国产日韩欧美一区二区三区三州_亚洲少妇熟女av_久久久久亚洲av国产精品_波多野结衣网站一区二区_亚洲欧美色片在线91_国产亚洲精品精品国产优播av_日本一区二区三区波多野结衣 _久久国产av不卡

?

基于圖像特征的銅粗選過(guò)程病態(tài)工況識(shí)別

2014-09-18 17:32盧明桂衛(wèi)華彭濤謝永芳

盧明+桂衛(wèi)華+彭濤+謝永芳

收稿日期:20130917

基金項(xiàng)目:國(guó)家創(chuàng)新研究群體科學(xué)基金資助項(xiàng)目(61321003);國(guó)家自然科學(xué)基金重點(diǎn)資助項(xiàng)目(61134006);國(guó)家自然科學(xué)基金資助項(xiàng)目(61273169)

作者簡(jiǎn)介:盧明(1979-),男,湖南益陽(yáng)人,中南大學(xué)博士研究生

通訊聯(lián)系人,Email: mlu@hnust.edu.cn

摘要:泡沫圖像特征是指泡沫圖像中與浮選性能相關(guān)的局部黑色水化區(qū)域大小,即局部光譜特征.針對(duì)這一局部光譜特征形狀、大小無(wú)規(guī)則性,提出了一種基于多維主元分析的特征提取方法,并將提取的特征應(yīng)用于銅浮選粗選過(guò)程病態(tài)工況識(shí)別.首先,描述了銅浮選粗選過(guò)程,分析了影響粗選過(guò)程的主要因素和黑色水化區(qū)域形成機(jī)理;然后,提出一種基于多維主元分析的圖像局部光譜特征提取方法;最后,將基于多維主元分析的圖像局部光譜特征提取算法應(yīng)用于銅浮選粗選泡沫圖像,并將所提取的圖像特征用于銅粗選病態(tài)工況識(shí)別.工業(yè)現(xiàn)場(chǎng)數(shù)據(jù)驗(yàn)證了所提方法的有效性.

關(guān)鍵詞:泡沫圖像;圖像特征;多維主元分析(MPCA);病態(tài)工況識(shí)別;銅粗選過(guò)程

中圖分類號(hào):TP391.41 文獻(xiàn)標(biāo)識(shí)碼:A

Sick Condition Recognition Based on the Image

Feature of Froth Image in Copper Rough Process

LU Ming1,2,GUI Weihua1,PENG Tao1,XIE Yongfang1

(1.School of Information Science and Engineering, Central South Univ, Changsha, Hunan410083,China;

2.School of Information and Electrical Engineering, Hunan Univ of Science and Technology, Xiangtan, Hunan411201,China)

Abstract:The image features of copper flotation froth image means the size of the area of local black hydration in the froth image, which is called local spectral feature and related to flotation performance. A local spectral feature extraction method based on MPCA was proposed for the irregularity of the size and the shape, and the extracted features were used in copper rougher flotation process to identify sick conditions. Firstly, we described the copper rougher flotation process and analyzed the impact of the main factors roughing process and the formation mechanism of black hydration region. Then, a method was proposed to extract the local feature of image based on MPCA. Lastly, the image local feature extraction algorithm based on MPCA was applied to the copper flotation rougher froth image and the extracted image features were used in copper rougher process for sick condition recognition. The validity of the proposed method has been verified with industrial data.

Key words:froth images;image feature;MultiPrincipal Component(MPCA);sick condition recognition;copper rough process

浮選是一種應(yīng)用最為廣泛的將有用礦物從礦石中分離出來(lái)的選礦方法.一直以來(lái), 選廠的生產(chǎn)操作都是依靠有經(jīng)驗(yàn)的工人對(duì)浮選泡沫進(jìn)行肉眼觀察完成的,對(duì)泡沫的判斷缺乏客觀標(biāo)準(zhǔn), 使得人工觀測(cè)為主的礦物浮選過(guò)程難以處于穩(wěn)定最優(yōu)運(yùn)行狀態(tài)[1-2].采用機(jī)器視覺(jué)代替人類視覺(jué), 利用圖像處理技術(shù)從泡沫圖像中提取出最為顯著、有效的視覺(jué)特征,對(duì)浮選泡沫進(jìn)行客觀描述, 并將視覺(jué)特征應(yīng)用于浮選過(guò)程的工況識(shí)別,能為礦物浮選過(guò)程實(shí)現(xiàn)實(shí)時(shí)控制與優(yōu)化提供操作指導(dǎo)[3-5].

