研究泡沫图像分离岭研究在矿物浮选系统自动化控制中的应用,提高控制准确度以保证矿物回收率.由于泡沫的产生随机性强,存在泡沫相互粘连、边缘模糊的问题而不易分割识别,传统的分离岭分析方法对粘连、模糊的泡沫不能准确分割,无法有效提取泡沫特征而造成浮选系统控制准确度不高的问题.为解决上述问题,提出局部纹理分析方法控制矿物浮选系统.通过对泡沫图像自适应分割后,提取粗分割图像的纹理特征并识别,据识别结果对区域进行再分割或合并以实现泡沫分离岭,避免传统方法对粘连、模糊泡沫分割不准确的问题,然后根据提取出的泡沫大小形状等特征在线控制矿物浮选系统.实验表明,改进方法能够有效解决粘连、模糊泡沫分割不准确的问题,而保证了矿物浮选系统的控制准确度和矿物的回收率.%Research the bubble image separation ridge analysis in mineral flotation system automation control application , improving control accuracy in order to ensure that the mineral recovery. Because of the strong randomicity in bubble produced procedure, the bubbles adhere with each other and have fuzzy edges, so there is difficulty for segmentation and identification. Therefore, this paper put forward a local texture analysis method to control the mineral flotation systems. Through the adaptive segmentation of bubble images, the texture characteristics were extracted form thick segmentation images and then the recognition was processed. According to the results the regions were divided or merged again, avoiding the inaccurate segmentation of traditional method for adhered and fuzzy bubbles. Then according to the extracted features of bubble sizes and shapes, the mineral flotation systems were controlled on - line. Experimental results show that this method can effectively solve the problem that adhesion fuzzy foam segmentation is not accurate, and ensure the mineral flotation system control accuracy and the recovery rate of minerals.
展开▼
