This work presents the concept of image dataset classification using CNN and proposed deep learning method. It uses the dataset of bacteria for classification purpose. The CNN and DBN system has a problem with accuracy, then proposed method is used for improving the system. The use of PCA method provides only identification of features in images but it does not help to improve accuracy of system. Due to this, it requires better deep learning method for improving accuracy of system. The CNN method uses only 2 convolutional layers for feature mapping. But the proposed method uses 5 convolutional layers and 3 overlapping layers. Due to this, it helps to improve accuracy of system as compared to other existing methods. In CNN, the layers based approach is main part in this system and convolutional layer is the first layer, then follows the hidden layer and output layer. This shows that proposed AlexNet shows better improvement in accuracy of datasets as compared to other methods and hence proves better.