【摘要】：為加快畜牧業(yè)現(xiàn)代化程度,克服傳統(tǒng)方法中奶牛個(gè)體識(shí)別正確率低的缺陷,針對(duì)奶牛個(gè)體紋理特征,對(duì)傳統(tǒng)KPCA(核主成分分析)方法從降低協(xié)方差矩陣維數(shù)和引入類別信息兩個(gè)角度進(jìn)行改進(jìn),并與小波變換進(jìn)行結(jié)合,應(yīng)用于奶牛個(gè)體識(shí)別領(lǐng)域。首先對(duì)歸一化后的奶牛圖像進(jìn)行一層小波分解得到4個(gè)分量子圖,然后對(duì)各子圖利用改進(jìn)的KPCA進(jìn)行特征提取并引入加權(quán)策略融合,最后構(gòu)造出多類SVM分類器進(jìn)行學(xué)習(xí)分類。將預(yù)先采集的20頭奶牛個(gè)體的視頻數(shù)據(jù)轉(zhuǎn)化成圖片序列并選取20 000張組成實(shí)驗(yàn)數(shù)據(jù)集,通過多組對(duì)比實(shí)驗(yàn)對(duì)小波融合系數(shù)、融合向量組數(shù)、特征維數(shù)三個(gè)重要參數(shù)進(jìn)行設(shè)定,然后利用不同算法進(jìn)行奶牛個(gè)體識(shí)別實(shí)驗(yàn)。結(jié)果表明,提出方法在識(shí)別正確率達(dá)到96.31%時(shí),僅用了4.20 s,較其他算法具有明顯優(yōu)勢(shì),可以有效地應(yīng)用到奶牛個(gè)體識(shí)別領(lǐng)域,兼具高性能、低成本的優(yōu)勢(shì)。
[Abstract]:In order to speed up the modernization of animal husbandry and overcome the defect of low correct rate of individual identification in traditional methods, this paper aims at the individual texture features of dairy cattle. The traditional KPCA (Kernel Principal component Analysis) method is improved from the aspects of reducing the dimension of covariance matrix and introducing category information. It is combined with wavelet transform and applied to the field of individual identification of dairy cows. Firstly, four sub-quantum graphs are obtained by wavelet decomposition of the normalized dairy cow image. Then, the improved KPCA is used to extract the features and the weighted strategy is introduced to each sub-graph. Finally, a multi-class SVM classifier is constructed for learning classification. The video data of 20 cows were converted into image sequence and 20 000 pieces of experimental data were selected. Three important parameters of wavelet fusion coefficient, fusion vector group number and feature dimension were set by comparison experiments. Then the dairy cow individual recognition experiment is carried out by different algorithms. The results show that when the recognition accuracy reaches 96.31, the proposed method only uses 4.20 s, which has obvious advantages over other algorithms, and can be effectively applied to the field of individual identification of dairy cows, with the advantages of high performance and low cost.
【作者單位】： 河北工業(yè)大學(xué)計(jì)算機(jī)科學(xué)與軟件學(xué)院;河北省大數(shù)據(jù)計(jì)算重點(diǎn)實(shí)驗(yàn)室;
【基金】：天津市科委科技支撐計(jì)劃項(xiàng)目(15ZCZDNC00130)
【分類號(hào)】：S823;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 梁鈺超;馮玉凡;汪斌;;RFID無線射頻識(shí)別技術(shù)在犬個(gè)體識(shí)別中的應(yīng)用研究[J];養(yǎng)犬;2010年04期

2 孫國(guó)鳳;開發(fā)和牛的個(gè)體識(shí)別用基因標(biāo)記[J];生物技術(shù)通報(bào);1995年05期

，

本文編號(hào)：2252857