本文選題：曲波變換 + 煤巖識(shí)別　； 參考：《煤炭學(xué)報(bào)》2017年05期

【摘要】：針對(duì)小波難以表達(dá)煤巖圖像的邊緣曲線特征,影響識(shí)別精度的問(wèn)題,提出一種基于曲波變換的方法,對(duì)煤巖圖像邊緣進(jìn)行稀疏表示。該方法通過(guò)曲波變換對(duì)煤巖圖像進(jìn)行曲波分解,得到各尺度層曲波系數(shù),保留圖像變換后的Coarse層低頻系數(shù),基于壓縮感知理論,利用隨機(jī)高斯矩陣對(duì)高頻系數(shù)進(jìn)行測(cè)量,實(shí)現(xiàn)高維系數(shù)降維,Coarse層低頻系數(shù)與降維后的高頻系數(shù)通過(guò)級(jí)聯(lián)構(gòu)成煤巖圖像特征向量,最后結(jié)合支持向量機(jī)對(duì)煤巖圖像進(jìn)行分類(lèi)識(shí)別。實(shí)驗(yàn)表明:通過(guò)曲波分解提取的特征能夠有效地表達(dá)煤巖圖像邊緣的曲線特征,所提出方法煤巖的分類(lèi)準(zhǔn)確率達(dá)93.75%,比Haar小波方法提高了4.37%,所用降維方法比線性降維方法提取的特征向量更加有利于煤巖圖像的分類(lèi)識(shí)別。
[Abstract]:Aiming at the problem that wavelet is difficult to express the edge curve feature of coal and rock image and affect the recognition accuracy, a method based on Qu Bo transform is proposed to represent the edge of coal and rock image sparsely.This method decomposes the marching wave of coal and rock images by Qu Bo transform, obtains the Qu Bo coefficients of each scale layer, and preserves the low frequency coefficients of the Coarse layer after the image transformation. Based on the theory of compression perception, the high frequency coefficients are measured by using the random Gao Si matrix.The feature vectors of coal and rock images are constructed by cascading the low frequency coefficients of Coarse layer and the high frequency coefficients after dimension reduction. Finally, the classification and recognition of coal and rock images are carried out with support vector machine.The experimental results show that the features extracted by Qu Bo can effectively express the curve features of coal and rock images.The classification accuracy of the proposed method is 93.75, which is 4.37 higher than that of the Haar wavelet method. The feature vectors extracted by the reduced dimension method are more favorable to the classification and recognition of coal and rock images than the linear dimensionality reduction method.
【作者單位】： 中國(guó)礦業(yè)大學(xué)(北京)機(jī)電與信息工程學(xué)院;
【基金】：國(guó)家重點(diǎn)研發(fā)計(jì)劃資助項(xiàng)目(2016YFC0801800) 國(guó)家自然科學(xué)基金重點(diǎn)資助項(xiàng)目(51134024)
【分類(lèi)號(hào)】：TD67;TP391.41

【相似文獻(xiàn)】

相關(guān)會(huì)議論文 前1條

1 黃廣譚;張明;張軍華;傅金榮;梁鴻賢;;曲波變換與EMD結(jié)合的弱信號(hào)提取方法研究[A];中國(guó)地球物理2013——第十八專(zhuān)題論文集[C];2013年

，

本文編號(hào)：1768596