本文選題：手勢識別　切入點：高斯膚色模型　出處：《計算機(jī)工程與應(yīng)用》2017年06期

【摘要】：在手勢識別研究過程中,人工選取特征難以適應(yīng)手勢的多變性。提出了一種結(jié)合膚色模型和卷積神經(jīng)網(wǎng)絡(luò)的手勢識別方法,對采集的不同背景下的手勢圖像,首先用膚色高斯模型分割出手勢區(qū)域,然后采用卷積神經(jīng)網(wǎng)絡(luò)建立手勢的識別模型,該模型融合了手勢特征提取和分類過程,模擬視覺傳導(dǎo)和認(rèn)知,有效避免了人工特征提取的主觀性和局限性。識別模型以手勢區(qū)域的灰度信息為輸入,同時利用權(quán)值共享和池化等技術(shù)減少網(wǎng)絡(luò)權(quán)值個數(shù),降低了模型的復(fù)雜度。實驗結(jié)果表明,卷積神經(jīng)網(wǎng)絡(luò)(CNN)方法能夠有效進(jìn)行特征學(xué)習(xí),在不同數(shù)據(jù)集下對手勢的平均識別率都達(dá)到95%以上,與傳統(tǒng)方法進(jìn)行對比實驗,表明該方法具有較高的識別率和實時性。
[Abstract]:In the process of gesture recognition, artificial feature selection is difficult to adapt to the variety of gestures. A combination of skin color model and convolutional neural network method of gesture recognition, gesture image acquisition under the background of different, firstly divided the gesture area with color Gauss model, then the model recognition gesture convolutional neural network. The model combines the feature extraction and classification process, simulation of visual conduction and cognition, effectively avoids the subjectivity and limitation of artificial feature extraction. Recognition model by gray information of the gesture area as input, using weight sharing and pooling technology to reduce the number of network weights, reduce the complexity of model experiment. The results show that the convolution neural network (CNN) method can effective learning characteristics in different data sets, the average for the gesture recognition rate of over 95%, and the traditional party The comparison experiment shows that the method has high recognition rate and real time.

【作者單位】： 昆明理工大學(xué)信息工程與自動化學(xué)院;
【基金】：國家自然科學(xué)基金(No.61263017) 云南省自然科學(xué)基金(No.2011FZ060,No.KKSY201303120)
【分類號】：TP391.41;TP183

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 ;新型手勢識別技術(shù)可隔著口袋操作手機(jī)[J];電腦編程技巧與維護(hù);2014年07期

2 任海兵,祝遠(yuǎn)新,徐光，

本文編號：1669099