本文選題：語義鄰域 + 圖像標注��； 參考：《模式識別與人工智能》2017年03期

【摘要】：傳統(tǒng)圖像標注方法中人工選取特征費時費力,傳統(tǒng)標簽傳播算法忽視語義近鄰,導(dǎo)致視覺相似而語義不相似,影響標注效果.針對上述問題,文中提出融合深度特征和語義鄰域的自動圖像標注方法.首先構(gòu)建基于深度卷積神經(jīng)網(wǎng)絡(luò)的統(tǒng)一、自適應(yīng)深度特征提取框架,然后對訓(xùn)練集劃分語義組并建立待標注圖像的鄰域圖像集,最后根據(jù)視覺距離計算鄰域圖像各標簽的貢獻值并排序得到標注關(guān)鍵詞.在基準數(shù)據(jù)集上實驗表明,相比傳統(tǒng)人工綜合特征,文中提出的深度特征維數(shù)更低,效果更好.文中方法改善傳統(tǒng)視覺近鄰標注方法中的視覺相似而語義不相似的問題,有效提升準確率和準確預(yù)測的標簽總數(shù).
[Abstract]:In the traditional image labeling methods, it takes time and effort to select the features manually, and the traditional label propagation algorithm neglects the semantic nearest neighbor, which leads to visual similarity and semantic dissimilarity, which affects the annotation effect. In order to solve the above problems, an automatic image tagging method based on depth feature and semantic neighborhood is proposed. Firstly, a unified and adaptive depth feature extraction framework based on the deep convolution neural network is constructed, and then the training set is divided into semantic groups and the neighborhood image set of the image to be tagged is established. Finally, according to the visual distance, the contribution value of each label of the neighborhood image is calculated and the tagged keywords are sorted. The experiments on the datum data set show that the depth feature dimension proposed in this paper is lower and the effect is better than that of the traditional artificial synthesis feature. In this paper, the problem of visual similarity and semantic dissimilarity in traditional visual nearest neighbor labeling methods is improved, and the accuracy rate and the number of accurately predicted labels are effectively improved.
【作者單位】： 福州大學(xué)數(shù)學(xué)與計算機科學(xué)學(xué)院;福州大學(xué)福建省網(wǎng)絡(luò)計算與智能信息處理重點實驗室;
【基金】：國家自然科學(xué)基金項目(No.61502105) 福建省自然科學(xué)基金項目(No.2013J05088) 福建省中青年教師教育科研項目(No.JA15075)資助~~
【分類號】：TP391.41
，

本文編號：1838533