Automatic image captioning is the task where given an image the system must generate a caption that describes the contents of the image. Once you can detect objects in photographs and generate labels for those objects, you can see that the next step is to turn those labels into a coherent sentence description. Most of the approaches involve the use of very large convolution neural networks (CNN) for the object detection in the photographs and then a recurrent neural network (RNN) like an LSTM (Long short-term memory) to turn the labels into a coherent sentence. In our proposed approach we have tailored the CNN and LSTM and has been tested with CIFAR 10 and MNIST datasets. The experimentation resulted 94.67% accuracy with 25 random iterations.