浮選流程大多分為粗選、掃選、精選3個(gè)流程單元,每個(gè)流程單元由數(shù)量不等的浮選槽組成,各個(gè)流程之間彼此連接,相互影響[6-8].其中粗選首槽浮選工況好壞,直接影響了后續(xù)流程的操作和最終的產(chǎn)品質(zhì)量及產(chǎn)能.在整個(gè)流程中,粗選過(guò)程工況的識(shí)別尤為重要.以粗選首槽泡沫品位為評(píng)價(jià)指標(biāo),將銅粗選工況分為“正?!焙汀安B(tài)”兩個(gè)區(qū)域.銅粗選過(guò)程中的“病態(tài)”工況是指因初始條件和操作條件改變而導(dǎo)致粗選產(chǎn)品質(zhì)量不能滿足后續(xù)浮選流程要求的工況.當(dāng)出現(xiàn)病態(tài)工況時(shí),浮選泡沫圖像中的泡沫顏色(光譜)和形態(tài)特征會(huì)發(fā)生相應(yīng)的變化.

本文描述了銅浮選粗選過(guò)程的特點(diǎn),提出以黑色水化區(qū)域面積作為銅浮選粗選泡沫圖像局部光譜特征,并針對(duì)這一特征大小、形狀無(wú)規(guī)則性,提出一種基于MPCA的局部光譜特征提取新方法,并將所提取的特征用于銅浮選粗選病態(tài)工況識(shí)別.

1銅浮選粗選過(guò)程描述及泡沫圖像局部光

譜特征

如圖1所示,為某銅浮選廠生產(chǎn)流程,分為粗選、掃選、精選3個(gè)流程單元.虛線框?yàn)榇诌x過(guò)程.在整個(gè)銅浮選流程中,粗選是礦石經(jīng)過(guò)磨礦、注水、分級(jí)后進(jìn)入選別的第1步.粗選首槽的浮選工況好壞,直接影響了后續(xù)流程的操作和最終的產(chǎn)品質(zhì)量及產(chǎn)能.粗選工況好壞的衡量指標(biāo)是粗精礦品位,根據(jù)冶金學(xué)工業(yè)試驗(yàn),粗選的泡沫品位不能太高也不能太低,需要控制在某一范圍內(nèi),超出這一范圍, 則視為粗選過(guò)程工況處于“病態(tài)”,需要及時(shí)調(diào)整操作變量.長(zhǎng)期以來(lái),粗選過(guò)程的操作依賴于“人工看泡”[9-11].但是浮選現(xiàn)場(chǎng)環(huán)境惡劣,勞動(dòng)強(qiáng)度大,而且人工判別的方式主觀性太強(qiáng),易導(dǎo)致工況波動(dòng).如圖1所示,在粗選首槽安裝CCD彩色攝像機(jī)獲取粗選首槽泡沫圖像,從泡沫圖像中提取出最為顯著、有效的視覺(jué)特征,并將所提取的特征用于銅粗選過(guò)程病態(tài)工況識(shí)別,可以規(guī)范操作,為后續(xù)流程的調(diào)整提供指導(dǎo).

