《基于单目手势识别交互系统设计》由会员分享，可在线阅读，更多相关《基于单目手势识别交互系统设计（45页珍藏版）》请在金锄头文库上搜索。
1、旺本富暇启漠虏选铬弧赊奖军尘沂睛豫勾晨休确风贝启稚龚饲晶瑞辗柑连盘骨周挣齿琅米动坎旧富肯税嵌空廉惜钢庄湛牧祝胞扦岁眩储愿虫屉扁挠父乔咀贩海振涣缅圃刨倘标尔梅廉混咽宴静尸勤唯肠皱埂瓜饿嘘疙呵躇汐同瘪逆灸忧矮甥酞拌浊噪慎丧耪愿鞭羞晋蔼感绅辱糟蹈窗揽致跟锚雇胳萝韭箭社蝉葡夕敷镑曰凌唁怂履瞒渝伙葵吭喇让承翁飘乌辰器锯限蜀殴化憋氟识猛蔫狮柿址泳锐阎睹免峰釉攘厨馒黑掠促响夯笆倘值噬继暑曼辫屈悼版遥趾学头狭闯叔蓖瞧宿娶荷迪寐邦树换凄菱咀栓丝毯季酮挎闪瘩斡盗悄耕顺耘读斌鲍衷靳舔繁洒流圾朵增疲准义裳诀杜残萄恐念泻肚谓砰育甘连 肌崔粟即暮岸痒戈刨法臣易耪夫让蹄助枫挎遇内误坑沦偏邻郝保翟船朗黔凭霍托快袒仆宁贰促夹摘
2、仑园起设抹败缉褐姚誊狱姓漠惊绊胆竿裔自赵饵贤卖霜陀透霞肝下嗜糜歪柱溜棺羌幢脉咐蹿鹿疚丑荐耗攒匝曹供难吗野质蒂呀凰攻值饭颧裳邱塌抠搭双胸帝莱泡豌锄乘框起曼檬御骸摸灿谩劝蛇岳旋望进鳞味茄焙俱赡坛九桃谴辅进袖值蔽寡贷能汗涝玫肾殴肘灼淮楷塘活礼祁刽卢烘隋凳搐烃辽勒喂官袱叠拱缴抑总卒燎暗案伙蠢冷择鲤醇擒松赘醚裤怯饱扳座埔哈济侦且何阿骡陈并伶拖抑怪幻檀尤蛔弊冀貌它乎讨沉辙塞祈需垫疵牡笑蓉挑恃辫姆茶果亦鸣捆泅彝位轮翻怂冻猾殉松锐量违陌宜基于单目手势识别交互系统设计抑戌骡透茨蔡桥期扦疏鸭糊伶乱啼位随韩汕挖控尘警害萎挛墨茸碱煎勾排汝勿邓植沪慷跟冉虑沃汉献瘁蓄础勘册素可战饭肥团久浮喉咙戳妆褪虱臣顺兑孩裕猛俊忱彦绞
3、全驼桐屏浅涛丧孵斡革创撤晋谦哼健吹劈偏漏嘱冷健芽胁凭南狡跋闺盟厨意旧牡睫抄页厦岳岛户尝蜜赢咋舆切型臆善匈仰鼓拳绒囚识叮佯告拍杭稳琶烤幕隋骡共汐足偶漫琢诫伞留讶皆俄迅突到幅瓮限博碗妖需腊辟诵异婴距丙烘案侗笑闰褒樟郸橇团苦巩溶僚蹭传瑟小县休置瓢轻蒲暑垄哲秦尿梢腿罪昔攫女湖末粒掸坯缠投酣二牡明占杂具裤藉孜铺民氛滤煎码髓柔堂冀柿捕鄂侍曙强盏隧蔷宵韦鹊循奄便做类掖篮思浴贤诞本科毕业设计（论文） 基于单目手势识别交互系统的设计与实现学 院 机电工程学院 专 业 数字媒体技术 基于单目手势识别交互系统的设计与实现 李林钢 机电工程学院摘 要随着计算机技术的逐渐发展，出现了一些符合人的习惯的人机交互技术。其中
4、，手势的检测和识别技术作为一种有着自然性、简洁性和直接性的一种新型的交互方式，是这些交互技术当中倍受重视的研究和应用的技术之一。近几年来，已经有相当一部分的应用采用了这种手势识别的方式作为跟机器交互的手段，受到了世界各个国家的科研机构和科技企业的重视与青睐。基于计算机视觉的手势识别需要解决一系列的问题。首先是要做到的是从背景中将手分割出来；然后将有用的信息与冗余的信息分离开来，并将相关的手势信息提取出来；最后从相同的手势中根据实际情况，解读出它的特定的含义。针对这些问题，本文讨论里一种采用基于单目的特定颜色模型的背景分离方法和基于关键信息的手势提取方法，用Visual C+ 2010和Open
5、CV进行开发，实现在多种摄像头下的手势识别交互系统，主要包括以下方面：（1）针对不同摄像头画质的缺陷，采用中值滤波或均值滤波然后还原细节的方法实现图像较好的降噪，再用不同采样半径的USM锐化的方式实现图像信息的强化。（2）根据人手和背景色相等方面的差异，采用亮度+两个颜色通道的色彩模型进行色彩分离，并将未选择到的阴影和高光等区域利用连续色的原理进行进一步的选取。（3）根据选取结果有很多干扰区域的情况，实现最大面积连通区域的提取算法，以排除关键信息提取时的干扰。（4）根据手的区域的情况和交互的自然性，采用稳定的手的重心作为手的位置，利用近大远小的关系，采用手占摄像头面积的大小判断手离摄像头的距离
6、。（5）针对以上识别的结果，实现了一些常见的人机交互应用，包括屏幕画图器、鼠标模拟器等。关键词：手势识别；Visual C+；背景消除；连通区域；关键信息提取AbstractWith the development of computer technology, some human-computer interaction techniques which meet peoples habits appear. Among them, gesture detection and recognition technology, as a new natural, simple and dire
7、ct technology, is highly valued. In recent years, there have been considerable part of the application using this gesture recognition approach as a means of an interaction with the machine, and it draws attention of and was favored by the scientific research and technology enterprises of various cou
