Research Portfolio for PhD Opportunities in Computer Science
I am building a research portfolio anchored by a kinship-verification project and manuscript, while remaining broadly open to PhD opportunities across software engineering and computer science. This page highlights the project, publication draft, and research direction I can share directly with prospective PhD advisors.
Building publication-ready research infrastructure for a difficult biometric task where inherited resemblance must be distinguished from identity, age, pose, and image-quality variation.
Research framing
My current project uses kinship verification as a concrete research vehicle, while my broader PhD interests remain open across software engineering and computer science. The work emphasizes rigor, reproducibility, and extensible experimentation.
Technical depth
The toolkit spans classical handcrafted descriptors, metric-learning workflows, native deep-learning pipelines, and Gated Autoencoder-style pair modeling under one consistent experimental interface.
PhD-ready signal
The combination of a manuscript draft, research infrastructure, and dataset-centric experimentation gives faculty a concrete way to assess fit, rigor, and publication potential.
Kinship Verification from Face Imagery
Manuscript draft | 2026
A draft manuscript centered on a unified research toolkit for kinship verification, bringing classical descriptors, metric-learning pipelines, deep models, and gated pair-representation learning into one reproducible experimental framework.
Kinship Verification Toolkit
Research infrastructure for reproducible computer-vision experiments
This project turns a fragmented kinship-verification literature into a maintainable Python platform for running, comparing, and extending experiments across multiple algorithmic families.
Kinship verification is challenging because resemblance signals are subtle, age-dependent, and easily confounded by pose, lighting, and expression. The project focuses on building research infrastructure that makes these experiments cleaner, more comparable, and easier to extend.
A clean base for reproducible experiments, comparative benchmarks, publication support, and future advisor-led extensions.
- Classical feature baselines using handcrafted pair descriptors.
- Metric-learning style KinVer experiments over bundled feature matrices.
- Native deep-learning pipelines for KinFaceW and FIW-style settings.
- Gated Autoencoder variants for pairwise representation learning.
- Designed a unified CLI, config system, and reporting layout for consistent experimentation.
- Integrated public benchmark workflows with support for a local private dataset adapter.
- Created a cleaner base for benchmarking, ablations, publication-ready reporting, and future model extensions.
Research infrastructure, experimental rigor, and room to scale
Happy to share the manuscript, codebase, and broader research interests directly
I am broadly open to PhD opportunities across software engineering and computer science, and I am flexible about research direction. I would be glad to share the paper draft and discuss how my project and engineering experience could contribute to a wide range of research areas, including but not limited to software engineering, systems, data-intensive platforms, applied AI, and other rigorous CS research environments.