırılması yaklaşımı bulunmasına rağmen bu alanda hala yüksek çalışma süresi, kullanılan numuneye ve mikroskop çeşidine göre farklı performans gösterme gibi çeşitli eksiklikler mevcuttur. Bu çalışmada, literatürdeki bu eksiklikleri gidermek amacıyla mikroskobik sistemlerde kan hücrelerinin optimum odaklı görüntülenmesi için hem yeni veri seti oluşturulmakta hem de derin öğrenme tabanlı yeni bir odaklama derinliği artırılması yaklaşımı önerilmektedir. Çalışmanın performansını değerlendirmek için Algı Tabanlı Görüntü Kalitesi, Referanssız Görüntü Uzamsal Kalite, Bulanıklık ve Doğallık Görüntü Kalitesi olmak üzere dört farklı kriter kullanılmaktadır. Geliştirilen çalışmada 13 farklı odaklama derinliğinin artırılması yaklaşımı test edilmektedir. Bu çalışmada performans değerlendirme kriterleri sonuçları ile kan hücrelerinin optimum odaklı görüntülenmesi için önerilen derin öğrenme tabanlı odaklama derinliğinin artırılması yaklaşımının diğer yaklaşımlara göre daha performanslı olduğu ispatlanmaktadır.
- 3 December 2024
- Published by Kahramanmaras Sutcu Imam University Journal of Engineering Sciences in Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi
- Vol. 27 (4) , 1465-1476
KAN HÜCRELERİNİN OPTİMUM ODAKLI GÖRÜNTÜLENMESİ İÇİN DERİN ÖĞRENME TABANLI YAKLAŞIMIN GELİŞTİRİLMESİ
Mikroskobik sistemlerde var olan odaklama derinliği sebebiyle kan hücreleri bulunan numuneler tamamıyla odaklı görüntülenememektedir. Bu durum yapay zeka ve görüntü işleme algoritmalarının performans kaybına sebep olabilmektedir. Bunu çözmek için odaklama derinliğinin artırılması yaklaşımları kullanılmakta ve numunenin optimum odaklı görüntüsü elde edilmektedir. Literatürde birçok odaklama derinliğinin artırılması yaklaşımı bulunmasına rağmen bu alanda hala yüksek çalışma süresi, kullanılan numuneye ve mikroskop çeşidine göre farklı performans gösterme gibi çeşitli eksiklikler mevcuttur. Bu çalışmada, literatürdeki bu eksiklikleri gidermek amacıyla mikroskobik sistemlerde kan hücrelerinin optimum odaklı görüntülenmesi için hem yeni veri seti oluşturulmakta hem de derin öğrenme tabanlı yeni bir odaklama derinliği artırılması yaklaşımı önerilmektedir. Çalışmanın performansını değerlendirmek için Algı Tabanlı Görüntü Kalitesi, Referanssız Görüntü Uzamsal Kalite, Bulanıklık ve Doğallık Görüntü Kalitesi olmak üzere dört farklı kriter kullanılmaktadır. Geliştirilen çalışmada 13 farklı odaklama derinliğinin artırılması yaklaşımı test edilmektedir. Bu çalışmada performans değerlendirme kriterleri sonuçları ile kan hücrelerinin optimum odaklı görüntülenmesi için önerilen derin öğrenme tabanlı odaklama derinliğinin artırılması yaklaşımının diğer yaklaşımlara göre daha performanslı olduğu ispatlanmaktadır.
