基于內(nèi)容的動(dòng)畫(huà)短片分類
發(fā)布時(shí)間：2018-10-24 11:59
【摘要】： 隨著互聯(lián)網(wǎng)技術(shù)的迅速發(fā)展,網(wǎng)上的多媒體信息也越來(lái)越多,特別是近兩年來(lái),數(shù)碼動(dòng)畫(huà)繼音樂(lè)和圖片之后異軍突起,成為又一種互聯(lián)網(wǎng)上用來(lái)傳播信息的常見(jiàn)數(shù)字媒體。因此,迫切需要一種技術(shù)對(duì)動(dòng)畫(huà)進(jìn)行分類,檢索和過(guò)濾。過(guò)去幾年中迅速發(fā)展的CBIR技術(shù)雖然對(duì)靜態(tài)圖像取得了滿意的效果,但是這些技術(shù)并不是針對(duì)動(dòng)畫(huà)設(shè)計(jì)的,無(wú)法直接用于動(dòng)畫(huà)的分類,檢索和過(guò)濾。 鑒于此,本文嘗試在傳統(tǒng)CBIR技術(shù)的基礎(chǔ)上,提出一種用于基于內(nèi)容的動(dòng)畫(huà)短片分類方法。由于現(xiàn)在許多動(dòng)畫(huà)被用作廣告,對(duì)用戶來(lái)說(shuō)是一種垃圾信息,因此找到一種檢測(cè)和過(guò)濾這種信息的方法是很有價(jià)值的,在本文中,主要按照這兩類對(duì)動(dòng)畫(huà)進(jìn)行分類�？紤]到動(dòng)畫(huà)與圖片分類的主要不同來(lái)自于特征提取,而分類器并不關(guān)心其輸入的特征向量是來(lái)自于動(dòng)畫(huà)還是圖片,因此本文將重點(diǎn)放在特征的提取和分析上。 本文首先介紹了基于內(nèi)容的圖像檢索技術(shù)的發(fā)展現(xiàn)狀、系統(tǒng)構(gòu)架以及關(guān)鍵技術(shù)基礎(chǔ),詳細(xì)闡述了圖像語(yǔ)義特征的提取方法,分析方法以及常用的分類方法,鑒于本文分類目標(biāo)的特殊性,還介紹了一些其它的特征提取方法,例如圖像中文字區(qū)域的識(shí)別等。 在提取特征的基礎(chǔ)上,本文使用互信息量(MI)對(duì)不同特征的有效性進(jìn)行了分析,對(duì)提取的不同特征的判別力進(jìn)行了比較;此外,還分析了將動(dòng)畫(huà)整體考慮與將其看作一系列圖片考慮時(shí)的不同,指出后一種做法的效果較差。 最后,本文使用RBF核的支持向量機(jī)(SVM)作為分類器,對(duì)特征分析的結(jié)果進(jìn)行了驗(yàn)證,不但比較了單個(gè)特征的分類結(jié)果,也比較了不同特征的組合的分類結(jié)果。最終的分類結(jié)果驗(yàn)證了對(duì)特征進(jìn)行分析時(shí)的結(jié)論,最后最優(yōu)的特征組合平均錯(cuò)誤概率達(dá)到了8.28%。
[Abstract]:With the rapid development of Internet technology, there are more and more multimedia information on the Internet, especially in the past two years, digital animation, after music and pictures, has become another common digital media used to spread information on the Internet. Therefore, there is an urgent need for a technology to classify, retrieve and filter animation. The rapid development of CBIR technology in the past few years has achieved satisfactory results for still images, but these techniques are not designed for animation and can not be directly used for animation classification, retrieval and filtering. In view of this, based on the traditional CBIR technology, this paper proposes a method for content-based animation short film classification. Now many animations are used as advertisements, which is a kind of junk information for users, so it is very valuable to find a way to detect and filter this information. In this paper, we classify the animation according to these two kinds of animation. Considering that the main difference between animation and image classification comes from feature extraction and the classifier does not care whether the input feature vector is from animation or picture, this paper focuses on feature extraction and analysis. This paper first introduces the development of content-based image retrieval technology, the system framework and the key technical basis, and describes the image semantic feature extraction methods, analysis methods and common classification methods in detail. In view of the particularity of the classification object in this paper, some other feature extraction methods are also introduced, such as the recognition of the text region in the image, and so on. On the basis of feature extraction, the validity of different features is analyzed by using mutual information quantity (MI), and the discriminant power of different features is compared. The difference between considering animation as a whole and considering it as a series of pictures is also analyzed, and it is pointed out that the effect of the latter method is poor. Finally, the support vector machine (SVM) based on RBF kernel is used as the classifier to verify the results of feature analysis, not only comparing the classification results of individual features, but also comparing the classification results of different feature combinations. The final classification results verify the conclusion of the feature analysis, and the average error probability of the optimal feature combination reaches 8.28%.
【學(xué)位授予單位】：上海交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2007
【分類號(hào)】：TP391.4
本文編號(hào)：2291341
[Abstract]:With the rapid development of Internet technology, there are more and more multimedia information on the Internet, especially in the past two years, digital animation, after music and pictures, has become another common digital media used to spread information on the Internet. Therefore, there is an urgent need for a technology to classify, retrieve and filter animation. The rapid development of CBIR technology in the past few years has achieved satisfactory results for still images, but these techniques are not designed for animation and can not be directly used for animation classification, retrieval and filtering. In view of this, based on the traditional CBIR technology, this paper proposes a method for content-based animation short film classification. Now many animations are used as advertisements, which is a kind of junk information for users, so it is very valuable to find a way to detect and filter this information. In this paper, we classify the animation according to these two kinds of animation. Considering that the main difference between animation and image classification comes from feature extraction and the classifier does not care whether the input feature vector is from animation or picture, this paper focuses on feature extraction and analysis. This paper first introduces the development of content-based image retrieval technology, the system framework and the key technical basis, and describes the image semantic feature extraction methods, analysis methods and common classification methods in detail. In view of the particularity of the classification object in this paper, some other feature extraction methods are also introduced, such as the recognition of the text region in the image, and so on. On the basis of feature extraction, the validity of different features is analyzed by using mutual information quantity (MI), and the discriminant power of different features is compared. The difference between considering animation as a whole and considering it as a series of pictures is also analyzed, and it is pointed out that the effect of the latter method is poor. Finally, the support vector machine (SVM) based on RBF kernel is used as the classifier to verify the results of feature analysis, not only comparing the classification results of individual features, but also comparing the classification results of different feature combinations. The final classification results verify the conclusion of the feature analysis, and the average error probability of the optimal feature combination reaches 8.28%.
【學(xué)位授予單位】：上海交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2007
【分類號(hào)】：TP391.4
【引證文獻(xiàn)】
中國(guó)碩士學(xué)位論文全文數(shù)據(jù)庫(kù) 前2條
1 仝琳;論攝影技術(shù)在動(dòng)畫(huà)制作中的重要作用[D];山東師范大學(xué);2010年
2 劉永翔;基于支持向量機(jī)的瓦斯突出預(yù)測(cè)研究[D];太原理工大學(xué);2012年
，本文編號(hào)：2291341
本文鏈接：http://www.wukwdryxk.cn/wenyilunwen/guanggaoshejilunwen/2291341.html
最近更新
教材專著
