本文關(guān)鍵詞： 多標記學習 空間信息 殘缺圖像 關(guān)聯(lián)性 遷移學習　出處：《山東師范大學》2017年碩士論文　論文類型：學位論文

【摘要】：伴隨著網(wǎng)絡信息技術(shù)的飛速發(fā)展,互聯(lián)網(wǎng)+模式的迅速興起,人們對于網(wǎng)絡信息的獲取與需求呈指數(shù)般增長。除了對文字信息的需求外,對于圖像內(nèi)容信息的認知與理解也逐漸為人們所重視。圖像自動標注技術(shù)的出現(xiàn),在一定程上彌補了人工標注存在的耗時耗力、較為主觀等不足,提升了圖像理解技術(shù)的效率。但現(xiàn)今人們對于圖像內(nèi)容的理解已經(jīng)不僅僅拘泥于單一的概念和標記了,而更傾向于多層次多角度的解讀,圖像的多標記學習應運而生,更好的適應了人們的需求。圖像的多標記學習方法層出不窮且漸趨成熟,對于圖像區(qū)域空間信息的運用也越來越充分,但是現(xiàn)實世界中除了完整的圖像外還存在著大量殘缺或者被遮擋的圖像,其中也包含著大量有效的信息,針對這部分特殊的圖像族群,運用空間信息,提出殘缺圖像的多標記學習方法,該方法可以減弱圖像缺損部分對圖像內(nèi)容理解的影響,提高殘缺圖像的標注查全和查準率,更好體現(xiàn)整幅圖像的蘊含信息。同時,圖像的多標記學習中圖像與圖像之間,圖像與標記之間,標記與標記之間的關(guān)聯(lián)性還需更充分的利用,將機器學習中的相似性遷移思想融合進圖像的多標記學習中,提出基于相似性遷移學習的圖像多標記算法,探究圖像與標記之間的關(guān)聯(lián)性,能夠有效提高圖像的標注質(zhì)量,減少噪聲干擾。本文的主要工作與創(chuàng)新點概括如下:1.結(jié)合空間信息對于圖像內(nèi)容理解的重要性,針對殘缺圖像族群,提出一種基于空間信息的多標記算法。首先選取圖像缺損部分的最小矩形局域,沿矩形邊沿延伸將所有圖像按此比例進行分割,然后以圖像的分割子塊為單位進行圖像的相似性度量,利用圖像分割區(qū)域的空間結(jié)構(gòu)信息完成對圖像的自動標注。這種方法能夠充分的利用殘缺圖像的空間信息,減弱圖像缺損部分對圖像內(nèi)容理解的影響,提高殘缺圖像的標注查全和查準率,更好的體現(xiàn)整幅圖像的蘊含信息。2.為了進一步探究圖像標記之間的關(guān)聯(lián)性,融合遷移學習理論,提出一種基于相似性遷移學習的圖像多標記算法。首先建立圖像間的特征相似度量,然后引入相似性遷移學習算法,將圖像的底層特征相似度量遷移到圖像所對應標注詞的相似度量,通過統(tǒng)計方法實現(xiàn)圖像的自動標注。該方法能夠有效提高圖像的標注質(zhì)量,減少噪聲干擾,為圖像多標記學習提供額外的有用信息,在一定程度上彌補了樣本數(shù)據(jù)的不足。通過運用圖像空間的區(qū)域結(jié)構(gòu)信息,融合遷移學習理論將圖像相似性遷移到圖像的標記學習中,論文中的多標記學習算法對于殘缺圖像族群能夠有效提高其標記性能,具有良好的魯棒性;對于完整圖像族群,可以有效弱化干擾,增強其標記學習效果。
[Abstract]:With the rapid development of network information technology and the rapid rise of Internet mode, people's access to and demand for network information has increased exponentially, in addition to the demand for text information. Recognition and understanding of image content information has gradually been paid attention to. The appearance of automatic image tagging technology, in a certain process, make up for the shortcomings of manual annotation, such as time-consuming, more subjective and so on. It improves the efficiency of image understanding technology. But nowadays, people's understanding of image content is not only limited to a single concept and label, but also more inclined to multi-level and multi-angle interpretation. Image multi-label learning emerged as the times require to better meet the needs of the people. Image multi-label learning methods emerge one after another and gradually mature, the use of spatial information in the image region is becoming more and more fully. But in the real world in addition to the complete image there are also a large number of incomplete or occluded images which also contain a large number of effective information for this part of the special image groups the use of spatial information. This paper proposes a multi-label learning method for incomplete images, which can reduce the effect of image defects on image content understanding and improve the tagging and checking accuracy of incomplete images. At the same time, the relationship between image and image, between image and label, between mark and label should be used more fully in image multi-label learning. The idea of similarity transfer in machine learning is integrated into image multi-label learning, and an image multi-label algorithm based on similarity transfer learning is proposed to explore the correlation between image and label. The main work and innovation of this paper are summarized as follows: 1. Combining the importance of spatial information for image content understanding, aiming at incomplete image groups. A multi-label algorithm based on spatial information is proposed. Firstly, the minimum rectangular region of the defective part of the image is selected and all images are segmented in this proportion along the edge of the rectangle. Then we measure the similarity of the image in the unit of segmentation sub-block. This method can make full use of the spatial information of the incomplete image and reduce the influence of the image defect on the understanding of the image content by using the spatial structure information of the image segmentation region. In order to further explore the relevance of image markers, fusion transfer learning theory is used to improve the tagging and precision rate of incomplete images, and better reflect the information contained in the whole image. 2. An image multi-label algorithm based on similarity transfer learning is proposed. Firstly, the feature similarity between images is established, and then the similarity transfer learning algorithm is introduced. The image's bottom feature similarity is transferred to the image's corresponding tagged word's similarity, and the image's automatic annotation is realized by statistical method. This method can effectively improve the image's tagging quality and reduce the noise interference. To provide additional useful information for image multi-label learning, to a certain extent, to make up for the lack of sample data, by using the image space of regional structure information. Fusion transfer learning theory transfers image similarity to image tagging learning. The multi-label learning algorithm in this paper can effectively improve the marking performance of incomplete image populations and has good robustness. For the complete image population, the interference can be weakened effectively and the effect of marker learning can be enhanced.
【學位授予單位】：山東師范大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前10條