- 25 March 2024
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 37 (4) , 1991-2013
DL-EDOF: Novel Multi-Focus Image Data Set and Deep Learning-Based Approach for More Accurate and Specimen-Free Extended Depth of Focus
Depth of focus (DOF) is defined as the axial range in which the specimen stage moves without losing focus while the imaging apparatus remains stable. It may not be possible to capture an image that includes the entire specimen in focus due to the narrow DOF in microscopic systems. Extended depth of focus (EDOF) is used to overcome this limitation in microscopic systems. Although the researchers have developed so many EDOF microscope approaches, this research field still has some crucial shortcomings such as high computational costs, complexity and execution time, requiring additional equipment, low precise characterization of curves, and edges in images, varying performance depending on the specimen and microscope, using only gray levels of input images to acquire the pixel’s focus values. In order to minimize these shortcomings and comprehensively analyze the performance of EDOF approaches, a novel multi-focus image data set is generated, and a deep learning-based EDOF microscope approach is proposed in this study. When compared with the state-of-art EDOF approaches, our study provides various crucial contributions such as the first EDOF approach based on unsupervised deep learning, providing more accurate and specimen-free EDOF, generating a novel multi-focus image data, not requiring any pre- or post-processing technique and acquiring the pixel’s focus degrees using deep features. In order to evaluate the effectiveness of the suggested approach, 20 different EDOF approaches are applied to a multi-focus image data set containing 9 image collections (4 synthetic and 5 microscope image collections) in total. Performance analysis metrics with and without requiring a reference image are preferred to identify which EDOF microscope approach can extract more essential details from the multi-focus images for the synthetic and microscope image collections, which are Root Mean Square Error (RMSE), Peak Signal Noise Ratio (PSNR), Universal Quality Index (UQI), Correlation Coefficient (CC), Perception-based Image Quality Evaluator (PIQE), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Extension of Universal Quality Index for N Images (UQIN), and Naturalness Image Quality Evaluator (NIQE). Objective and subjective analysis of this study demonstrates that unsupervised deep learning model is more efficient to transmit crucial details from multi-focus images. Moreover, the suggested EDOF microscope approach with highest PSNR, UQI, CC, UQIN and lowest RMSE, PIQE, BRISQUE, NIQE produces higher performance than the state-of-art approaches.
- 25 March 2024
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 37 (4) , 1991-2013
DL-EDOF: Novel Multi-Focus Image Data Set and Deep Learning-Based Approach for More Accurate and Specimen-Free Extended Depth of Focus
Depth of focus (DOF) is defined as the axial range in which the specimen stage moves without losing focus while the imaging apparatus remains stable. It may not be possible to capture an image that includes the entire specimen in focus due to the narrow DOF in microscopic systems. Extended depth of focus (EDOF) is used to overcome this limitation in microscopic systems. Although the researchers have developed so many EDOF microscope approaches, this research field still has some crucial shortcomings such as high computational costs, complexity and execution time, requiring additional equipment, low precise characterization of curves, and edges in images, varying performance depending on the specimen and microscope, using only gray levels of input images to acquire the pixel’s focus values. In order to minimize these shortcomings and comprehensively analyze the performance of EDOF approaches, a novel multi-focus image data set is generated, and a deep learning-based EDOF microscope approach is proposed in this study. When compared with the state-of-art EDOF approaches, our study provides various crucial contributions such as the first EDOF approach based on unsupervised deep learning, providing more accurate and specimen-free EDOF, generating a novel multi-focus image data, not requiring any pre- or post-processing technique and acquiring the pixel’s focus degrees using deep features. In order to evaluate the effectiveness of the suggested approach, 20 different EDOF approaches are applied to a multi-focus image data set containing 9 image collections (4 synthetic and 5 microscope image collections) in total. Performance analysis metrics with and without requiring a reference image are preferred to identify which EDOF microscope approach can extract more essential details from the multi-focus images for the synthetic and microscope image collections, which are Root Mean Square Error (RMSE), Peak Signal Noise Ratio (PSNR), Universal Quality Index (UQI), Correlation Coefficient (CC), Perception-based Image Quality Evaluator (PIQE), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Extension of Universal Quality Index for N Images (UQIN), and Naturalness Image Quality Evaluator (NIQE). Objective and subjective analysis of this study demonstrates that unsupervised deep learning model is more efficient to transmit crucial details from multi-focus images. Moreover, the suggested EDOF microscope approach with highest PSNR, UQI, CC, UQIN and lowest RMSE, PIQE, BRISQUE, NIQE produces higher performance than the state-of-art approaches.
