本文選題：Gist特征 + 顯著性計算�。� 參考：《吉林大學(xué)》2015年博士論文

【摘要】：本文對基于鄰接圖的流形學(xué)習(xí)降維算法，基于梯度方向直方圖的人臉特征提取算法和gist特征抽取算法進(jìn)行了深入研究，，分別對基于鄰接圖的流形學(xué)習(xí)降維算法，基于梯度方向直方圖的人臉特征提取算法和gist特征抽取算法提出了改進(jìn)算法，并基于這些改進(jìn)算法提出了新的人臉識別方法和建筑物識別方法。 經(jīng)典的k近鄰(k-nearest neighbors)鄰接圖構(gòu)造方法，通過計算樣本向量的k個近鄰來構(gòu)造流形學(xué)習(xí)算法的鄰接圖。這種方法沒有在構(gòu)建鄰接圖的時候考慮樣本的原始結(jié)構(gòu)信息，針對這一缺陷，筆者提出了基于樣本對應(yīng)列的鄰接圖(CorrespondingColumnsBasedGraph, CCG)構(gòu)造方法。 筆者在基于樣本對應(yīng)列的鄰接圖構(gòu)造方法的基礎(chǔ)上提出了基于樣本對應(yīng)塊的鄰接圖(CorrespondingblockBasedGraph,CBG)構(gòu)造方法。實(shí)驗證明，基于樣本對應(yīng)塊的鄰接圖對人臉識別中遇到的非均勻光照具有一定的魯棒性。 經(jīng)典的k近鄰鄰接圖構(gòu)造方法在構(gòu)建鄰接圖時，需要憑借經(jīng)驗指定近鄰參數(shù)k。針對這一問題，筆者在CCG和CBG的基礎(chǔ)上提出了基于樣本內(nèi)部結(jié)構(gòu)的鄰接圖構(gòu)造(Samples’Inner Structure Based Graph, SISG)方法。 筆者提出了用于人臉識別的局部敏感梯度方向直方圖(Locality Sensitive Histogramsof Oriented Gradients, LSHOG)。該梯度直方圖在提取人臉特征向量的時候體現(xiàn)了人臉圖片的二維結(jié)構(gòu)信息和全局信息，因此局部敏感梯度方向直方圖對于人臉上的遮擋和非均勻光照有一定的魯棒性。 本文在傳統(tǒng)的gist特征的抽取方法的基礎(chǔ)上提出了子區(qū)域多尺度gist特征提取方法。相比于原有的gist特征提取方法，本文提出的子區(qū)域多尺度gist特征提取方法對于建筑物圖片中的非均勻光照具有較高的魯棒性。 筆者將子區(qū)域多尺度gist特征提取方法和基于樣本內(nèi)部結(jié)構(gòu)鄰接圖的流形學(xué)習(xí)算法相結(jié)合提出了一種新的建筑物識別方法：基于子區(qū)域多尺度gist特征和樣本內(nèi)部結(jié)構(gòu)鄰接圖降維算法的建筑物識別方法。
[Abstract]:In this paper, manifold learning dimensionality reduction algorithm based on adjacent graph, face feature extraction algorithm based on gradient direction histogram and gist feature extraction algorithm are studied in detail. Based on gradient direction histogram and gist feature extraction algorithm, an improved face recognition method and a new building recognition method are proposed. The classical k-nearest neighbor adjacent graph construction method is used to construct the adjacent graph of the manifold learning algorithm by computing k nearest neighbors of the sample vector. This method does not take the original structure information of samples into account when constructing adjacent graphs. In view of this defect, a method of constructing adjacent graphs based on Corresponding columns (CCGs) based on sample corresponding columns is proposed in this paper. Based on the method of constructing adjacent graph based on sample correspondence column, a method of constructing adjacent graph based on Correspondingblock based CBG (CBG) based on sample corresponding block is proposed in this paper. The experimental results show that the adjacent graph based on the corresponding block of samples is robust to the non-uniform illumination in face recognition. The classical construction method of k-nearest neighbor graph needs to specify the nearest neighbor parameter k by experience when constructing the adjacent graph. In order to solve this problem, based on CCG and CBG, the method of constructing adjacent graphs based on internal structure of samples is proposed, which is called Inner Structure Based Graph (SISG). The local Sensitive Histogramsof Oriented gradient histogram for face recognition is presented in this paper. The gradient histogram presents the two-dimensional structure and global information of the face image when extracting the face feature vector, so the local sensitive gradient direction histogram is robust to the occlusion and non-uniform illumination of the human face. Based on the traditional gist feature extraction method, a multi-scale subregion gist feature extraction method is proposed in this paper. Compared with the original gist feature extraction method, the multi-scale gist feature extraction method proposed in this paper is robust to non-uniform illumination in building images. In this paper, a new building recognition method is proposed by combining subregion multi-scale gist feature extraction method and manifold learning algorithm based on adjacent graph of sample interior structure: based on sub-region multi-scale gist feature and sample interior knot. Building recognition method based on dimension reduction algorithm of adjacent graph.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2015
【分類號】：TP391.41

【參考文獻(xiàn)】

相關(guān)博士學(xué)位論文 前1條

1 王u&菁;流形上的張量子空間人臉識別算法的研究[D];吉林大學(xué);2012年

本文編號：1801123