本文選題：手勢(shì)識(shí)別 + 二值化網(wǎng)絡(luò)　； 參考：《湖南工業(yè)大學(xué)》2017年碩士論文

【摘要】：手勢(shì)識(shí)別是人機(jī)交互一個(gè)重要的研究課題,由于對(duì)它的研究特別是對(duì)基于視覺(jué)的手勢(shì)識(shí)別的研究順應(yīng)了近年來(lái)人機(jī)交互從機(jī)器友好型向著人類(lèi)友好型發(fā)展的趨勢(shì),因此有著極大的科研和應(yīng)用前景。然而在實(shí)際使用中,人手形態(tài)的多樣性,及其所處環(huán)境的背景、光線的變化等因素都給計(jì)算機(jī)從圖像信息中正確識(shí)別的手勢(shì)帶來(lái)了極大挑戰(zhàn)。針對(duì)這些問(wèn)題,本文分別對(duì)手勢(shì)識(shí)別、手勢(shì)檢測(cè)等問(wèn)題進(jìn)行了研究,主要工作如下:(1)針對(duì)手勢(shì)檢測(cè)問(wèn)題,結(jié)合視頻中的多種檢測(cè)算法提出了一種多策略融合的手勢(shì)檢測(cè)方法。為了解決復(fù)雜背景下手勢(shì)檢測(cè)出現(xiàn)的誤檢問(wèn)題,研究了膚色檢測(cè)、vibe運(yùn)動(dòng)檢測(cè)等算法的原理,根據(jù)各種算法在檢測(cè)中的特點(diǎn)在將膚色、運(yùn)動(dòng)和人臉信息進(jìn)行融合,提升了在復(fù)雜背景下手勢(shì)檢測(cè)的魯棒性。特別的針對(duì)手勢(shì)與類(lèi)膚色背景重合時(shí)的檢測(cè)容易失效問(wèn)題,對(duì)融合策略進(jìn)行了自適應(yīng)閾值的改進(jìn),改善了算法在該種情況下的檢測(cè)率。(2)針對(duì)手勢(shì)分類(lèi)識(shí)別問(wèn)題,在普通的深度學(xué)習(xí)卷積神經(jīng)網(wǎng)絡(luò)手勢(shì)識(shí)別方法的基礎(chǔ)上提出了一種基于二值卷積神經(jīng)網(wǎng)絡(luò)的手勢(shì)識(shí)別方法。該方法將網(wǎng)絡(luò)的二值化方法與卷積神經(jīng)網(wǎng)絡(luò)手勢(shì)識(shí)別方法相結(jié)合,使用二值化后的權(quán)值提替代網(wǎng)絡(luò)中原本的高精度權(quán)值,減少了算法計(jì)算量及內(nèi)存占用。通過(guò)實(shí)驗(yàn)證明,算法在取得了足夠的準(zhǔn)確性和魯棒性的基礎(chǔ)上,計(jì)算效率和在實(shí)時(shí)系統(tǒng)中的適用性得到了提升。(3)設(shè)計(jì)和實(shí)現(xiàn)了一個(gè)手勢(shì)識(shí)別系統(tǒng),展示了手勢(shì)識(shí)別在人機(jī)交互系統(tǒng)中的應(yīng)用。從系統(tǒng)的需求和功能模塊的設(shè)計(jì),到結(jié)合了前面提出的兩種方法的復(fù)雜背景下的手勢(shì)識(shí)別功能模塊及手勢(shì)訓(xùn)練模塊的實(shí)現(xiàn),再到將成熟的人臉識(shí)別檢測(cè)方案集成的協(xié)同認(rèn)證模塊的實(shí)現(xiàn),本文詳細(xì)地介紹了系統(tǒng)設(shè)計(jì)實(shí)現(xiàn)的各個(gè)細(xì)節(jié)。最后通過(guò)實(shí)驗(yàn)展示了系統(tǒng)用于識(shí)別數(shù)字和解鎖的功能和特性。
[Abstract]:Gesture recognition is an important research topic in human-computer interaction. Because of its research, especially the research on visual gesture recognition, it conforms to the trend of human-computer interaction from machine-friendly to human-friendly in recent years. Therefore, there is a great prospect of scientific research and application. However, in practical use, the diversity of the human hand shape, the background of the environment and the change of light bring great challenges to the correct recognition of hand gestures from the image information by the computer. Aiming at these problems, this paper studies the problems of gesture recognition and gesture detection respectively. The main work is as follows: (1) aiming at the problem of hand gesture detection, a multi-strategy fusion method for gesture detection is proposed in combination with a variety of video detection algorithms. In order to solve the problem of false detection in hand gesture detection in complex background, the principle of skin color detection and motion detection is studied. According to the characteristics of the algorithms in detection, the color, motion and face information are fused. The robustness of hand gesture detection in complex background is improved. Especially, aiming at the problem that the detection is easy to fail when the gesture and the similar skin color background coincide, the adaptive threshold of the fusion strategy is improved, and the detection rate of the algorithm in this case is improved. On the basis of common deep learning convolution neural network gesture recognition method, a gesture recognition method based on binary convolution neural network is proposed. This method combines the binarization method of the network with the hand gesture recognition method of convolution neural network, and uses the binary weight value to replace the original high precision weight value in the network, thus reducing the computational complexity and memory footprint of the algorithm. It is proved by experiments that the algorithm has achieved enough accuracy and robustness, and the computational efficiency and applicability in real-time system have been improved. (3) A hand gesture recognition system is designed and implemented. The application of gesture recognition in human-computer interaction system is demonstrated. From the design of the system requirements and function modules to the implementation of the hand gesture recognition function module and the gesture training module under the complex background of the two methods mentioned above, Then to the implementation of the collaborative authentication module which integrates the mature face detection scheme, this paper introduces the details of the system design and implementation in detail. Finally, the functions and characteristics of the system for identifying numbers and unlocking are demonstrated through experiments.
【學(xué)位授予單位】：湖南工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 程文博;張?jiān)?周華民;崔樹(shù)標(biāo);;基于卷積神經(jīng)網(wǎng)絡(luò)的注塑制品短射缺陷識(shí)別[J];塑料工業(yè);2015年07期

