Multi layered neural network architecture is proposed for compression of high-resolution images. The architecture considered has 64-4-64 structures, which achieves 100% compression. The proposed network is initially trained with pre selected data sets for accurate training. Feeding the scaled error back into the network at specific points, reduces the training time and reduces redundancy in weight storage. Results show the performance superiority of the network as compared with JPEG compression standard. Inserting noise on the compressed sets of data tests the network performance. Reconstructed image is compared with original image using SE and number of bits per pixel. The proposed architecture models array multipliers, carry save adders, global LUTs (Lookup Tables) for neuron construction. Calculated weights are stored in memory and read whenever required for signal processing. The control unit developed manages the data processing activity saving 20% of power when compared to direct form network structures. Power efficient architecture is developed for hardware implementation. A modification in the proposed architecture enhances the compression by 100% with sum-squared error of about 47.36.