Circuits, Systems, and Signal Processing
Image restoration and recognition are important computer vision tasks representing an inherent part of autonomous systems. These two tasks are often implemented in a sequential manner, in which the restoration process is followed by a recognition. In contrast, this paper proposes a joint framework that simultaneously performs both tasks within a shared deep neural network architecture. This joint framework integrates the restoration and recognition tasks by incorporating: (i) common layers, (ii) restoration layers and (iii) classification layers. The total loss function combines the restoration and classification losses. The proposed joint framework, based on capsules, provides an efficient solution that can cope with challenges due to noise, image rotations and occlusions. The developed framework has been validated and evaluated on a public vehicle logo dataset under various degradation conditions, including Gaussian noise, rotation and occlusion. The results show that the joint framework improves the accuracy compared with the single task networks.
Chen, Ruilong; Mihaylova, Lyudmila; Zhu, Hao; and Bouaynaya, Nidhal Carla, "A Deep Learning Framework for Joint Image Restoration and Recognition" (2019). Henry M. Rowan College of Engineering Faculty Scholarship. 120.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Chen, R., Mihaylova, L., Zhu, H. & Bouaynaya, N. C. (2019). A Deep Learning Framework for Joint Image Restoration and Recognition. Circuits, Systems and Signal Processing 39, 1561–1580. https://doi.org/10.1007/s00034-019-01222-x