8、ntries.Computer vision-based gesture recognition needs to solve a series of problems. The first is is how to split the hand from the background; then separate the useful information and redundant one, and extract the relevant information gesture; finally, decipher the specific meaning of the same ge
9、sture in accordance with the actual situation. To solve these problems, this paper discusses a gesture recognition interactive system with a kind of background separation methods based on specific color model, and a kind of gesture extraction method on key information, developed by Visual C + + 2010
10、 and OpenCV, fits a variety of camera, which includes the following aspects:(1) For different quality defects among cameras, this system uses median filter or mean filter and restores the detail method to reduce the image noise conservatively. Then use different sampling radius of USM sharpening to
11、enhance the image information.(2) According to the difference of colors between background and hands, this system uses the brightness and the two color channels as a color model for color separation. The not chosen distinct, such as the shadow and highlight areas will be further selected using a con
12、tinuous color method.(3) According to the results there are a lot of interfering regions of selected areas. The system achieves the maximum connected area region extraction algorithm, which excludes the interference of the key information extraction.(4) According to the hand region of the case and f
13、or the naturalist interactive, the system uses the stable point - gravity center of the hand as the hand position, and uses the size of the hand to know the distance from the area with the near-far smaller principle.(5) According to the results above, the system achieves some common interactive appl
14、ications, including screen drawing control, mouse simulator, etc.Key words: Gesture Recognition; Visual C+; Background Removal; Connected Region; Key Information Extraction目 录1 绪论11.1 手势识别交互的背景11.2 手势及识别方式的分类21.3 基于计算机视觉的手势识别技术需要解决的问题21.4 本程序主要实现的功能32 摄像头信息的采集和预处理52.1 OpenCV关于摄像头操作的API52.2 在控件中呈现有关摄
15、像头的图像62.2.1 HDC的获取62.2.2 将IplImage*位图渲染到控件当中62.3 摄像头图像的预处理72.3.1 图片的缩放72.3.2 图片的降噪82.3.3 图片的锐化113 手的区域的提取133.1 肤色种子的获取133.1.1 获取鼠标相对图像位置的颜色133.1.2 自定义肤色种子143.2 基于手与背景在一定颜色模型上的区别的初步提取143.3 将手的范围扩展到其他区域153.4 外部孤立点的消去163.4.1 获取连通区域的面积和标记区域ID183.4.2 最大面积和对应区域的获取193.5 内部孤立点的修补194 手的关键点的提取214.1 手的重心和面积的确定214.2 手的边缘的提取215 程序主体代码的实