銅粗選過(guò)程中的病態(tài)工況是指因初始條件和操作條件改變而導(dǎo)致粗選產(chǎn)品質(zhì)量不能滿足后續(xù)浮選流程要求的工況.可以用粗選首槽泡沫品位作為粗選過(guò)程工況的評(píng)價(jià)指標(biāo).粗選過(guò)程中病態(tài)工況的識(shí)別是基于機(jī)器視覺(jué)的浮選過(guò)程監(jiān)控的關(guān)鍵.通過(guò)長(zhǎng)期觀察發(fā)現(xiàn),銅粗選槽溢流口處的泡沫狀態(tài)能很好地反應(yīng)泡沫上礦物附著的情況.如果目標(biāo)礦物附著不好,泡沫頂部或在泡沫連接處因?yàn)闆](méi)有承載金屬礦粒呈現(xiàn)水化的反光區(qū)域,顏色為黑色.這一區(qū)域過(guò)大則水化現(xiàn)象嚴(yán)重,泡沫上附著金屬礦粒較少,泡沫品位低;反之則泡沫坍塌現(xiàn)象嚴(yán)重,泡沫上附著的金屬礦粒掉入礦漿,泡沫品位也會(huì)降低.黑色水化區(qū)域的大小能很好地反映當(dāng)前浮選工況.某銅浮選粗選首槽泡沫圖像及局部黑色水化區(qū)域如圖2所示,對(duì)比泡沫背景,水化區(qū)域在視覺(jué)上呈現(xiàn)為黑色,與泡沫圖像中目標(biāo)礦物的顏色不一致,形狀、大小沒(méi)有規(guī)則.

2基于MPCA的圖像局部光譜特征提取

多元圖像分析是指利用PCA,PLS等多元統(tǒng)計(jì)分析工具,將多個(gè)通道圖像數(shù)據(jù)投影到互不相關(guān)的主成分空間上,利用主元和圖像像素變量之間的關(guān)系來(lái)提取圖像特征[12-13].

將一幀原始RGB圖像表示為一組由單變量組成的三維數(shù)據(jù)集合(I×J×M),其中I,J為像素幾何坐標(biāo),M為光譜坐標(biāo),如圖3所示.(I×J×M)可看作單變量圖像fM(x,y)在M方向的堆疊,M=R,G,B.

先將(I×J×M)展開(kāi)成2維數(shù)據(jù)矩陣X(N×M),如圖3所示,其中N=I×J.于是,I×J個(gè)像素的fM(x,y)可以按照行或者列特定的順序展開(kāi)成一維的N×1圖像像素矢量.

展開(kāi)后的2維多元圖像矩陣可以寫成:

X(I×J)×M=[X1 X2 … XM]N×M.(1)

對(duì)X(N×M)進(jìn)行PCA,將其分解成A(A≤M)個(gè)主成分的線性組合:

XN×M=∑Aa=1tapTa+E. (2)

式中:ta(a=1,2,…,A,A≤M)為標(biāo)準(zhǔn)正交的N維主成分得分矢量;pa(a=1,2,…,A,A≤M)為標(biāo)準(zhǔn)正交的M維主成分負(fù)載矢量;E為N×M維的殘差矩陣.當(dāng)A=M時(shí),殘差矩陣E為0矩陣.

對(duì)于展開(kāi)后的多元圖像矩陣X(N×M),一般有N遠(yuǎn)大于M,也就是矩陣X(N×M)在行方向上元素很多,在列方向上元素很少.對(duì)于這樣的“窄”矩陣進(jìn)行PCA分解,常采用構(gòu)造“核”矩陣的方法[14-15]來(lái)減少計(jì)算時(shí)間.構(gòu)造核矩陣:

K=XTX. (3)

其中K為Μ×Μ的低維核矩陣.

然后對(duì)K進(jìn)行奇異值特征分解,得到的特征矢量就是主成分負(fù)載矢量pa,將pa根據(jù)特征值大小按照降序排列,得到排序以后的負(fù)載矢量pda,pd1為最大的特征值對(duì)應(yīng)的特征矢量.由負(fù)載矢量pda,可計(jì)算出主元得分矢量tda:

tda=Xpda. (4)

得分矢量tda中的每個(gè)元素對(duì)應(yīng)于3個(gè)變量(R,G,B)的加權(quán)平均像素,是不同像素位置的像素強(qiáng)度信息的壓縮表述,代表了原圖像中不同像素位置的光譜信息[16-18].如果同一圖像中不同像素位置像素光譜特征相同,這些像素的得分值的關(guān)系將完全相同,即原始圖像中所有具有相同光譜特征的像素的得分值在散點(diǎn)圖中將重疊或者至少在同一區(qū)域.因此,根據(jù)累計(jì)貢獻(xiàn)率選取主元個(gè)數(shù),畫出不同主元的得分矢量強(qiáng)度散點(diǎn)圖并在散點(diǎn)圖中標(biāo)記出感興趣的區(qū)域就可以捕獲原始圖像中的局部區(qū)域光譜特性.

