To well monitor and optimize the flotation production, a computer vision and image analysis system is used. In such a system, the first important step is to acquire the froth surface images in high quality. Froth imaging quality is hard to control, and the industrial field noise, froth 3D properties, complex textures, and mixed colors can also cause the flotation image to be difficult to segment and process. To acquire high quality images, a new system for image acquisition of the lead flotation is studied. The system constructs the free-form surface lens based on the non-imaging optics theory, which can improve the optical efficiency of the lens and the uniformity of light sources, and can reduce flare effects. For the compensation, an improved MSR (Multi-Scale Retinex) adaptive image algorithm is proposed to increase the brightness and intensity contrast for small bubbles, and to enhance texture details and froth weak edges by analyzing the Retinex output characteristics of the shaded area and improving the gain function. Under the condition of the optimal parameters, the image acquisition system can obtain uniform illumination and reduce different noises. Experiments show that the new froth image acquisition system increases Signal/Noise by 14%, contrast by 21%, and image segmentation accuracy by 26% in an image.

https://www.mdpi.com/2075-163X/8/3/103/pdf

Froth Image Acquisition and Enhancement on Optical Correction and Retinex Compensation

The classical gray level co-occurrence matrix(GLCM) neglects the directional differences of texture. A novel method of image classification is presented in this paper. Multi-angle weighting of GLCM is proposed to decrease effects of directional difference, in which second-order statistics, such as energy, entropy, moment of inertia, moments of deficit and relevance, are calculated to describe image texture. The contributions to classifier of second-order statistics are evaluated using information gain. The model based on one against one support vector machines (OAOSVM) is realized. The experimental results has shown that the proposed method can accomplish image classification with higher accuracy on several standard image datasets than other methods.

http://ieeexplore.ieee.org/iel7/7225914/7259602/07260238.pdf

Texture information fusion based image classification

in this paper, a multi-stage features sparse learning method for hyperspectral image scene recognition is proposed. The hyperspectral image is decomposed into five scales by Gaussian function at eight angles. Gabor visual features are extracted at different scales of each angle. The visual dictionary of hyperspectral image is constructed by sparse coding, and the sparse coding coefficient matrix of multi angle and multi-scale features of hyperspectral image is formed Compared with BoVW or PLSA, the overall accuracy of SVM classifier is improved by 4.47% and 5.39% respectively, and the kappa coefficient is improved by 0.0685 and 0.0768 respectively. The results show that the proposed multi-angle and multi-scale sparse coding method for hyperspectral image scene recognition is more interpretable than the description of hyperspectral image features with BoVW or PLSA, and can effectively improve the effect of hyperspectral image scene recognition.

Multi-stage Features Sparse Learning Based Scene Recognition of Hyperspectral Image

In this study, a novel fuzzy co-occurrence matrix to extract texture feature is presented. The impact of directional difference is eliminated through multi-angle fusion of gray level co-occurrence matrix (GLCM). Fuzzy c-means is introduced into gray level co-occurrence matrix, and the membership of each pixel to texture unit is calculated. Then second-order statistics, such as energy, entropy, contrast, homogeneity and correlation, are deduced to describe texture characteristics. Experiments assisted by one-against-rest support vector machine on benchmark texture datasets have shown that the proposed method, considering the directional differences and uncertainty probability of GLCM, provides a better rotation invariance and robustness than the other improved GLCM.

Fuzzy co-occurrence matrix fusion based texture feature extraction

http://or.nsfc.gov.cn/bitstream/00001903-5/487791/1/1000017198119.pdf

Chen Zhipeng

Papers

Froth homogeneity analysis using rotate classification fuzzy texture spectrum for mineral flotation process monitoring