The accurate prediction and control of burning through point are the keys of improving the quantity and quality of sinter. The position of burning through point can be determined by identifying the flame image features of the tail through the sinter. How to effectively segment the image of the flame is the key to identify the characteristics of the flame. By using the approach of the c-means clustering flame image segmentation based on particle-pair optimizer, the flame image of the sintering machine plant-tail section will be segmented in this paper. Frequently, the standard c-means clustering algorithm may easily immerse in partial minimum and slow converging speed. However, this new calculation method can overcome these shortcomings. Besides, the results of the experiment also show that this method has many other advantages, such as effectively removing the halo of the sintering machine plant-tail section, high segmenting speed and obvious segmenting effects. This approach will lay a good foundation for the extraction and identification of image features in the following stages.
