本文關(guān)鍵詞：可計(jì)算圖像美學(xué)研究進(jìn)展，，由筆耕文化傳播整理發(fā)布。

可計(jì)算圖像美學(xué)研究進(jìn)展

Review for computational image aesthetics

[1] [2] [3]

Wang Weining, Yi Jingjian, He Qianhua （School of Electronic and Information, South China University of Technology, Guangzhou 510640, China）

華南理工大學(xué)電子與信息學(xué)院,廣州510640

文章摘要：可計(jì)算圖像美學(xué)研究目的是希望計(jì)算機(jī)能夠模擬人類(lèi)的視覺(jué)系統(tǒng)與審美思維對(duì)圖像進(jìn)行美學(xué)價(jià)值的判斷。其研究成果可以應(yīng)用到融合主觀(guān)感知的基于語(yǔ)義的圖像檢索、圖像美學(xué)質(zhì)量評(píng)估、圖像的美學(xué)修正、攝影的美學(xué)預(yù)測(cè)、藝術(shù)作品風(fēng)格分析、人機(jī)交互等方面。該研究涉及美學(xué)、藝術(shù)、認(rèn)知科學(xué)、計(jì)算機(jī)科學(xué)、心理學(xué)等多個(gè)學(xué)科。屬于多學(xué)科交叉的創(chuàng)新性前沿研究課題，具有重要的理論研究?jī)r(jià)值和應(yīng)用前景�？偨Y(jié)國(guó)際上最新研究成果，對(duì)該研究的常用方法和存在問(wèn)題進(jìn)行了系統(tǒng)的分析及綜述，給出了可計(jì)算圖像美學(xué)分析研究的一般框架，對(duì)圖像的審美度量、美學(xué)視覺(jué)特征提取和美學(xué)推導(dǎo)等關(guān)鍵技術(shù)，以及圖像美學(xué)的應(yīng)用與發(fā)展前景等進(jìn)行了詳細(xì)討論，并且針對(duì)當(dāng)前研究存在的問(wèn)題提出關(guān)鍵的解決方案。

Abstr：The purpose of the computational image aesthetics research is to endow computer with the ability to assess the aesthetics value of images as human beings do. The results can be used in many fields, for example semantic-based image retrieval, fusing the subjective perception, image aesthetics evaluation, image aesthetics retouching, photograph aesthetics prediction, art works style analysis and man-machine interaction. Computational image aesthetics is a new interdisciplinary advanced topic with good developing prospect, while it involves different subjects, including Aesthetics, Art, Cognitive Sci- ence, Computer Science, Psychology, and so on. In this paper, the latest achievements of the computation image aesthetics research are introduced at first, then a general framework of the computational image aesthetics is proposed after the analy- sis and summary of methods commonly applied in this field. Additionally, we point out the exiting problems and we discuss including image aesthetics measurement, extraction of aesthetics vision features, aesthetics deduction, and also the applica- tion and future developments of image aesthetics. Furthermore, some crucial solutions are pointed out to solve the exiting problems.

文章關(guān)鍵詞：

Keyword：:image aesthetics aesthetics vision features aesthetics measure aesthetics classification

課題項(xiàng)目：國(guó)家自然科學(xué)基金項(xiàng)目（60602014,60972132）;廣東省自然科學(xué)基金團(tuán)隊(duì)項(xiàng)目（9351064101000003）;中央高�；究蒲谢痦�(xiàng)目（2009ZM0180）

作者信息：會(huì)員可見(jiàn)

  本文關(guān)鍵詞：可計(jì)算圖像美學(xué)研究進(jìn)展，由筆耕文化傳播整理發(fā)布。