依據(jù)公式(5),式中為Kronecker積,構(gòu)建第一得分圖像Ta (既d=1時(shí)的圖像):

Ta=Xpda. (5)

然后利用得分值和組成該區(qū)域的像素變量之間的關(guān)系將標(biāo)記的感興趣區(qū)域映射到第一得分圖像Ta上.

將特征像素值約束為0到255之間的整數(shù),即:

Ta(i,j)=

RoundTa(i,j)-min [Ta(i,j)]max [Ta(i,j)]-min [Ta(i,j)]×255.(6)

式中:max [Ta(i,j)],min [Ta(i,j)]分別為主元圖像中最大像素值和最小像素值.

統(tǒng)計(jì)像素點(diǎn)個(gè)數(shù),計(jì)算標(biāo)記區(qū)域的面積大小SL作為圖像的局部區(qū)域光譜特征:

SL=N×Si. (7)

式中:N為標(biāo)記區(qū)域的像素點(diǎn)個(gè)數(shù);Si為單位像素面積.

3實(shí)驗(yàn)結(jié)果與分析

3.1基于MPCA的銅浮選泡沫圖像局部光譜特征

提取算法

根據(jù)銅浮選泡沫圖像中的黑色水化區(qū)域的特點(diǎn),提出基于MPCA的銅浮選泡沫局部特征提取算法,其步驟如下:

1)將原始圖像(I×J×M)展開(kāi)成二維數(shù)據(jù)X(N×M),其中N=I×J.

2)構(gòu)造核矩陣K=XTX,并對(duì)K矩陣進(jìn)行奇異值分解,計(jì)算負(fù)載矢量pa,并將pa根據(jù)特征值大小按照降序排列,得到排序以后的負(fù)載矢量pda.

3)按式(4)計(jì)算主元得分矢量,計(jì)算累積貢獻(xiàn)率CCR,根據(jù)累計(jì)貢獻(xiàn)率CCR≥85%,選取主元個(gè)數(shù).

4)依據(jù)選取的主元,繪制主元得分矢量強(qiáng)度散點(diǎn)圖,標(biāo)記局部區(qū)域?qū)?yīng)的得分值聚集區(qū)或離群區(qū),同時(shí)記錄得分值所對(duì)應(yīng)的特征像素值和空間位置.

5)按照式(5)重構(gòu)第一得分圖像,利用得分值和局部區(qū)域特征像素變量之間的關(guān)系,將得分矢量強(qiáng)度散點(diǎn)圖中標(biāo)記的區(qū)域映射到第一得分圖像.

6)按照式(6)將特征像素值約束為0~255之間的整數(shù).按照式(7)計(jì)算標(biāo)記區(qū)域面積作為光譜特征.

3.2銅浮選泡沫圖像采集及局部光譜特征提取

如圖4所示,在銅粗選首槽泡沫表層上方110 cm處搭建浮選泡沫圖像采集系統(tǒng),系統(tǒng)由光源,工業(yè)攝像機(jī),信號(hào)傳輸裝置構(gòu)成.攝像機(jī)視場(chǎng)范圍為23.84 cm×17.88 cm,在如表1所示入礦條件下,采集泡沫圖像樣本200個(gè),選取包含了明顯黑色水化區(qū)域的典型圖像作為訓(xùn)練圖像,其余圖像作為測(cè)試圖像.同時(shí)采集對(duì)應(yīng)時(shí)刻的銅粗選首槽泡沫樣本,獲得泡沫品位化驗(yàn)值.

針對(duì)訓(xùn)練圖像,按照3.1節(jié)算法步驟1),2)建立MPCA全局模型,即計(jì)算負(fù)載矢量:

pd1=0.575 5 0.579 0.577 5T,

pd2=-0.523 0.117 0.845T.

然后按照步驟3),4)計(jì)算出測(cè)試圖像的得分矢量,選取兩個(gè)主元t1,t2,畫出其得分矢量強(qiáng)度散點(diǎn)圖,如圖5所示,第一得分矢量值為-4~-2,第二得分矢量值為0.2~-0.6所對(duì)應(yīng)的像素為局部區(qū)域特征像素.依據(jù)得分值和特征像素之間的關(guān)系,記錄特征像素值、特征像素個(gè)數(shù)和空間位置.

