本文選題：圖像情感 + 中國畫�。� 參考：《南京師大學(xué)報(bào)(自然科學(xué)版)》2017年03期

【摘要】：圖像情感是指計(jì)算機(jī)識別數(shù)字圖像所表達(dá)內(nèi)容引起人的情感反應(yīng),根據(jù)不同的情感反應(yīng),可以對不同的圖像進(jìn)行分類.在信息量急劇增長的今天,圖像情感分類有助于圖像的標(biāo)注和檢索,蘊(yùn)藏著很大的社會和商業(yè)價(jià)值.不同于西洋畫的"以形寫形",中國畫有著自己明顯的特征:傳統(tǒng)的國畫不講焦點(diǎn)透視,不強(qiáng)調(diào)自然界對于物體的光色變化,不拘泥于物體外表的肖似,而多強(qiáng)調(diào)抒發(fā)作者的主觀情趣.這比彌合一般的低層特征和人類情感高層語義之間的鴻溝的難度更大.基于卷積神經(jīng)網(wǎng)絡(luò)因?yàn)槠渚哂薪Y(jié)構(gòu)簡單、適應(yīng)性強(qiáng)、訓(xùn)練參數(shù)少、連接點(diǎn)多等特點(diǎn),可以直接輸入原始圖像,能夠避免對圖像進(jìn)行復(fù)雜的前期預(yù)處理.相比傳統(tǒng)圖像特征提取方法,卷積神經(jīng)網(wǎng)絡(luò)具有明顯的優(yōu)勢.本文的目的是利用卷積神經(jīng)網(wǎng)絡(luò)發(fā)掘低層特征和情感語義之間的聯(lián)系,提取國畫圖像特征,對得到的特征進(jìn)行PCA降維、歸一化等操作后,利用支持向量機(jī)(SVM)分類器進(jìn)行情感分類.
[Abstract]:Image emotion refers to the human emotional response caused by computer recognition of digital image expression. According to different emotional reactions, different images can be classified. With the rapid increase of information, image emotional classification is helpful to image tagging and retrieval, and it contains great social and commercial value. Unlike Western paintings, Chinese painting has its own obvious characteristics: traditional Chinese painting does not stress focus perspective, does not emphasize the natural changes in the light and color of objects, and does not stick to the appearance of objects. And more emphasis on the subjective feelings of the lyricist. This is more difficult than bridging the gap between the general low-level features and the high-level semantics of human emotions. Based on convolution neural network, because of its simple structure, strong adaptability, less training parameters and more connecting points, it can directly input the original image and avoid the complicated pre-processing of the image. Compared with the traditional image feature extraction method, the convolution neural network has obvious advantages. The purpose of this paper is to use convolution neural network to explore the relationship between low-level features and emotional semantics, extract the features of traditional Chinese painting image, and perform PCA dimensionality reduction, normalization and other operations. Support vector machine (SVM) classifier is used to classify emotion.
【作者單位】： 大數(shù)據(jù)分析與系統(tǒng)實(shí)驗(yàn)室(天津大學(xué)軟件學(xué)院);天津大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】：國家自然科學(xué)基金(61572351;61772360)
【分類號】：J212;TP18;TP391.41
，

本文編號：1936963