Local entropy based pre-processing for flame images of alumina rotary kiln

The sintering status of rotary kiln is so complex that it can not be described by a precise mathematical model. Therefore it is difficult to monitor the online status continuously and control the sintering conditions automatically. The evaluation and control of the sintering information from burning flame images have been shown effective yet challenging techniques in the rotary kiln process. Based on the image coarse segmentation using grayscale value information, this paper presents a new scheme of segmenting the flame and material zones with local entropy information at the segmentation stage of pre-processing for more discriminable flame and material zones. Our experimental results show that the proposed method achieves good segmentation performance, and that the computational burden is much lower compared with traditional texture segmentation algorithms.