根據(jù)步驟5)重構(gòu)第一得分圖像,利用得分值和特征像素變量之間的關(guān)系,將得分矢量強(qiáng)度散點(diǎn)圖中對(duì)應(yīng)的局部區(qū)域投影回第一得分圖像,如圖6所示.這一投影過(guò)程需結(jié)合圖5,反復(fù)調(diào)整,直至所標(biāo)記區(qū)域滿意為止.統(tǒng)計(jì)特征像素個(gè)數(shù),并根據(jù)單位像素面積,計(jì)算標(biāo)記區(qū)域的面積SL.

最后,針對(duì)其余圖像,重復(fù)步驟3)至步驟6),計(jì)算黑色水化區(qū)域的大小作為局部光譜特征:

SL=SL1,SL2,…,SL199,SL200.

3.3基于局部光譜特征的銅粗選“病態(tài)”工況識(shí)別

銅粗選過(guò)程是整個(gè)銅浮選流程的第1步,浮選性能好壞直接影響后續(xù)流程的操作和產(chǎn)品質(zhì)量,通常用粗選首槽泡沫品位作為衡量粗選過(guò)程浮選性能的指標(biāo).將本文所提方法應(yīng)用于泡沫圖像樣本,提取局部光譜特征,畫出局部光譜特征與首槽泡沫品位的散點(diǎn)圖,如圖7所示.局部區(qū)域面積為15~28 cm2時(shí)對(duì)應(yīng)的泡沫品位較高.當(dāng)局部區(qū)域面積過(guò)大時(shí)(局部局域面積大于28 cm2),泡沫水化現(xiàn)象嚴(yán)重,泡沫上附著的金屬礦粒少,泡沫品位低;而局部區(qū)域面積過(guò)小時(shí)(局部區(qū)域面積小于15 cm2),泡沫坍塌現(xiàn)象嚴(yán)重,泡沫上附著的金屬礦粒掉入礦漿,泡沫品位也會(huì)降低.因此,由圖7可知,便可以得到銅粗選首槽“病態(tài)”工況所對(duì)應(yīng)的局部光譜特征閾值區(qū)間,識(shí)別出粗選過(guò)程的“病態(tài)”工況.

4工業(yè)應(yīng)用

為了驗(yàn)證本文所提的方法,基于Visual C++和Matlab7.0開(kāi)發(fā)了如圖4所示的銅浮選泡沫圖像監(jiān)控系統(tǒng)應(yīng)用于國(guó)內(nèi)某銅浮選廠粗選流程.該系統(tǒng)能夠提供浮選泡沫視覺(jué)圖像和對(duì)應(yīng)的圖像視覺(jué)特征曲線,實(shí)現(xiàn)了銅浮選粗選首槽病態(tài)工況的識(shí)別,并將其總結(jié)為專家控制規(guī)則,現(xiàn)場(chǎng)工作人員能及時(shí)了解工況,根據(jù)工況的變化調(diào)整操作以穩(wěn)定和提高浮選品位及回收率.2012年1-5月,所開(kāi)發(fā)系統(tǒng)在工業(yè)現(xiàn)場(chǎng)連續(xù)試運(yùn)行5個(gè)月,分析對(duì)比入礦條件基本相同,藥劑制度相同情況下的2010年回收率數(shù)據(jù),如圖8所示,系統(tǒng)投入運(yùn)行前銅回收率平均值為86.48%,標(biāo)準(zhǔn)差0.846 759;投入運(yùn)行后銅回收率平均值為87.23% ,標(biāo)準(zhǔn)差為0.825 57.在一定程度上,對(duì)于穩(wěn)定和提高銅回收率指標(biāo)有幫助.

