【摘要】：隨著互聯(lián)網(wǎng)的飛速發(fā)展,越來(lái)越多的圖片、視頻和文字等多媒體信息被大量的上傳到互聯(lián)網(wǎng)。其中,圖片和視頻作為能高效地提供直觀(guān)視覺(jué)效果的媒體,在社交網(wǎng)絡(luò)中更是成為了最為活躍的一類(lèi)信息載體。基于互聯(lián)網(wǎng)視覺(jué)媒體的信息處理是指運(yùn)用當(dāng)前網(wǎng)絡(luò)上存在的大量圖片／視頻等媒質(zhì),以及這些媒質(zhì)所附帶的標(biāo)注、評(píng)論、用戶(hù)喜好等信息,進(jìn)行多源異質(zhì)的媒體信息分析、處理及應(yīng)用。其研究?jī)?nèi)容涉及到計(jì)算機(jī)圖形學(xué)、計(jì)算機(jī)視覺(jué)以及機(jī)器學(xué)習(xí)等多個(gè)領(lǐng)域,目的是充分利用現(xiàn)有的視覺(jué)媒體資源,開(kāi)發(fā)出適應(yīng)用戶(hù)需求的智能應(yīng)用。 基于上述背景,本文在具體應(yīng)用中若干關(guān)鍵問(wèn)題的驅(qū)動(dòng)下,運(yùn)用圖像處理和計(jì)算機(jī)視覺(jué)中相關(guān)方法與技術(shù),將互聯(lián)網(wǎng)上多種視覺(jué)媒體資源進(jìn)行智能整合和多樣化重現(xiàn),研究了以下三個(gè)方面的內(nèi)容：多模態(tài)藝術(shù)化的圖像渲染；皮影戲中人臉圖像渲染和視頻動(dòng)畫(huà)交互；面向家具風(fēng)格的特征提取和視覺(jué)分類(lèi)。本文的主要研究?jī)?nèi)容及創(chuàng)新之處概述如下： 1、提出了融合文字信息的多模態(tài)圖像藝術(shù)化渲染方法,并設(shè)計(jì)實(shí)現(xiàn)了Picwords系統(tǒng)； 圖像的藝術(shù)化渲染是將圖像風(fēng)格抽象化和藝術(shù)化的圖像處理技術(shù)。本文提出了一種全新的圖像藝術(shù)化渲染方法,將圖片和文字兩種模態(tài)所攜帶的語(yǔ)義信息進(jìn)行有機(jī)融合,以豐富原圖的語(yǔ)義信息。該方法利用原圖像的主體結(jié)構(gòu)關(guān)聯(lián)低頻信息和整體效果,同時(shí)將文本進(jìn)行幾何形變并作為重構(gòu)目標(biāo)的高頻細(xì)節(jié)信息,進(jìn)而完成圖片和文字兩種模態(tài)的視覺(jué)融合�；谏鲜龇椒�,本文設(shè)計(jì)并實(shí)現(xiàn)了多模態(tài)圖像渲染系統(tǒng)Picwords。該系統(tǒng)將輸入圖像及其相關(guān)的關(guān)鍵詞融合進(jìn)同一張圖片中,同時(shí)對(duì)關(guān)鍵詞的權(quán)重進(jìn)行了自動(dòng)調(diào)整。該系統(tǒng)輸出結(jié)果最大限度地保持了圖像的整體視覺(jué)效果,并傳達(dá)了更多語(yǔ)義信息,在海報(bào)設(shè)計(jì)、廣告宣傳和社交網(wǎng)絡(luò)中都有得到廣泛的應(yīng)用； 2、提出了面向皮影戲的人臉?biāo)囆g(shù)化渲染方法和動(dòng)畫(huà)交互方法,并設(shè)計(jì)了皮影戲遺產(chǎn)電子化保護(hù)系統(tǒng)； 為了保護(hù)中國(guó)皮影戲這一寶貴的非物質(zhì)文化遺產(chǎn),本文設(shè)計(jì)了一個(gè)面向皮影戲的遺產(chǎn)電子化系統(tǒng)。該系統(tǒng)包括皮影戲創(chuàng)作模塊和皮影戲操作模塊,旨在利用網(wǎng)絡(luò)上與皮影戲相關(guān)的圖片和視頻等視覺(jué)媒體資源,將皮影戲的創(chuàng)作個(gè)性化,操作簡(jiǎn)潔化。其創(chuàng)作模塊根據(jù)用戶(hù)提供的人臉圖片,通過(guò)人臉?shù)秩痉椒ㄉ蓚�(gè)性化的皮影戲頭像并保持皮影戲人物的特點(diǎn)。操作模塊可通過(guò)動(dòng)畫(huà)交互方式將皮影的表演動(dòng)作的操作轉(zhuǎn)化為由腳本命令進(jìn)行控制,在保持了皮影戲表演特點(diǎn)的同時(shí),簡(jiǎn)化了操作的復(fù)雜度。該系統(tǒng)可有力輔助皮影戲這一文化遺產(chǎn)的保護(hù)和傳承。 3、提出了基于深度學(xué)習(xí)并融合傳統(tǒng)圖像分類(lèi)的家具風(fēng)格圖片分類(lèi)方法； 家具風(fēng)格是家具最具判別力的外觀(guān)視覺(jué)特征。利用該特征進(jìn)行家具風(fēng)格的智能挑選與推薦,可提升現(xiàn)代家居生活質(zhì)量,兼具學(xué)術(shù)與應(yīng)用價(jià)值。傳統(tǒng)的目標(biāo)分類(lèi)和家具的風(fēng)格分類(lèi)的不同之處在于：前者是以家具的結(jié)構(gòu)和功能作為分類(lèi)依據(jù)；而后者更注重發(fā)掘和分析家具細(xì)節(jié)上的不同,如花紋、材料、顏色等。本文對(duì)此展開(kāi)了以下工作：首先,根據(jù)目前家具市場(chǎng)的風(fēng)格選擇需求,建立了家具風(fēng)格的圖像數(shù)據(jù)集,這也是第一個(gè)針對(duì)家具風(fēng)格研究而建立的視覺(jué)數(shù)據(jù)集；其次,分別比較了傳統(tǒng)的圖像分類(lèi)方法和基于深度神經(jīng)網(wǎng)絡(luò)的圖像分類(lèi)方法在家具風(fēng)格分類(lèi)上的性能,并提出了多尺度的圖像卷積特征；最后,在深度學(xué)習(xí)的基礎(chǔ)上融合傳統(tǒng)圖像分類(lèi)方法,對(duì)16類(lèi)家具風(fēng)格分類(lèi)進(jìn)行實(shí)驗(yàn)(分類(lèi)正確率達(dá)到了70%)并對(duì)實(shí)驗(yàn)結(jié)果進(jìn)行了深入分析。
[Abstract]:With the rapid development of the Internet, more and more multimedia information such as pictures, videos and characters are uploaded to the Internet in a large amount. Among them, pictures and videos are the media that can provide visual visual effect with high efficiency, and the most active type of information carrier is in the social network. The information processing based on the Internet visual media refers to the analysis, processing and application of multi-source heterogeneous media information by using media such as a large number of pictures/ videos that exist on the current network, as well as the information such as the annotations, the comments, the user preference and the like that are attached to the media. The purpose of this study is to make full use of the existing visual media resources, and to develop an intelligent application to meet the needs of users. Based on the above background, under the driving of several key problems in the specific application, this paper uses the related methods and techniques of image processing and computer vision to realize the intelligent integration and diversification of various visual media resources on the Internet, and studies the following three aspects: Appearance: multi-modal and artistic