2 趙凱旋;何東健;;基于卷積神經(jīng)網(wǎng)絡(luò)的奶牛個(gè)體身份識(shí)別方法[J];農(nóng)業(yè)工程學(xué)報(bào);2015年05期

3 譚文學(xué);趙春江;吳華瑞;高榮華;;基于彈性動(dòng)量深度學(xué)習(xí)神經(jīng)網(wǎng)絡(luò)的果體病理圖像識(shí)別[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2015年01期

4 余凱;賈磊;陳雨強(qiáng);徐偉;;深度學(xué)習(xí)的昨天、今天和明天[J];計(jì)算機(jī)研究與發(fā)展;2013年09期

5 馮志全;蔣彥;;手勢(shì)識(shí)別研究綜述[J];濟(jì)南大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年04期

6 翁漢良;戰(zhàn)蔭偉;;基于視覺(jué)的多特征手勢(shì)識(shí)別[J];計(jì)算機(jī)工程與科學(xué);2012年02期

7 安濤;彭進(jìn)業(yè);吳靜;;基于Haar小波分解的實(shí)時(shí)手勢(shì)識(shí)別[J];計(jì)算機(jī)工程;2011年24期

8 任_g;顧成成;;基于HOG特征和SVM的手勢(shì)識(shí)別[J];科技通報(bào);2011年02期

9 吳江琴;高文;陳熙霖;;基于數(shù)據(jù)手套輸入的漢語(yǔ)手指字母的識(shí)別[J];模式識(shí)別與人工智能;1999年01期

相關(guān)博士學(xué)位論文 前1條

1 沙亮;基于無(wú)標(biāo)記全手勢(shì)視覺(jué)的人機(jī)交互技術(shù)[D];清華大學(xué);2010年

，

本文編號(hào)：1906226