5結(jié)論

銅粗選工況識(shí)別是銅浮選全流程監(jiān)控的關(guān)鍵.本文描述了銅浮選粗選過(guò)程,分析了影響粗選過(guò)程的主要因素和粗選首槽泡沫圖像黑色水化區(qū)域形成機(jī)理,提出以黑色水化區(qū)域面積作為銅浮選粗選過(guò)程病態(tài)工況識(shí)別的局部圖像特征,并針對(duì)這一特征大小、形狀無(wú)規(guī)則性,提出一種基于MPCA的局部光譜特征提取新方法.該方法無(wú)需考慮原始圖像中的像素空間位置,能很好地捕獲原始圖像的局部光譜特征.所提取的特征與浮選泡沫品位有很強(qiáng)的相關(guān)性,可用于銅浮選粗選過(guò)程病態(tài)工況識(shí)別.但是入礦類型的改變會(huì)引起粗選工況區(qū)間的漂移,用單一的圖像特征會(huì)造成病態(tài)工況區(qū)間的誤識(shí)別.這將是我們下一步要解決的問(wèn)題.

參考文獻(xiàn)

[1]桂衛(wèi)華.礦物浮選泡沫圖像處理與過(guò)程監(jiān)測(cè)技術(shù)[M]. 長(zhǎng)沙:中南大學(xué)出版社,2013:11-17.

GUI Weihua. Mineral flotation froth image processing and process monitoring technology[M].Changsha: Central South University Press, 2013.(In Chinese)

[2]桂衛(wèi)華,陽(yáng)春華,盧明,等.基于機(jī)器視覺(jué)的礦物浮選過(guò)程監(jiān)控技術(shù)研究進(jìn)展[J].自動(dòng)化學(xué)報(bào),2013, 39(11):1879-1887.

GUI Weihua, YANG Chunhua, LU Ming, et al. Machinevisionbased online measuring and controlling technologies for mineral flotation—a review[J]. Acta Automatica Sinica, 2013, 39(11):1879-1887. (In Chinese)

[3]CIT IR C, AKTAS Z, BER BERR. Off line image analysis for froth flotation of coal[J]. Computers & Chemical Engineering, 2004,28(60):625-632.

[4]HATONEN J. Image analysis in mineral flotation[D]. Helsinki, Finland: Helsinki University of Technology, 1999.

[5]ALDRICH C, MAIIAIS C, SHEAN B J, et al. Online monitoring and control of froth flotation systems with machine vision:a review[J]. International Journal of Mineral Processing, 2010,96(4):1-13.

[6]XU C H, GUI W H, YANG C H. Flotation process fault detection using output PDF of bubble size distribution[J]. Minerals Engineering, 2012,26:5-12.

[7]BONIFAZI G, SERRANTI S,VOLPE F,et al.Characterization of flotation froth colour and structure by machine vision[J]. Computers & Geosciences, 2001,27(9):1111-1117.

[8]BONIFAZI G,SERRANTI S,VOLPE F,et al.Flotation froth characterization by closed domain (bubbles) color analysis[C]//4th Int Conf on Quality Control by Artificial Vision,November 10-12, Takamatsu, Japan, 1998:131-137.

[9]BARTOLACCI G,PELLETIER R,TESSIER J.Application of numerical image analysis to process diagnosis and physical parameter measurement in mineral processes —part 1: flotation control based on froth textural characteristic[J]. Minerals Engineering, 2006,19(6/8):734-747.

[10]KAARTINEN J. Data acquisition and analysis system for mineral flotation[D].Finland:Control Engineering Laboratory, Helsinki University of Technology, 2001.

[11]KAARTINEN J, HATONEN J, MIETTUNEN J, et al. Image analysis based control of zinc flotation a multicamera approach[C]//Preprints of the Seventh International Conference on Control, Automation, Robotics and Vision(ICARV 2002), Singapore,2002.

[12]GARCAMUOZ S,GIERER D S.Coating assessment for colored immediate release tablets using multivariate image analysis[J].International Journal of Pharmaceutics,2010,395:104-113.

[13]ESBENSEN K,GELADI P.Strategy of multivariate image analysis[J].Chemometrics and Intelligent Laboratory Systems,1989,7(1/2):67-86.

[14]PARTSMONTALBAN J M,DE JUAN A,F(xiàn)ERRER A. Multivariate image analysis: a review with applications[J]. Chemometrics and Intelligent Laboratory Systems,2011,107(1):1-23.

[15]GELADI P,ISAKSSON H,LINDQVIST L,et al.Principal component analysis of multivariate images[J].Chemometrics and Intelligent Laboratory Systems,1989,5(3):209-220.

