A Robust Framework for 2D Human Face Reconstruction from Half-Frontal Views in Low-Quality Surveillance Footage

This paper proposes a robust framework for reconstructing 2D human facial images from half-frontal views, primarily captured under low-quality surveillance conditions. A custom MATLAB-based Graphical User Interface (GUI) is developed to support the complete pipeline, including frame extraction, enha...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International Journal of Emerging Engineering and Technology Ročník 3; číslo 2; s. 13 - 18
Hlavní autori: Siddiqua, Maria, Zia, Muhammad Furqan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Swedish College of Egineering and Technology 30.12.2024
Predmet:
2D face reconstruction
eye detection
face synthesis
half-frontal view
image enhancement
MATLAB GUI
ISSN:2958-3764, 2958-3764
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper proposes a robust framework for reconstructing 2D human facial images from half-frontal views, primarily captured under low-quality surveillance conditions. A custom MATLAB-based Graphical User Interface (GUI) is developed to support the complete pipeline, including frame extraction, enhancement, and face reconstruction. Representative frames are extracted and enhanced for video inputs using one of three techniques: histogram equalization, contrast stretching, or logarithmic transformation. Reconstruction involves detecting a single eye from the half-frontal image, followed by horizontal flipping and concatenation to generate a symmetric full-frontal face. The reconstructed faces are validated using the Viola-Jones object detection algorithm to confirm the presence and alignment of facial features. Quantitative evaluation uses the Structural Similarity Index (SSIM) and Jaccard Index (JI) to measure image quality and geometric accuracy. The proposed method is tested on publicly available datasets and a custom-designed dataset reflecting real-world surveillance challenges such as low resolution and poor illumination. Experimental results demonstrate that the framework delivers accurate and visually coherent reconstructions with low computational overhead, making it suitable for real-time surveillance and facial analysis applications.
ISSN:2958-3764
2958-3764
DOI:10.57041/z5e98x92