基于2D-PCA特征描述的非負(fù)權(quán)重鄰域嵌入人臉超分辨率重建算法
doi: 10.11999/JEIT140739
基金項(xiàng)目:
國家自然科學(xué)基金(61071091, 61071166, 60802021)，江蘇省研究生培養(yǎng)創(chuàng)新工程(CXZZ12_0470)，江蘇省自然科學(xué)青年基金(BK20130867)， 江蘇省高校自然科學(xué)研究項(xiàng)目(12KJB510019)和南京郵電大學(xué)校科研基金(NY212015)資助課題
Novel Neighbor Embedding Face Hallucination Based on Non-negative Weights and 2D-PCA Feature
-
摘要: 在基于鄰域嵌入人臉圖像的超分辨率重建算法中，訓(xùn)練和重建均在特征空間進(jìn)行，因此，特征選擇對算法性能具有較大影響。另外，算法模型對重建權(quán)重未加限定，導(dǎo)致負(fù)數(shù)權(quán)重出現(xiàn)而產(chǎn)生過擬合效應(yīng)，使得重建人臉圖像質(zhì)量衰退?？紤]到人臉圖像的特征選擇以及權(quán)重符號限定的重要作用，該文提出一種基于2維主成分分析(2D- PCA)特征描述的非負(fù)權(quán)重鄰域嵌入人臉超分辨率重建算法。首先將人臉圖像分成若干子塊，利用K均值聚類獲得圖像子塊的局部視覺基元，并利用得到的局部視覺基元對圖像子塊分類。然后，利用2D-PCA對每一類人臉圖像子塊提取特征，并建立高、低分辨率樣本庫。最后，在重建過程中使用新的非負(fù)權(quán)重求解方法求取權(quán)重。仿真實(shí)驗(yàn)結(jié)果表明，相比其他基于鄰域嵌入人臉超分辨率重建方法，所提算法可有效提高權(quán)重的穩(wěn)定性，減少過擬合效應(yīng)，其重建人臉圖像具有較好的主客觀質(zhì)量。Abstract: In neighbor embedding based face hallucination, the training and reconstruction processes are performed in the feature space, thus the feature selection is important. In addition, there is no constraint specified for the signs of the weights generated in neighbor embedding algorithm, which leads to over-fitting and degradation of the recovered face images. Considering the importance of feature selection and the constraints of weights, a novel neighbor embedding face hallucination method is proposed based on non-negative weights and Two-Dimensional Principal Component Analysis (2D-PCA) features. First, the face images are partitioned into patches, and the local visual primitives are obtained by k-means clustering algorithm. The face image patches are classified with the local visual primitives generated before. Second, the feature of face image patches is captured with 2D-PCA, and the low and high dictionary is established. Finally, a novel non-negative weights solution method is used to obtain the weights. The experiment results show that the weights computed by the proposed method have more stable behavior and obviously less over-fitting phenomenon, furthermore, the recovery face images have better subjective and objective quality.
-
計(jì)量
- 文章訪問數(shù): 2109
- HTML全文瀏覽量: 139
- PDF下載量: 758
- 被引次數(shù): 0
下載:
