This paper uses two compression techniques on an image, namely, Vector Quantization (VQ) and Feed Forward Neural Network (FFNN). VQ is used along with K-Mean clustering to initiate the centroids and form the codebook. The FFNN in this algorithm has an architecture specification of 64 nodes in the input and the output layer along with 16 hidden layers with 16 nodes each. The VQ is applied first on the input image to achieve compression and then the VQ compressed image is fed to the FFNN network for additional compression. A set of observations for compression is recorded for different values of K with a tile size 8. The results are obtained for different values of K such as 50, 100, 150, 200, 250, 500 and 1000. The proposed algorithm gives a compression ratio of about 2 and an acceptable PSNR of about 20db for the standard test image Lena. Objective The main objective of this paper is to introduce an algorithm which combines an artificial intelligence technique with a standard compression technique to achieve desirable compression ratios. The flow of this paper is as follows, Section 1 gives an overall introduction about the image compression. Section 2 is about the related work done in image compression where a survey on few related standard papers and their methodologies and results are discussed. Section 3 gives a detailed explanation of the proposed algorithm with flow charts and step wise explanations. Section 4 includes the results and observations obtained through the proposed algorithm. The final section concludes the paper with scope for the future work using this algorithm.