山东农业科学
山東農業科學
산동농업과학
SHANGDONG AGRICULTURAL SCIENCES
2015年
8期
116-118
,共3页
水果%分类%主成分分析%外形相似%自动化识别
水果%分類%主成分分析%外形相似%自動化識彆
수과%분류%주성분분석%외형상사%자동화식별
Fruit%Classification%Principal component analysis%Shape similarity%Automatic recognition
水果分类在超市导购中有较为重要的应用价值，应用自动化识别技术能够实现大量水果的高效分类。主成分分析可以从多元事物中解析出主要影响因素，从而利用一个或几个较好的综合指标来概括信息。本研究采用基于主成分分析的识别分类技术对10种外形相似的水果进行预处理、训练和识别，得到了较好的识别效果，各种水果的平均识别率达到93％以上，基本能够满足实际应用。
水果分類在超市導購中有較為重要的應用價值，應用自動化識彆技術能夠實現大量水果的高效分類。主成分分析可以從多元事物中解析齣主要影響因素，從而利用一箇或幾箇較好的綜閤指標來概括信息。本研究採用基于主成分分析的識彆分類技術對10種外形相似的水果進行預處理、訓練和識彆，得到瞭較好的識彆效果，各種水果的平均識彆率達到93％以上，基本能夠滿足實際應用。
수과분류재초시도구중유교위중요적응용개치，응용자동화식별기술능구실현대량수과적고효분류。주성분분석가이종다원사물중해석출주요영향인소，종이이용일개혹궤개교호적종합지표래개괄신식。본연구채용기우주성분분석적식별분류기술대10충외형상사적수과진행예처리、훈련화식별，득도료교호적식별효과，각충수과적평균식별솔체도93％이상，기본능구만족실제응용。
Fruit classification is important for supermarket shopping guiding,which can be achieved effi-ciently by automatic recognition technology.The principal component analysis can separate out the main influ-encing factors from multiple things,and then use one or several better comprehensive indexes to summarize in-formation.In this paper,10 kinds of shape similar fruits were pretreated,trained and recognized by recogni-tion and classification technologies based on the principal component analysis,and better recognition effects were obtained.The average recognition rate of various kinds of fruits were more than 93%,which indicated that this method could meet the actual application.