[16]YU H,MACGREGOR J F.Multivariate image analysis and regression for prediction of coating and distribution in the production of snack foods[J].Chemometrics and Intelligent Laboratory Systems,2003,67(2):125-144.

[17]LIU J J,MACGREGOR J F.Estimation and monitoring of product aesthetics: application to manufacturing of “engineered stone” countertops[J].Machine Vision and Applications, 2006,16:374-383.

[18]許悟生,謝柯夫.基于像素灰度關(guān)聯(lián)的邊緣檢測(cè)[J].湖南師范大學(xué)自然科學(xué)學(xué)報(bào),2012,35(4):26-30.

XU Wusheng, XIE Kefu. Edge detection based on pixel gray correlation[J].Journal of Natural Science of Hunan Normal University,2012,35(4):26-30.(In Chinese)

[3]CIT IR C, AKTAS Z, BER BERR. Off line image analysis for froth flotation of coal[J]. Computers & Chemical Engineering, 2004,28(60):625-632.

[4]HATONEN J. Image analysis in mineral flotation[D]. Helsinki, Finland: Helsinki University of Technology, 1999.

[5]ALDRICH C, MAIIAIS C, SHEAN B J, et al. Online monitoring and control of froth flotation systems with machine vision:a review[J]. International Journal of Mineral Processing, 2010,96(4):1-13.

[6]XU C H, GUI W H, YANG C H. Flotation process fault detection using output PDF of bubble size distribution[J]. Minerals Engineering, 2012,26:5-12.

[7]BONIFAZI G, SERRANTI S,VOLPE F,et al.Characterization of flotation froth colour and structure by machine vision[J]. Computers & Geosciences, 2001,27(9):1111-1117.

[8]BONIFAZI G,SERRANTI S,VOLPE F,et al.Flotation froth characterization by closed domain (bubbles) color analysis[C]//4th Int Conf on Quality Control by Artificial Vision,November 10-12, Takamatsu, Japan, 1998:131-137.

[9]BARTOLACCI G,PELLETIER R,TESSIER J.Application of numerical image analysis to process diagnosis and physical parameter measurement in mineral processes —part 1: flotation control based on froth textural characteristic[J]. Minerals Engineering, 2006,19(6/8):734-747.

[10]KAARTINEN J. Data acquisition and analysis system for mineral flotation[D].Finland:Control Engineering Laboratory, Helsinki University of Technology, 2001.

[11]KAARTINEN J, HATONEN J, MIETTUNEN J, et al. Image analysis based control of zinc flotation a multicamera approach[C]//Preprints of the Seventh International Conference on Control, Automation, Robotics and Vision(ICARV 2002), Singapore,2002.

[12]GARCAMUOZ S,GIERER D S.Coating assessment for colored immediate release tablets using multivariate image analysis[J].International Journal of Pharmaceutics,2010,395:104-113.

[13]ESBENSEN K,GELADI P.Strategy of multivariate image analysis[J].Chemometrics and Intelligent Laboratory Systems,1989,7(1/2):67-86.

[14]PARTSMONTALBAN J M,DE JUAN A,F(xiàn)ERRER A. Multivariate image analysis: a review with applications[J]. Chemometrics and Intelligent Laboratory Systems,2011,107(1):1-23.

[15]GELADI P,ISAKSSON H,LINDQVIST L,et al.Principal component analysis of multivariate images[J].Chemometrics and Intelligent Laboratory Systems,1989,5(3):209-220.

[16]YU H,MACGREGOR J F.Multivariate image analysis and regression for prediction of coating and distribution in the production of snack foods[J].Chemometrics and Intelligent Laboratory Systems,2003,67(2):125-144.

[17]LIU J J,MACGREGOR J F.Estimation and monitoring of product aesthetics: application to manufacturing of “engineered stone” countertops[J].Machine Vision and Applications, 2006,16:374-383.

[18]許悟生,謝柯夫.基于像素灰度關(guān)聯(lián)的邊緣檢測(cè)[J].湖南師范大學(xué)自然科學(xué)學(xué)報(bào),2012,35(4):26-30.

