牛臉特征點檢測的研究與實現(xiàn)
發(fā)布時間：2018-07-24 11:19
【摘要】：牛的面部輪廓是牛臉的重要特征,牛臉特征點的檢測及其形狀分析可以用于牛身份鑒別、咀嚼分析及健康狀況評估等領域。針對真實生產(chǎn)環(huán)境下牛場視頻監(jiān)控圖像中存在的拍攝角度差異大、光照不均勻、牛臉局部有遮擋等問題。本文研究了監(jiān)督式梯度下降算法(SDM),局部二值算法(LBF)和主動外觀模型算法(FAAM)三種算法提取牛臉輪廓信息,為進一步分析牛的面部表情和健康狀況提供了理論基礎。主要研究內(nèi)容和結論如下:(1)牛臉檢測器訓練。基于AdaBoost級聯(lián)分類器原理,結合牛臉的特征,訓練牛臉檢測器。由于牛臉較長,截取牛臉正例圖像大小為15×25像素。負例樣本是與正例樣本尺寸相同的牛臉背景圖像。最終訓練出的牛臉檢測器在600幅單張牛臉圖像中,檢測率達到了93%。(2)牛臉特征點標定研究。根據(jù)特征點選取的規(guī)則,選擇29個點來標記牛臉輪廓,并實現(xiàn)了特征點標定軟件。手動標記600幅牛面部圖像,每幅圖像的特征數(shù)據(jù)保存成文本格式。對所有的訓練集進行對齊處理,對齊后的數(shù)據(jù)集為后續(xù)模型的建立提供數(shù)據(jù)。(3)三種特征點檢測算法在牛臉特征點檢測中的應用。牛臉特征點檢測過程中由于牛臉較長,對初始化算法進行了改進,采用分離式模型對牛臉面部特征點進行初始化。通過實驗分析和比較了三種算法的時間效率和準確性,并采用三種誤差分析方法比較了算法的性能。實驗結果表明,LBF算法,SDM算法以及FAAM算法每幅圖像的平均檢測時間分別為0.39秒,1.48秒,71.34秒。LBF算法,SDM算法以及FAAM算法尺寸歸一化點對點的平均誤差分別為0.0359像素,0.0275像素,0.0269像素,左右眼角歸一化后點對點的歐式距離度量平均誤差分別為0.0245像素,0.0188像素,0.0184像素,均方根誤差分別為0.0323像素,0.0247像素,0.0242像素。實驗結果驗證了牛臉特征點檢測的可行性和實用性,其中FAAM算法獲得的模型精度最高,而LBF算法的計算效率最高。因此在牛臉特征點檢測過程中,根據(jù)實際需求要在準確率和時間效率上做出取舍。
[Abstract]:The facial contour of cattle is an important feature of cattle face. The detection and shape analysis of bull face feature points can be used in identification, chewing analysis and health assessment of cattle. Aiming at the problems of large angle difference, uneven illumination and partial occlusion of cattle face in the real production environment, the video surveillance image of cattle farm is different. In this paper, the supervised gradient descent algorithm (SDM),) local binary algorithm (LBF) and the active appearance model algorithm (FAAM) are studied to extract bovine face contour information, which provides a theoretical basis for further analysis of cattle facial expression and health status. The main contents and conclusions are as follows: (1) Bovine face detector training. Based on the principle of AdaBoost cascade classifier and the features of bovine face, the bovine face detector is trained. Because the cattle face is longer, the sample image size is 15 脳 25 pixels. The negative sample is a cattle face background image with the same size as the positive sample. Finally, in 600 single bovine face images, the trained bovine face detector has a detection rate of 93%. (2) study on the calibration of bull face feature points. According to the rule of feature point selection, 29 points are selected to mark the bull face contour, and the feature point calibration software is implemented. Manually mark 600 cattle facial images, each image's feature data saved as text format. All training sets are aligned and the aligned data sets provide data for the subsequent modeling. (3) the application of three feature point detection algorithms in cattle face feature point detection. In the process of cattle face feature point detection, the initialization algorithm is improved because of the long cow face, and the split model is used to initialize the cattle face feature point. The time efficiency and accuracy of the three algorithms are analyzed and compared experimentally, and the performance of the three algorithms is compared by using the three error analysis methods. The experimental results show that the average detection time of LBF algorithm and FAAM algorithm is 0.39 seconds, 1.48 seconds, 71.34 seconds, respectively, and the average error of normalized point-to-point of FAAM algorithm is 0.0359 pixels / 0.0275 pixels / 0.0269 pixels, respectively. The average error of Euclidean distance measurement after normalization of left and right eye corners is 0.0245 pixel / 0.0188 pixel / 0.0184 pixel, and the root mean square error is 0.0323 pixel / 0.0247 pixel / 0.0242 pixel respectively. The experimental results verify the feasibility and practicability of the bull face feature point detection. The FAAM algorithm has the highest model accuracy and the LBF algorithm has the highest computational efficiency. Therefore, in the process of bull face feature point detection, we should make a choice between accuracy and time efficiency according to actual demand.
