谷物外觀品質(zhì)檢測方法的研究
[Abstract]:The yield and quality of grain have great influence on people's life. At present, most of the grain detection experiments remain at the stage of artificial naked eye observation. Applying image processing to grain appearance classification can greatly improve the efficiency of grain screening. Compared with naked eye observation, the use of computer to detect grain appearance automatically has the advantages of high speed, high efficiency and good reusability. It is very worthy of research and development in the field of agricultural product classification. It is of high theoretical value and practical significance to analyze the appearance parameters of grain by processing the grain image and to evaluate the grain classification. Some characteristic parameters, such as the length, width and pixels occupied in the image, can be obtained from the image, and these parameters can be used to judge the grain shape and integrity. The grain appearance analysis algorithm studied in this paper is universal and can be applied to rice, mung bean, brown rice and oats. The main contents and innovations of this paper are as follows: (1) A complete system is designed, which includes the grain appearance collection system and the grain image analysis system. This system can be used instead of human observation to achieve the purpose of grain classification. (2) in the detection of a batch of cereals, there may be superposition and coincidence of grain, resulting in errors in grain parameter statistics. The watershed segmentation algorithm can be used to deal with this situation effectively. The algorithm can cut the grain edge which has not complex adhesion to achieve grain segmentation. However, the algorithm also has some shortcomings, such as excessive segmentation, often dividing a grain region into two blocks. By improving the algorithm in this paper, this situation can be avoided effectively.
【學(xué)位授予單位】:北方工業(yè)大學(xué)
【學(xué)位級別】:碩士
【學(xué)位授予年份】:2017
【分類號】:S126;TP391.41
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 趙巧敏;;機(jī)器視覺行業(yè)投資分析報告[J];機(jī)器人技術(shù)與應(yīng)用;2015年05期
2 孫翠霞;方華;胡波;;基于灰度圖像的大米堊白檢測算法研究[J];廣西工學(xué)院學(xué)報(自然科學(xué)版);2010年02期
3 王科俊;熊新炎;任楨;;高效均值濾波算法[J];計算機(jī)應(yīng)用研究;2010年02期
4 石禮娟;文友先;牟同敏;徐俊英;;谷物檢測中機(jī)器視覺技術(shù)的應(yīng)用進(jìn)展[J];湖北農(nóng)業(yè)科學(xué);2009年06期
5 王斌;劉興龍;劉永福;張立國;;機(jī)器視覺技術(shù)在農(nóng)業(yè)應(yīng)用中的研究[J];農(nóng)機(jī)化研究;2008年09期
6 陳建偉;劉瓔瑛;;基于機(jī)器視覺技術(shù)的大米品質(zhì)檢測綜述[J];糧食與食品工業(yè);2008年03期
7 高麗;楊樹元;李海強(qiáng);;一種基于標(biāo)記的分水嶺圖像分割新算法[J];中國圖象圖形學(xué)報;2007年06期
8 陳鯉江;劉鐵根;朱均超;鄧集杰;劉德瑞;盧萍;王磊;;基于飽和度的異色米粒檢測方法[J];光電子.激光;2007年01期
9 尚艷芬,侯彩云,常國華,周小豐;整精米自動識別方法的研究[J];中國水稻科學(xué);2004年05期
10 高浩軍,杜宇人;中值濾波在圖像處理中的應(yīng)用[J];電子工程師;2004年08期
相關(guān)博士學(xué)位論文 前1條
1 凌云;基于機(jī)器視覺的谷物外觀品質(zhì)檢測技術(shù)研究[D];中國農(nóng)業(yè)大學(xué);2004年
相關(guān)碩士學(xué)位論文 前2條
1 胡明明;基于彩色線陣CCD大米色選算法實(shí)驗(yàn)研究[D];哈爾濱工程大學(xué);2007年
2 張強(qiáng);基于機(jī)器視覺的產(chǎn)品檢測技術(shù)研究[D];中國人民解放軍信息工程大學(xué);2005年
,本文編號:2423774
本文鏈接:http://sikaile.net/kejilunwen/nykj/2423774.html