Tufts University | United States
Dr. Vladimir Frants is a research-oriented computer scientist whose work bridges artificial intelligence, quaternion neural networks, computer vision, and medical imaging. With a strong foundation in electrical engineering and computer science, his research focuses on developing robust and interpretable neural architectures for visual data enhancement, particularly in challenging environments such as adverse weather and biomedical imaging. His expertise extends to deep learning, digital signal processing, and computational vision, where he integrates theoretical insights with real-world applications in healthcare and intelligent transportation systems. Dr. Frants’s doctoral research centers on quaternion-valued neural architectures, a mathematically elegant extension of complex-valued neural networks, offering a richer representational framework for color and multi-channel image data. Through this, he has proposed advanced models for rain and haze removal, biomedical image enhancement, and adversarial robustness. His notable works include QRNet, a quaternion-based Retinex framework for enhancing wireless capsule endoscopy images (Bioengineering, 2025), and QSAM-Net and QCNN-H, pioneering architectures published in top-tier IEEE journals like IEEE Transactions on Multimedia and IEEE Transactions on Cybernetics. These contributions have advanced state-of-the-art performance in image restoration and artifact removal, reflecting a deep understanding of both mathematical modeling and real-world imaging challenges. His professional trajectory includes leading roles in software and signal processing research, where he combined machine learning with practical engineering. At Moscow State University of Technology “STANKIN,” he led a multidisciplinary team developing a CT-based 3D-printed prosthesis design platform, integrating deep learning for automated skull reconstruction and prosthesis generation. Earlier, at the Institute of Signal Processing and Computer Vision in Rostov-on-Don, he designed image inpainting and 3D reconstruction algorithms, contributing to advancements in visual computing efficiency. In academia, Dr. Frants has taught core computer science and programming courses and mentored undergraduate students on research projects that have led to published work in international conferences. His mentorship emphasizes research integrity, algorithmic creativity, and cross-disciplinary collaboration. Through his integration of theoretical depth, experimental design, and application-oriented innovation, Dr. Vladimir Frants continues to make significant contributions to the fields of artificial intelligence, medical imaging, and computational vision—pioneering intelligent systems that enhance perception, diagnosis, and decision-making in complex environments.
Featured Publications
Frants, V., Agaian, S., & Panetta, K. (2023). QCNN-H: Single-image dehazing using quaternion neural networks. IEEE Transactions on Cybernetics, 53(9), 5448–5458.
Frants, V., Agaian, S., & Panetta, K. (2023). QSAM-Net: Rain streak removal by quaternion neural network with self-attention module. IEEE Transactions on Multimedia, 26, 789–798.
Frantc, V. A., Voronin, V. V., Marchuk, V. I., Sherstobitov, A. I., & Agaian, S. (2014). Machine learning approach for objective inpainting quality assessment. In Mobile Multimedia/Image Processing, Security, and Applications 2014 (Vol. 9120). SPIE.
Voronin, V., Semenishchev, E., Frants, V., & Agaian, S. (2018). Smart cloud system for forensic thermal image enhancement using local and global logarithmic transform histogram matching. In 2018 IEEE International Conference on Smart Cloud (SmartCloud) (pp. 153–157). IEEE.
Voronin, V. V., Frantc, V. A., Marchuk, V. I., Sherstobitov, A. I., & Egiazarian, K. (2015). No-reference visual quality assessment for image inpainting. In Image Processing: Algorithms and Systems XIII (Vol. 9399, pp. 234–241). SPIE.
Viacheslav, V., Vladimir, F., Vladimir, M., Nikolay, G., Roman, S., & Valentin, F. (2014). Low-level features for inpainting quality assessment. In 2014 12th International Conference on Signal Processing (ICSP) (pp. 643–647). IEEE.
Zelenskii, A. A., Frants, V. A., & Semenishchev, E. A. (2020). Trajectory-planning algorithm based on engineering vision in manipulator management. Russian Engineering Research, 40(1), 1–5.
Zelensky, A., Semenishchev, E., Gavlicky, A., Tolstova, I., & Frantc, V. (2019). Fusing data processing in the construction of machine vision systems in robotic complexes. EPJ Web of Conferences, 224, 04009.
Voronin, V. V., Marchuk, V. I., Frantc, V. A., & Egiazarian, K. (2014). Fast texture and structure image reconstruction using the perceptual hash. In Image Processing: Algorithms and Systems XI (Vol. 8655, pp. 253–264). SPIE.