This year blue algae blooms occurred largely in Lake Taihu, which caused people pay close attention to environment ofLake Taihu once again. It is very important to extract the information of cyanobacteria bloom-forming to analyze the distribution ofcyanobacteria bloom and remote sensing is one of measures of monitoring and protecting water quality. In this paper, it takes theCBERS-02 CCD data as a main data source. The information of cyanobacteria bloom was extracted by the method of buildingdecision tree, and with NDVI as the test variable, threshold value was determined based on CART. It obtains better effects accordingto analyzing the extraction result. The information of cyanobacteria bloom is also extracted from MODIS image of May 17th, 2007.The present study provides technical reference for long-term monitoring cyanobacteria bloom-forming in Lake Taihu.