- 19 March 2024
- Published by Springer Nature
- p. 233-248
An Efficient Technique Based on Deep Learning for Automatic Focusing in Microscopic System
- 19 March 2024
- Published by Springer Nature
- p. 233-248
An Efficient Technique Based on Deep Learning for Automatic Focusing in Microscopic System
- 16 December 2023
- Published by Eskisehir Osmangazi Universitesi Muhendislik ve Mimarlik Fakultesi Dergisi in Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi
- Vol. 31 (3) , 917-930
INVESTIGATION OF EFFECTS OF DEEP FEATURES ON FOCUS VALUES EXTRACTION IN EXTENDED DEPTH OF FOCUS
Mikroskobik sistemlerde var olan odaklama derinliğinden dolayı numunenin tüm alanının odaklandığı görüntü elde etmek imkânsız olabilmektedir. Bu durum, mikroskobik sistemlerde görüntü işleme ve yapay zekâ algoritmaları kullanılarak gerçekleştirilen sınıflandırma, bölütleme, hizalama (registration), panoramik birleştirme (stitching) gibi uygulamalarının başarılarını olumsuz yönde etkilemektedir. Literatürde numunenin tüm alanının odaklandığı görüntü elde etmek için odaklama derinliğinin artırılması yaklaşımları geliştirilmektedir. Literatür çalışmaları, bu yaklaşımların, görüntülerdeki eğrilerin ve kenarların düşük kesinlikte karakterizasyonu, daha yüksek koşma süresi ve incelenen numuneye ve kullanılan mikroskoba göre performans değişimi gibi çeşitli kısıtlamalara sahip olduklarını ortaya koymaktadır. Ek olarak, bu yaklaşımlar odaklama bilgilerini genelde görüntülerin gri seviye değerlerini kullanarak hesaplamaktadırlar. Bu çalışmada bu kısıtlamaları minimize etmek için yeni bir odaklama derinliğinin artırılması yaklaşımı geliştirilmekte ve odaklama derinliğinin artırılmasında derin özelliklerin odaklama değerlerinin çıkarılmasındaki etkileri incelenmektedir. Çalışmada elde edilen sonuçlar derin özelliklerin piksellerin odaklama değerlerini hesaplamada gri seviye değerlerine göre daha etkin olduğunu göstermektedir.
- 16 December 2023
- Published by Eskisehir Osmangazi Universitesi Muhendislik ve Mimarlik Fakultesi Dergisi in Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi
- Vol. 31 (3) , 917-930
INVESTIGATION OF EFFECTS OF DEEP FEATURES ON FOCUS VALUES EXTRACTION IN EXTENDED DEPTH OF FOCUS
Mikroskobik sistemlerde var olan odaklama derinliğinden dolayı numunenin tüm alanının odaklandığı görüntü elde etmek imkânsız olabilmektedir. Bu durum, mikroskobik sistemlerde görüntü işleme ve yapay zekâ algoritmaları kullanılarak gerçekleştirilen sınıflandırma, bölütleme, hizalama (registration), panoramik birleştirme (stitching) gibi uygulamalarının başarılarını olumsuz yönde etkilemektedir. Literatürde numunenin tüm alanının odaklandığı görüntü elde etmek için odaklama derinliğinin artırılması yaklaşımları geliştirilmektedir. Literatür çalışmaları, bu yaklaşımların, görüntülerdeki eğrilerin ve kenarların düşük kesinlikte karakterizasyonu, daha yüksek koşma süresi ve incelenen numuneye ve kullanılan mikroskoba göre performans değişimi gibi çeşitli kısıtlamalara sahip olduklarını ortaya koymaktadır. Ek olarak, bu yaklaşımlar odaklama bilgilerini genelde görüntülerin gri seviye değerlerini kullanarak hesaplamaktadırlar. Bu çalışmada bu kısıtlamaları minimize etmek için yeni bir odaklama derinliğinin artırılması yaklaşımı geliştirilmekte ve odaklama derinliğinin artırılmasında derin özelliklerin odaklama değerlerinin çıkarılmasındaki etkileri incelenmektedir. Çalışmada elde edilen sonuçlar derin özelliklerin piksellerin odaklama değerlerini hesaplamada gri seviye değerlerine göre daha etkin olduğunu göstermektedir.