Currently, the one-dimensional signal processing method for heart-sound analysis and recognition is the mainstream in researches. In order to gain more intuitive features in manifestation, to improve the effect of classification, and to endarge the heart-sound recognition field, this paper puts forward a heart-sound texture feature extraction and recognition algoriithm, which is based on heart-sound window function and the combination of heart-sound and image processing technology. Firstly, we give a heart-sound model, a definition of heart-sound time-frequency diagram, and a heart-sound texture map; we also discuss how to utilize heart-sound window function and short-time Fourier transform to obtain a two-dimensional heart-sound time-frequency diagram. After that, in the light of the characteristics of heart-sound, we mainly study the structure principle and implementation method of a heart-sound window function Finally, the heart-sound texture feature extraction and identification are realized by the improved pulse-coupled neural network model (IPCNN). Simulation experiments show that compared with the traditional window function, the heart-sound time-frequency diagram obtained using heart-sound window function has a clearer and noise well suppressed texture. Furthermore, compared with other three kinds of typical recognition methods, IPCNN has the lower computational cost and higher recognition rate. So, we can arrive at the conclusion that the method for heart-sound feature extraction and recognition based on image processing techniques is the effective one.