支持向量機(jī)算法研究及其在目標(biāo)檢測(cè)上的應(yīng)用
發(fā)布時(shí)間：2018-08-22 18:55
【摘要】：機(jī)器學(xué)習(xí)(Machine Learning,ML)是計(jì)算機(jī)科學(xué)的一項(xiàng)重要分支。Arthur Samuel將其定義為無需精確編程而能夠具有學(xué)習(xí)能力的機(jī)器,也就是機(jī)器學(xué)習(xí)在一定程度上賦予了計(jì)算機(jī)一種"思考"能力。機(jī)器學(xué)習(xí)與計(jì)算統(tǒng)計(jì)學(xué)、數(shù)學(xué)優(yōu)化和數(shù)據(jù)挖掘有著密切的關(guān)系,但也有一定的差異。根據(jù)學(xué)習(xí)過程中是否有反饋信息,機(jī)器學(xué)習(xí)可以分為監(jiān)督式學(xué)習(xí)、無監(jiān)督式學(xué)習(xí)和增強(qiáng)學(xué)習(xí)三大類。支持向量機(jī)(SVM)是一種監(jiān)督式學(xué)習(xí)算法,可以用于解決分類、回歸問題等。支持向量機(jī)是通過在特征空間構(gòu)建超平面對(duì)分類或回歸問題進(jìn)行處理,通過核技巧將線性模型擴(kuò)展到非線性情況。支持向量機(jī)是機(jī)器學(xué)習(xí)領(lǐng)域最優(yōu)秀的算法之一,可以用于解決實(shí)際應(yīng)用中的許多問題。支持向量機(jī)在文本和超文本分類、圖像分類、手寫識(shí)別、生物識(shí)別等多個(gè)方面取得廣泛的應(yīng)用。針對(duì)支持向量機(jī)核參數(shù)和其他相關(guān)參數(shù)的設(shè)置通常是基于經(jīng)驗(yàn)的,而參數(shù)的選擇常常關(guān)系到模型最終的性能,本文提出使用粒子群算法和人工蜂群算法對(duì)支持向量機(jī)參數(shù)的選擇進(jìn)行優(yōu)化。相比其他SVM參數(shù)選擇方法,由于群智能優(yōu)化算法具有不要求參數(shù)連續(xù)、能夠跳出局部極值等優(yōu)點(diǎn),因而基于群智能優(yōu)化算法參數(shù)選擇的SVM模型能夠表現(xiàn)出更好的泛化性能。十幾年前,使用機(jī)器對(duì)圖像或視頻中的目標(biāo)識(shí)別和目標(biāo)檢索還是一件不可能實(shí)現(xiàn)的任務(wù)。但是隨著近年來互聯(lián)網(wǎng)的普及,越來越多的圖像出現(xiàn)在互聯(lián)網(wǎng)上,海量的圖像數(shù)據(jù)使得人工圖像處理和識(shí)別變得越來越不可能實(shí)現(xiàn)。研究人員一直致力于計(jì)算機(jī)視覺技術(shù)的研究,使得機(jī)器能夠代替人工完成對(duì)圖像的識(shí)別、分類、檢索等任務(wù)。支持向量機(jī)算法在處理圖像識(shí)別、分類、檢索等多種計(jì)算機(jī)視覺方面的任務(wù)上表現(xiàn)出優(yōu)異的性能。E-SVM(Exemplar-SVM)是近期提出的一種使用單一正樣本與一個(gè)負(fù)樣本集訓(xùn)練出的線性SVM模型。該算法已經(jīng)在目標(biāo)檢測(cè)、基于內(nèi)容的圖像檢索(Content Based Image Retrieval,CBIR)等領(lǐng)域取得了很好的應(yīng)用。該算法針對(duì)每一個(gè)正樣本訓(xùn)練一個(gè)相應(yīng)的線性SVM分類器,最終得到一個(gè)單樣本線性SVM模型的集合。在PASCAL VOC 2007目標(biāo)識(shí)別數(shù)據(jù)集的測(cè)試表明,E-SVM方法能夠取得與當(dāng)前最優(yōu)的目標(biāo)檢測(cè)算法LDPM相匹敵的識(shí)別率。由于E-SVM模型是對(duì)每一個(gè)樣本進(jìn)行訓(xùn)練最后得到多個(gè)特異性較強(qiáng)的檢測(cè)器,本文提出使用K-均值聚類的方法對(duì)E-SVM檢測(cè)器進(jìn)行處理,得到一組具有樣本平均特征的檢測(cè)器,這組檢測(cè)器由于融合了相應(yīng)目標(biāo)的多個(gè)特征,使得檢測(cè)器具有更好的泛化性能;并且聚類后的檢測(cè)器數(shù)目大大降低了,在進(jìn)行目標(biāo)檢測(cè)的時(shí)候,能夠降低識(shí)別時(shí)間,提升檢測(cè)效率。
[Abstract]:Machine learning (ML) is an important branch of computer science. Arthur Samuel defines it as a machine capable of learning without precise programming, that is, machine learning gives the computer a "thinking" ability to a certain extent. Machine learning is closely related to computational statistics, mathematical optimization and data mining, but there are some differences. According to whether there is feedback in the learning process, machine learning can be divided into three categories: supervised learning, unsupervised learning and reinforcement learning. Support Vector Machine (SVM) is a supervised learning algorithm, which can be used to solve classification and regression problems. Support vector machine (SVM) is used to deal with the problem of classification or regression by constructing a superplane in the feature space, and the linear model is extended to nonlinear cases by kernel techniques. Support vector machine (SVM) is one of the best algorithms in the field of machine learning and can be used to solve many problems in practical applications. Support vector machine (SVM) has been widely used in text and hypertext classification, image classification, handwriting recognition, biometric recognition and so on. The kernel parameters of support vector machines and other related parameters are usually based on experience, and the selection of parameters is often related to the final performance of the model. In this paper, particle swarm optimization and artificial bee swarm algorithm are used to optimize the parameters of support vector machine. Compared with other SVM parameter selection methods, the swarm intelligence optimization algorithm has the advantages of not requiring continuous parameters and being able to jump out of the local extremum, so the SVM model based on the parameter selection of the swarm intelligence optimization algorithm can show better generalization performance. More than a decade ago, using machines to identify and retrieve targets from images or videos was an impossible task. However, with the popularity of the Internet in recent years, more and more images appear on the Internet. The massive image data make artificial image processing and recognition more and more impossible. Researchers have been devoting themselves to the research of computer vision technology, which enables machines to complete the tasks of image recognition, classification, retrieval instead of manual. The support vector machine (SVM) algorithm shows excellent performance in many computer vision tasks, such as image recognition, classification, retrieval and so on. E-SVM (Exemplar-SVM) is a recently proposed linear SVM model trained using a single positive sample and a negative sample set. The algorithm has been applied to target detection and content-based image retrieval (Content Based Image Retrieval CBIR). The algorithm trains a corresponding