The use of deep learning in image segmentation, classification and detection
It provides an incremental comparison of existing deep learning methods for computer vision applications, with potential relevance to medical imaging and art analysis.
This paper compares LeNet and Network in Network architectures for image classification and detection tasks, evaluating their performance and computational efficiency using multiple datasets including burn wound images, art images, and facial databases.
Recent years have shown that deep learned neural networks are a valuable tool in the field of computer vision. This paper addresses the use of two different kinds of network architectures, namely LeNet and Network in Network (NiN). They will be compared in terms of both performance and computational efficiency by addressing the classification and detection problems. In this paper, multiple databases will be used to test the networks. One of them contains images depicting burn wounds from pediatric cases, another one contains an extensive number of art images and other facial databases were used for facial keypoints detection.