(1. 中南大學(xué) 冶金科學(xué)與工程學(xué)院，長沙 410083；
2. 中南大學(xué) 信息科學(xué)與工程學(xué)院，長沙 410083；
3. 長沙有色冶金設(shè)計研究院，長沙 410011)
摘 要:
關(guān)鍵字: 氧化鋁回轉(zhuǎn)窯；火焰圖像；火焰形狀；CBIR；傅里葉描述子
（1. School of Metallurgical Science and Engineering, Central South University, Changsha 410083, China;
2. School of Information Science and Engineering, Central South University, Changsha 410083, China;
3. Changsha Engineering and Research Institute of Nonferrous Metallurgy, Changsha 410011, China）
Abstract:A shape based alumina rotary kiln flame image retrieval method was proposed. First, the flame shapes were analyzed detailedly, a distance function was put forward. Through Fourier transformation, the flame shape Fourier descriptors were calculated. The results indicate that this distance function can depict the shape effectively. A flame image retrieval prototype system was proposed using this Fourier descriptors. With the flame images sampled from an alumina rotary kiln, retrieval experiments were carried out with the traditional retrieval method, invariant moment retrieval method and the proposed method. The results demonstrate that the proposed method outperforms the other two methods in terms of retrieval precision and efficiency. The research results can provide strong support for the control of the rotary kiln.
Key words: alumina rotary kiln; flame image; flame shape; CBIR; Fourier descriptor
