Studying Very Low Resolution Recognition Using Deep Networks
This addresses a practical problem in visual recognition for applications where low-resolution images are common, but it is incremental as it combines existing techniques into a dedicated method.
The paper tackled the Very Low Resolution Recognition (VLRR) problem, where regions of interest can be smaller than 16x16 pixels, by developing a deep learning method called Robust Partially Coupled Networks that integrates super resolution, domain adaptation, and robust regression, achieving very impressive performances on tasks like face identification, digit recognition, and font recognition.
Visual recognition research often assumes a sufficient resolution of the region of interest (ROI). That is usually violated in practice, inspiring us to explore the Very Low Resolution Recognition (VLRR) problem. Typically, the ROI in a VLRR problem can be smaller than $16 \times 16$ pixels, and is challenging to be recognized even by human experts. We attempt to solve the VLRR problem using deep learning methods. Taking advantage of techniques primarily in super resolution, domain adaptation and robust regression, we formulate a dedicated deep learning method and demonstrate how these techniques are incorporated step by step. Any extra complexity, when introduced, is fully justified by both analysis and simulation results. The resulting \textit{Robust Partially Coupled Networks} achieves feature enhancement and recognition simultaneously. It allows for both the flexibility to combat the LR-HR domain mismatch, and the robustness to outliers. Finally, the effectiveness of the proposed models is evaluated on three different VLRR tasks, including face identification, digit recognition and font recognition, all of which obtain very impressive performances.