1 余鷹;;多標記學習研究綜述[J];計算機工程與應用;2015年17期

2 何志芬;楊明;劉會東;;多標記分類和標記相關(guān)性的聯(lián)合學習[J];軟件學報;2014年09期

3 李宏益;吳素萍;;Mean Shift圖像分割算法的并行化[J];中國圖象圖形學報;2013年12期

4 劉立;詹茵茵;羅揚;劉朝暉;彭復員;;尺度不變特征變換算子綜述[J];中國圖象圖形學報;2013年08期

5 張敏靈;;一種新型多標記懶惰學習算法[J];計算機研究與發(fā)展;2012年11期

6 王春艷;;一種加權(quán)的ML-kNN算法[J];電腦知識與技術(shù);2012年04期

7 劉麗;匡綱要;;圖像紋理特征提取方法綜述[J];中國圖象圖形學報;2009年04期

8 劉曉民;;紋理研究及其應用綜述[J];測控技術(shù);2008年05期

9 吳介;裘正定;;底層內(nèi)容特征的融合在圖像檢索中的研究進展[J];中國圖象圖形學報;2008年02期

10 程顯毅;李小燕;任越美;;圖像空間關(guān)系特征描述[J];江南大學學報(自然科學版);2007年06期

相關(guān)博士學位論文 前1條

1 楊同峰;基于空間關(guān)系的圖像檢索與分類研究[D];山東大學;2013年

相關(guān)碩士學位論文 前1條

1 周慧;基于圖像低層特征的領(lǐng)帶花型檢索研究[D];浙江理工大學;2015年

，

本文編號：1487590