查看文章

In recent year, with the speedy development in the digital contents identification, automatic classification of the images became most challenging task in the fields of computer vision. Automatic understanding and analysing of images by system is difficult as compared to human visions. Several research have been done to overcome problem in existing classification system, but the output was narrowed only to low level image primitives. However, those approach lack with accurate classification of images. In this paper, our system uses deep learning algorithm to achieve the expected results in the area like computer visions. Our system present Convolutional Neural Network (CNN), a machine learning algorithm being used for automatic classification the images. Our system uses the Digit of MNIST data set as a bench mark for classification of grayscale images. The grayscale images in the data set used for training which require more computational power for classification of images. By training the images using CNN network we obtain the 98% accuracy result in the experimental part it shows that our model achieves the high accuracy in classification of images.