image rendering; human face image rendering and video animation interaction in a shadow play; feature extraction and visual segmentation for furniture style The main contents and innovations of this paper are as follows: Next:1. The multi-modality image rendering method of the fusion word information is put forward, and the Picword is designed and implemented. s system; an artistic rendering of an image is a diagram that abstracts and arizes the style of an image In this paper, a new image rendering method is presented, which combines the semantic information carried by the two modes of the picture and the text, so as to enrich the original image. The method uses the main structure of the original image to relate the low-frequency information and the overall effect, and simultaneously carries out the geometric transformation of the text and is used as the high-frequency detail information of the reconstruction target, so as to finish the two modes of the picture and the text, Based on the above method, the multi-modality image rendering system (Pic) is designed and implemented. the system merges the input image and its associated keywords into the same picture, and the weight of the key words Automatic adjustment. The output of the system keeps the overall visual effect of the image to the maximum extent, and conveys more semantic information, which is available in the report design, advertising and social network extensive In this paper, the rendering method and the animation interaction method for the face of the shadow play are put forward, and the inheritance of the shadow play is designed. Electronic protection system; in order to protect the precious intangible cultural heritage of China's shadow play, this paper designs a shadow-oriented shadow The system includes a shadow play creation module and a shadow play operation module, Personalization and operation are simple. The authoring module generates a personalized skin and shadow play head by means of a human face rendering method according to the face picture provided by the user. the operation module can convert the operation of the acting action of the shadow to be controlled by the script command through an animation interaction mode, Simplifies the complexity of the operation. The system can be used to help the shadow play. The protection and inheritance of the heritage.3. The classification of traditional images based on depth learning and fusion is put forward. The furniture-style picture classification method; the furniture style is a home The visual features of the appearance with the most discriminating force can be used to make the intelligent selection and recommendation of the furniture style, and the modern home life can be improved. The difference between the traditional object classification and the style classification of the furniture is that the former is based on the structure and function of the furniture, and the latter is more focused on the excavation and analysis of the details of the furniture Different, such as pattern, material, color, etc. In this paper, the following work is carried out: firstly, according to the current furniture market style selection requirement, the image data set of the furniture style is set up, which is also the first to research the furniture style Secondly, the performance of the traditional image classification method and the image classification method based on the depth neural network in the classification of the furniture style is compared, and the multi-scale image convolution characteristics are put forward; and finally, in the depth study, On the basis of the traditional image classification method, the classification of the 16-class furniture style is carried out (the classification accuracy is up to 70%).
【學(xué)位授予單位】：合肥工業(yè)大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)博士學(xué)位論文 前1條

1 叢林;圖像渲染與展示的若干問(wèn)題研究[D];浙江大學(xué);2012年

，

本文編號(hào)：2488131