In the printing industry, monitor gamut is one of the most important indices of the preprocess system. Usually, under some condition, monitor gamut is described as triangle by three vertex, all of them come from three monitor drive extreme values, in the channels such as red, green and blue one. In spite of the simplicity of the description method in manipulation, the triangle can not describe the monitor gamut exactly, because the number of the samples are too small too indicate the feature of the monitor gamut perfectly and the monitor gamut is related to its surround and configuration. In the research, based on mapping relation of digital image pixel value and its corresponding monitoring color, data pairs of digital image pixel values and its corresponding monitoring color blocks chroma values are sampled to establish a mapping model, which is based on BP neural network with exactitude to a perfect certainty. Then, more digital image pixel values are sampled at thicker intervals, their corresponding printing color chroma values are calculated by the mapping model, so the monitor gamut is covered by thicker chroma data not only in the gamut but also on the gamut polygon contour and vertexes, that leads to the best of its ability, much more vertexes are acquired in far much more color hue angel ranges to form the gamut polygon, and the gamut is described much more fully. The experiment shows that the gamut polygon drawn by the mapping model describes the monitor gamut much more objectively and reflects the monitor gamut factually.