The use of deep learning in image segmentation, classification and detection

TL;DR

This paper compares the performance and efficiency of LeNet and Network in Network architectures across various image classification and detection tasks using diverse datasets.

Contribution

It provides a comparative analysis of LeNet and NiN architectures for image classification and detection in different application domains.

Findings

NiN outperforms LeNet in accuracy and efficiency.

Performance varies across different datasets and tasks.

The study highlights the suitability of each network for specific applications.

Abstract

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.