linear SVM classifier for each positive sample and finally obtains a set of single-sample linear SVM models. The test results on PASCAL VOC 2007 target recognition data set show that the proposed method can achieve recognition rate comparable to the current optimal target detection algorithm (LDPM). Because the E-SVM model is to train each sample to obtain several detectors with strong specificity, this paper presents a K- mean clustering method to process the E-SVM detector and obtain a set of detectors with average sample characteristics. Due to the fusion of multiple features of the corresponding target, these detectors have better generalization performance, and the number of detectors after clustering is greatly reduced, and the recognition time can be reduced when the target is detected. Improve detection efficiency.
【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP18
[Abstract]:Machine learning (ML) is an important branch of computer science. Arthur Samuel defines it as a machine capable of learning without precise programming, that is, machine learning gives the computer a "thinking" ability to a certain extent. Machine learning is closely related to computational statistics, mathematical optimization and data mining, but there are some differences. According to whether there is feedback in the learning process, machine learning can be divided into three categories: supervised learning, unsupervised learning and reinforcement learning. Support Vector Machine (SVM) is a supervised learning algorithm, which can be used to solve classification and regression problems. Support vector machine (SVM) is used to deal with the problem of classification or regression by constructing a superplane in the feature space, and the linear model is extended to nonlinear cases by kernel techniques. Support vector machine (SVM) is one of the best algorithms in the field of machine learning and can be used to solve many problems in practical applications. Support vector machine (SVM) has been widely used in text and hypertext classification, image classification, handwriting recognition, biometric recognition and so on. The kernel parameters of support vector machines and other related parameters are usually based on experience, and the selection of parameters is often related to the final performance of the model. In this paper, particle swarm optimization and artificial bee swarm algorithm are used to optimize the parameters of support vector machine. Compared with other SVM parameter selection methods, the swarm intelligence optimization algorithm has the advantages of not requiring continuous parameters and being able to jump out of the local extremum, so the SVM model based on the parameter selection of the swarm intelligence optimization algorithm can show better generalization performance. More than a decade ago, using machines to identify and retrieve targets from images or videos was an impossible task. However, with the popularity of the Internet in recent years, more and more images appear on the Internet. The massive image data make artificial image processing and recognition more and more impossible. Researchers have been devoting themselves to the research of computer vision technology, which enables machines to complete the tasks of image recognition, classification, retrieval instead of manual. The support vector machine (SVM) algorithm shows excellent performance in many computer vision tasks, such as image recognition, classification, retrieval and so on. E-SVM (Exemplar-SVM) is a recently proposed linear SVM model trained using a single positive sample and a negative sample set. The algorithm has been applied to target detection and content-based image retrieval (Content Based Image Retrieval CBIR). The algorithm trains a corresponding linear SVM classifier for each positive sample and finally obtains a set of single-sample linear SVM models. The test results on PASCAL VOC 2007 target recognition data set show that the proposed method can achieve recognition rate comparable to the current optimal target detection algorithm (LDPM). Because the E-SVM model is to train each sample to obtain several detectors with strong specificity, this paper presents a K- mean clustering method to process the E-SVM detector and obtain a set of detectors with average sample characteristics. Due to the fusion of multiple features of the corresponding target, these detectors have better generalization performance, and the number of detectors after clustering is greatly reduced, and the recognition time can be reduced when the target is detected. Improve detection efficiency.
【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP18
【參考文獻(xiàn)】
相關(guān)期刊論文 前4條
1 陳健飛;蔣剛;楊劍鋒;;改進(jìn)ABC-SVM的參數(shù)優(yōu)化及應(yīng)用[J];機(jī)械設(shè)計(jì)與制造;2016年01期
2 李t熋，
本文編號(hào)：2198007
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2198007.html
最近更新
教材專著
