A Survey to study about different Convolutional Neural Network on Various Image Classifications

Abstract

Multi label Image classification using Convolutional Neural Network is yet very difficult when it comes to performing. However, Single Label Image Classification can be performed easily and promisingly. As there are many categories of objects in a real world image, it becomes difficult to label them under various categories and also because of the lack of multi-label training image and high complexity. This paper surveys different Convolutional Neural Network (CNN) using Single Label Image Classification on which Multi Label Image Classification can be performed with High Accuracy. We have also learnt different trained Convolutional Neural Network architecture using UC MERCED Dataset which is essayed in this paper.