Abstract

The fundamental reason for the work exhibited in this paper, is to break down the idea of a deep learning algorithm to be specific, convolutional neural networks (CNN) in image classification. A study of deep learning, its strategies, comparison of frameworks, and algorithms is presented. The significance of (sufficient) training has been considered. The advancement has shown imperative execution in various vision assignments, for instance, image identification, question area and sementic division. In particular, late advances of deep learning procedures pass on asking execution to fine-grained image classification which intends to perceive subordinate-level classifications.

Keyword

Convolutional neural networks, Residual learning, Batch normalization, Deep learning.

Cite this article

.A review:deep learning technique for image classification. ACCENTS Transactions on Image Processing and Computer Vision. 2018;4(11):21-25. DOI:10.19101/TIPCV.2018.411003

Refference