Coal Gangue Image Process Approaches with Wavelet Analysis

According to main distribution regions of coal resource and the characteristic of gangues, a novel image process method of separating gangues from coal is proposed with wavelet analysis in this article. Under the different frequency ranges, a series of image processing approaches are exerted on coal gangue images with wavelet transform. Images of gangues and coal are first collected by means of the measurement system, and then are denoised. The image edges are detected by fast multi-scale edge detection. Images are segmented by algorithm of self-adaptive threshold. Using the multi-resolution merit of wavelet analysis, gangues images decomposition are especially stressed on, which provides the important data for selecting gangues from the coal. The coal gangues automatic separation system is realized by means of a newly ARM microprocessor, which has characteristics of high-performance, low power dissipation and low-cost exactly. The experiments result reveals that the proposed methods are efficient and practicable compared to traditional methods. And the suggested system is satisfied with accuracy requirements and real-time performance.