本文選題：圖像美學(xué)分析　切入點(diǎn)：美感分類　出處：《華南理工大學(xué)》2013年碩士論文　論文類型：學(xué)位論文

【摘要】：可計(jì)算圖像美學(xué)的研究目的是希望計(jì)算機(jī)能夠模擬人類的視覺(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。其研究結(jié)果可以應(yīng)用到融合主觀感知的基于語(yǔ)義的圖像檢索、圖像美學(xué)質(zhì)量評(píng)估、攝影的美學(xué)預(yù)測(cè)與修正、藝術(shù)作品風(fēng)格分析、人機(jī)交互，以及設(shè)計(jì)、攝影、廣告等領(lǐng)域。 本文以數(shù)字圖像和攝影照片為研究對(duì)象，探索采用計(jì)算機(jī)進(jìn)行圖像美學(xué)自動(dòng)分類與評(píng)價(jià)的可計(jì)算方法，，通過(guò)對(duì)圖像劃分整體區(qū)域和關(guān)鍵區(qū)域，提取有效的低層視覺(jué)特征和高層美學(xué)特征，并采用機(jī)器學(xué)習(xí)的方法建立圖像美感等級(jí)評(píng)估分類器和美學(xué)分?jǐn)?shù)預(yù)測(cè)模型，實(shí)現(xiàn)了機(jī)器自動(dòng)評(píng)估圖像的高、低美感并預(yù)測(cè)圖像的美學(xué)分?jǐn)?shù)。 圍繞可計(jì)算圖像美學(xué)的分類評(píng)價(jià)研究，本文的工作包括： 1、基于人類視覺(jué)心理學(xué)美感研究，建立了包含人類審美評(píng)價(jià)信息的美學(xué)圖庫(kù)。 2、設(shè)計(jì)了一種結(jié)合分水嶺分割算法與圖像梯度特征的主體區(qū)域提取方法，提取主體區(qū)域作為圖像的關(guān)鍵區(qū)域。 3、完成了基于美學(xué)的圖像特征提取，包括圖像低層特征、高層美學(xué)特征及區(qū)域特征。 4、對(duì)特征數(shù)據(jù)進(jìn)行機(jī)器訓(xùn)練學(xué)習(xí)，采用AdaBoos（tAdaptive Boosting，自適應(yīng)增強(qiáng)算法）分類算法建立圖像美感等級(jí)評(píng)估分類器，并通過(guò)SVR（Support Vector Regression,支持向量回歸）算法建立圖像美學(xué)分?jǐn)?shù)預(yù)測(cè)模型。 5、實(shí)現(xiàn)了可計(jì)算的圖像美學(xué)分類評(píng)價(jià)系統(tǒng)。 本文對(duì)大量含有美感信息的圖像進(jìn)行測(cè)試，實(shí)現(xiàn)高低美感分類的平均分類準(zhǔn)確率為77.4%，而回歸預(yù)測(cè)相關(guān)性為0.795、均方根誤差為0.244。實(shí)驗(yàn)證明了本文算法的有效性，系統(tǒng)美感的結(jié)果與人類對(duì)圖像審美感知結(jié)果高度相關(guān)。
[Abstract]:The purpose of the research on computable image aesthetics is to hope that the computer can simulate human visual system and aesthetic thinking to judge the aesthetic value of images. The research results can be applied to semantic image retrieval based on subjective perception. Image Aesthetics quality Assessment, Photography Aesthetics Prediction and Correction, Art style Analysis, Human-Computer interaction, Design, Photography, Advertising, etc. In this paper, we take digital images and photographic photographs as research objects, and explore the computable method of automatic classification and evaluation of image aesthetics by using computer. By dividing the image into the whole region and the key area, Extraction of effective low-level visual features and high-level aesthetic features, and the establishment of image aesthetic evaluation classifier and aesthetic score prediction model by machine learning method, which can automatically evaluate the image height. Low aesthetic sense and predict the aesthetic score of the image. Based on the research of classification and evaluation of computable image aesthetics, the work of this paper includes:. 1. Based on the study of aesthetic sense of human visual psychology, an aesthetic library containing human aesthetic evaluation information is established. 2. A main region extraction method combining watershed segmentation algorithm with image gradient feature is designed. The main body region is extracted as the key region of the image. Thirdly, the extraction of image features based on aesthetics is completed, including image low-level features, high-level aesthetic features and regional features. 4. The feature data is trained by machine, and an image aesthetic evaluation classifier is established by using AdaBoos(tAdaptive boost (adaptive enhancement algorithm) classification algorithm, and an image aesthetic score prediction model is established by SVR(Support Vector regression (support vector regression) algorithm. 5. A computable image aesthetic classification and evaluation system is implemented. In this paper, a large number of images with aesthetic information are tested, and the average classification accuracy is 77.4, the correlation of regression prediction is 0.795, and the root mean square error is 0.244.The experimental results show that the algorithm is effective. The result of systematic aesthetic sense is highly related to the result of human aesthetic perception of image.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 黃\

本文編號(hào)：1634277