XU Wusheng, XIE Kefu. Edge detection based on pixel gray correlation[J].Journal of Natural Science of Hunan Normal University,2012,35(4):26-30.(In Chinese)

[3]CIT IR C, AKTAS Z, BER BERR. Off line image analysis for froth flotation of coal[J]. Computers & Chemical Engineering, 2004,28(60):625-632.

[4]HATONEN J. Image analysis in mineral flotation[D]. Helsinki, Finland: Helsinki University of Technology, 1999.

[5]ALDRICH C, MAIIAIS C, SHEAN B J, et al. Online monitoring and control of froth flotation systems with machine vision:a review[J]. International Journal of Mineral Processing, 2010,96(4):1-13.

[6]XU C H, GUI W H, YANG C H. Flotation process fault detection using output PDF of bubble size distribution[J]. Minerals Engineering, 2012,26:5-12.

[7]BONIFAZI G, SERRANTI S,VOLPE F,et al.Characterization of flotation froth colour and structure by machine vision[J]. Computers & Geosciences, 2001,27(9):1111-1117.

[8]BONIFAZI G,SERRANTI S,VOLPE F,et al.Flotation froth characterization by closed domain (bubbles) color analysis[C]//4th Int Conf on Quality Control by Artificial Vision,November 10-12, Takamatsu, Japan, 1998:131-137.

[9]BARTOLACCI G,PELLETIER R,TESSIER J.Application of numerical image analysis to process diagnosis and physical parameter measurement in mineral processes —part 1: flotation control based on froth textural characteristic[J]. Minerals Engineering, 2006,19(6/8):734-747.

[10]KAARTINEN J. Data acquisition and analysis system for mineral flotation[D].Finland:Control Engineering Laboratory, Helsinki University of Technology, 2001.

[11]KAARTINEN J, HATONEN J, MIETTUNEN J, et al. Image analysis based control of zinc flotation a multicamera approach[C]//Preprints of the Seventh International Conference on Control, Automation, Robotics and Vision(ICARV 2002), Singapore,2002.

[12]GARCAMUOZ S,GIERER D S.Coating assessment for colored immediate release tablets using multivariate image analysis[J].International Journal of Pharmaceutics,2010,395:104-113.

[13]ESBENSEN K,GELADI P.Strategy of multivariate image analysis[J].Chemometrics and Intelligent Laboratory Systems,1989,7(1/2):67-86.

[14]PARTSMONTALBAN J M,DE JUAN A,F(xiàn)ERRER A. Multivariate image analysis: a review with applications[J]. Chemometrics and Intelligent Laboratory Systems,2011,107(1):1-23.

[15]GELADI P,ISAKSSON H,LINDQVIST L,et al.Principal component analysis of multivariate images[J].Chemometrics and Intelligent Laboratory Systems,1989,5(3):209-220.

[16]YU H,MACGREGOR J F.Multivariate image analysis and regression for prediction of coating and distribution in the production of snack foods[J].Chemometrics and Intelligent Laboratory Systems,2003,67(2):125-144.

[17]LIU J J,MACGREGOR J F.Estimation and monitoring of product aesthetics: application to manufacturing of “engineered stone” countertops[J].Machine Vision and Applications, 2006,16:374-383.

[18]許悟生,謝柯夫.基于像素灰度關(guān)聯(lián)的邊緣檢測(cè)[J].湖南師范大學(xué)自然科學(xué)學(xué)報(bào),2012,35(4):26-30.

XU Wusheng, XIE Kefu. Edge detection based on pixel gray correlation[J].Journal of Natural Science of Hunan Normal University,2012,35(4):26-30.(In Chinese)

松阳县| 临夏县| 任丘市| 高尔夫| 盐津县| 江口县| 金坛市| 潞西市| 高安市| 荔浦县| 教育| 延寿县| 巨野县| 班玛县| 朝阳区| 定远县| 宝丰县| 麻江县| 固原市| 镶黄旗| 明水县| 墨江| 小金县| 东平县| 胶南市| 湖州市| 平罗县| 龙川县| 保德县| 祁阳县| 苏尼特右旗| 东光县| 始兴县| 化德县| 南乐县| 精河县| 广饶县| 北流市| 东源县| 云浮市| 新郑市|