Özet:

The Classification of images is an paramount topic in artificial vision systems which has drawn a notable amount of interest over the past years. This field aims to classify an image, which is an input, based on its visual content. Currently, most people relied on hand-crafted feature to describe an image in a particular way. Then, using classifiers which are learnable, such as SVM, random forest and decision tree were applied to the extract features to come to a final decision. The problem arises when large number of photos are concerned. It becomes too difficult problem to find fea-ture from them. This is the one of reasons that deep neural network model has been introduced. Owing to the existence of Deep learning, it can become feasible to represent the hierarchical nature of features using various number of layers and cor-responding weight with them. The existing image classification methods have been gradually applied in real world problems, but then there are various problems in its application processes, such as unsatisfactory effect and extremely low classification accuracy or then and weak adaptive ability. Models using deep learning concepts have robust learning ability, which combines the feature extraction and the process of clas-sification into a whole which then completes an image classification task, which can improve the image classification accuracy effectively. Convolutional Neural Networks are a powerfull deep neural network technique. These network preserve the spatial structure of a problem and were built for object recognition tasks such as classifying an image into respective classes. CNN are very known because people are getting an state of the art outcomes on complex computer vision and natural language processing tasks. Convolutional neural networks have been extensively used .

Anahtar Kelimeler: