Multi-task deep CNN model for no-reference image quality assessment on smartphone camera photos
This work addresses the need for automated quality assessment of smartphone photos, which is crucial for consumer decisions, but it is incremental as it builds on prior CNN-based approaches.
The paper tackled the labor-intensive problem of evaluating smartphone camera photo quality by proposing a multi-task deep CNN model that uses scene type detection as an auxiliary task, resulting in improved SROCC performance compared to traditional and single-task CNN-based methods.
Smartphone is the most successful consumer electronic product in today's mobile social network era. The smartphone camera quality and its image post-processing capability is the dominant factor that impacts consumer's buying decision. However, the quality evaluation of photos taken from smartphones remains a labor-intensive work and relies on professional photographers and experts. As an extension of the prior CNN-based NR-IQA approach, we propose a multi-task deep CNN model with scene type detection as an auxiliary task. With the shared model parameters in the convolution layer, the learned feature maps could become more scene-relevant and enhance the performance. The evaluation result shows improved SROCC performance compared to traditional NR-IQA methods and single task CNN-based models.