本文選題：完全局部二值模式(CLBP)　切入點(diǎn)：有判別力的完全局部二值模式(disCLBP)　出處：《計(jì)算機(jī)工程與應(yīng)用》2017年04期 　論文類(lèi)型：期刊論文

【摘要】：針對(duì)完全局部二值模式(CLBP)存在直方圖維數(shù)過(guò)高和特征冗余,會(huì)導(dǎo)致識(shí)別速度降低和識(shí)別率低的問(wèn)題,提出基于有判別力的完全局部二值模式(Discriminative completed LBP,dis CLBP)的人臉表情識(shí)別算法。首先,對(duì)人臉表情圖像進(jìn)行預(yù)處理獲得表情子區(qū)域;然后提取表情子區(qū)域和整幅圖像的dis CLBP特征,針對(duì)不同的表情篩選出不同的表情特征,再將篩選出的表情子區(qū)域特征直方圖融合;最后用最近鄰分類(lèi)器進(jìn)行分類(lèi)識(shí)別。該算法在CK人臉表情庫(kù)上進(jìn)行實(shí)驗(yàn)的平均識(shí)別率為97.3%。
[Abstract]:In view of the problem of high histogram dimension and feature redundancy, the problem of low recognition speed and low recognition rate can be caused by the completely local binary mode CLBP. A face expression recognition algorithm based on discriminative completed discriminative completed is proposed. Firstly, the facial expression sub-region is obtained by preprocessing the facial expression image, and then the dis CLBP feature of the expression sub-region and the whole image is extracted. According to different facial expressions, different facial features are selected, and then the histogram of the selected facial expression sub-regions is fused. Finally, the nearest neighbor classifier is used to classify and recognize. The average recognition rate of the algorithm in the CK facial expression database is 97.3%.
【作者單位】： 江南大學(xué)物聯(lián)網(wǎng)工程學(xué)院智能系統(tǒng)與網(wǎng)絡(luò)計(jì)算研究所;
【基金】：國(guó)家自然科學(xué)基金(No.61202312,No.61170121) 教育部留學(xué)回國(guó)人員科研啟動(dòng)基金項(xiàng)目
【分類(lèi)號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 孫蔚;王波;;人臉表情識(shí)別綜述[J];電腦知識(shí)與技術(shù);2012年01期

2 楊梅娟;;人臉表情識(shí)別綜述[J];甘肅科技;2006年04期

3 劉曉e，

本文編號(hào)：1645480