A new approach for separating mathematics from usual text is presented. Contrary to the existing methods, it is more oriented toward the segmentation than the recognition, isolating the formulas outside and inside the text lines. The objective is to delimit a part of text which could disturb the OCR application, not yet trained for formula recognition and restructuring. The method is based on an adaptive segmentation working at two levels 1) A primary labelling identifies the more characteristic symbols; 2) A secondary labelling extends the context of the symbols for delimiting the formula inside the text. Experiments done on some commonly seen mathematical documents, show that our proposed method can achieve quite satisfactory rate making mathematical formulas extraction more feasible for real-world applications. The average rate of primary labelling of mathematical symbols is about 95.3% and their secondary labelling can improve the rate about 4%. Thus, about 95% of formulas are wel...