發(fā)布時間：2018-03-02 19:10

  本文選題：半監(jiān)督學(xué)習(xí)　切入點：Group　出處：《華東師范大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著大數(shù)據(jù)時代的到來、互聯(lián)網(wǎng)技術(shù)的飛速發(fā)展和成像設(shè)備的日漸普及,圖像等媒體資源的數(shù)據(jù)采集越來越便捷,圖像在醫(yī)學(xué)、天文學(xué)、刑偵、交通、軍事、環(huán)境學(xué)、社交網(wǎng)絡(luò)等各行各業(yè)發(fā)揮著至關(guān)重要的作用。面對以幾何速度增長的網(wǎng)絡(luò)圖像數(shù)量,傳統(tǒng)的圖像數(shù)據(jù)的分析和處理面臨資源基數(shù)龐大、特征維度高、需要的存儲空間大、查詢速度慢等方面的挑戰(zhàn),研究大規(guī)模圖像搜索算法的需求日益迫切:考慮現(xiàn)實生活中的數(shù)據(jù)標(biāo)記現(xiàn)狀,尤其是在圖像搜索與識別等領(lǐng)域,最大量的、獲取最便捷的數(shù)據(jù)都是沒有標(biāo)簽的,因此基于半監(jiān)督學(xué)習(xí)的圖像搜索算法是具有重大現(xiàn)實意義和實際需求的算法;圖像數(shù)據(jù)本身具有顏色、形狀、紋理等特征,圖像數(shù)據(jù)的不同維度之間可能具有某些結(jié)構(gòu)或語義聯(lián)系,有效的建模圖像數(shù)據(jù)的結(jié)構(gòu)非常關(guān)鍵;此外,設(shè)計有效的求解算法對大規(guī)模數(shù)據(jù)集上的圖像搜索至關(guān)重要。本文在以上幾點現(xiàn)實背景下,在已有的半監(jiān)督哈希圖像搜索算法基礎(chǔ)上,進行了以下工作:1.提出了基于Group Lasso的半監(jiān)督哈希圖像搜索算法。半監(jiān)督的學(xué)習(xí)方法充分利用了所有帶標(biāo)簽和無標(biāo)簽的訓(xùn)練數(shù)據(jù);哈希圖像搜索算法只存儲圖像的二進制哈希碼,節(jié)省了存儲空間且只需常數(shù)的查詢時間;還可以推廣至超大規(guī)模圖像數(shù)據(jù)集搜索。2.用Group Lasso將組結(jié)構(gòu)考慮進圖像搜索模型,使同組的特征具有了同時選入或同時剔除出模型的特性。通過Group Lasso引入了組間稀疏性,起到了特征選擇的作用,避免了過擬合并提高了模型的準(zhǔn)確性。3.求解基于Group Lasso的半監(jiān)督哈希圖像搜索模型時引入了鄰近梯度法優(yōu)化模型并快速求解。4.在標(biāo)準(zhǔn)圖像數(shù)據(jù)庫MNIST和CIFAR10上測試模型,并與已有的其他圖像搜索算法對比。
[Abstract]:With the arrival of big data era, the rapid development of Internet technology and the increasing popularity of imaging equipment, image and other media resources data collection more and more convenient, images in medicine, astronomy, criminal investigation, transportation, military, environmental science, Social networks and other industries play a vital role. In the face of the geometric growth of the number of network images, the traditional image data analysis and processing faces a huge resource base, high feature dimension, large storage space. Due to the challenge of slow query speed and so on, it is increasingly urgent to study large-scale image search algorithms: to consider the current situation of data marking in real life, especially in the field of image search and recognition. Therefore, the image search algorithm based on semi-supervised learning is of great practical significance and practical need, and the image data itself has the characteristics of color, shape, texture, etc. There may be some structural or semantic connection between the different dimensions of the image data, and effective modeling of the structure of the image data is critical; in addition, It is very important to design an effective algorithm for image search on large scale data sets. In this paper, based on the existing semi-supervised hash image search algorithms, The following work is done: 1. A semi-supervised hashing image search algorithm based on Group Lasso is proposed. The semi-supervised learning method makes full use of all tagged and untagged training data; the hash image search algorithm only stores binary hash codes of images. It saves storage space and requires only constant query time; it can also be extended to very large scale image dataset search. 2. The group structure is taken into account in the image search model with Group Lasso. The features of the same group have the characteristics of selecting or removing the model at the same time. The sparsity between groups is introduced through Group Lasso, which plays the role of feature selection. By avoiding over-fitting and merging, the accuracy of the model is improved. 3. In solving the semi-supervised hash image search model based on Group Lasso, the optimization model of adjacent gradient method is introduced and the model is quickly solved. The model is tested on the standard image database MNIST and CIFAR10. And compared with other existing image search algorithms.
【學(xué)位授予單位】：華東師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前1條

1 ;“互聯(lián)網(wǎng)+”人工智能三年行動實施方案[J];中國信息技術(shù)教育;2016年11期

，

本文編號：1557803