The use of algorithms is helpful in analysis of various data samples. Examples of these applications are sound and graphic processing that are used in authentication and analysis of images. In this work, we propose technique of extracting data from image file created based on voice sample. Proposed method makes use of mathematical model of wavelet transformation and its graphical visualization like scaleogram combined with computational intelligence methods like neural network and heuristic algorithm. In order to verify operation of proposed technique we present experimental results.