【學位授予單位】：西北農(nóng)林科技大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
本文編號：2141213
[Abstract]:The facial contour of cattle is an important feature of cattle face. The detection and shape analysis of bull face feature points can be used in identification, chewing analysis and health assessment of cattle. Aiming at the problems of large angle difference, uneven illumination and partial occlusion of cattle face in the real production environment, the video surveillance image of cattle farm is different. In this paper, the supervised gradient descent algorithm (SDM),) local binary algorithm (LBF) and the active appearance model algorithm (FAAM) are studied to extract bovine face contour information, which provides a theoretical basis for further analysis of cattle facial expression and health status. The main contents and conclusions are as follows: (1) Bovine face detector training. Based on the principle of AdaBoost cascade classifier and the features of bovine face, the bovine face detector is trained. Because the cattle face is longer, the sample image size is 15 脳 25 pixels. The negative sample is a cattle face background image with the same size as the positive sample. Finally, in 600 single bovine face images, the trained bovine face detector has a detection rate of 93%. (2) study on the calibration of bull face feature points. According to the rule of feature point selection, 29 points are selected to mark the bull face contour, and the feature point calibration software is implemented. Manually mark 600 cattle facial images, each image's feature data saved as text format. All training sets are aligned and the aligned data sets provide data for the subsequent modeling. (3) the application of three feature point detection algorithms in cattle face feature point detection. In the process of cattle face feature point detection, the initialization algorithm is improved because of the long cow face, and the split model is used to initialize the cattle face feature point. The time efficiency and accuracy of the three algorithms are analyzed and compared experimentally, and the performance of the three algorithms is compared by using the three error analysis methods. The experimental results show that the average detection time of LBF algorithm and FAAM algorithm is 0.39 seconds, 1.48 seconds, 71.34 seconds, respectively, and the average error of normalized point-to-point of FAAM algorithm is 0.0359 pixels / 0.0275 pixels / 0.0269 pixels, respectively. The average error of Euclidean distance measurement after normalization of left and right eye corners is 0.0245 pixel / 0.0188 pixel / 0.0184 pixel, and the root mean square error is 0.0323 pixel / 0.0247 pixel / 0.0242 pixel respectively. The experimental results verify the feasibility and practicability of the bull face feature point detection. The FAAM algorithm has the highest model accuracy and the LBF algorithm has the highest computational efficiency. Therefore, in the process of bull face feature point detection, we should make a choice between accuracy and time efficiency according to actual demand.
【學位授予單位】：西北農(nóng)林科技大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
【參考文獻】
相關期刊論文 前10條
1 李志剛;賈策;王曉聞;劉強;董常生;;牛肉質構特性的近紅外光譜無損檢測[J];農(nóng)業(yè)工程學報;2016年16期
2 何東健;劉冬;趙凱旋;;精準畜牧業(yè)中動物信息智能感知與行為檢測研究進展[J];農(nóng)業(yè)機械學報;2016年05期
3 關文強;許立興;劉敬斌;劉斌;張德權;趙菲;荊紅彭;;精準冰溫對鮮牛肉貯藏品質的影響[J];制冷學報;2015年04期
4 任超;馮勇建;;EmguCV圖像處理庫在WPF中的應用[J];計算機應用與軟件;2013年05期
5 時華良;李維國;;基于局部與全局擬合的活動輪廓模型[J];計算機工程;2012年18期
6 欒汝朋;孟慶翔;張峻峰;趙金石;任麗萍;周振明;;牛肉產(chǎn)業(yè)鏈全程質量安全追溯體系的建立與應用[J];中國農(nóng)學通報;2012年06期
7 陳長喜;張宏福;王兆毅;王乙丁;;畜禽健康養(yǎng)殖預警體系研究與應用[J];農(nóng)業(yè)工程學報;2010年11期
8 王麗婷;丁曉青;方馳;;基于隨機森林的人臉關鍵點精確定位方法[J];清華大學學報(自然科學版);2009年04期
9 郭立力;趙春江;;十折交叉檢驗的支持向量機參數(shù)優(yōu)化算法[J];計算機工程與應用;2009年08期
10 唐徙文;曾義;;人臉檢測級聯(lián)分類器快速訓練算法[J];計算機仿真;2007年12期
相關碩士學位論文 前4條
1 黃為慶;基于超聲圖像分析與機器視覺的奶牛乳腺體積的測量[D];天津科技大學;2012年
2 呂寶華;人臉特征定位方法研究[D];西北工業(yè)大學;2007年
3 李華明;基于中國人面貌形態(tài)學特征的人臉姿態(tài)估計方法研究[D];西北大學;2005年
4 胥斌;奶牛疾病診斷遺傳神經(jīng)網(wǎng)絡模型研究[D];重慶大學;2004年
，本文編號：2141213
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2141213.html
最近更新
教材專著
