本文選題：視覺顯著性 + 目標(biāo)檢測　； 參考：《吉林大學(xué)》2017年碩士論文

【摘要】：人類視覺神經(jīng)系統(tǒng)可以主觀地處理看到的自然場景,因?yàn)橛?jì)算能力的限制和高時(shí)效性的需求,處理過程會被簡化壓縮:視神經(jīng)會選擇場景中吸引其注意的部分目標(biāo)率先進(jìn)行理解,這種機(jī)制被稱作選擇性注意機(jī)制。反過來從能展示自然場景的圖像出發(fā),反映場景的圖像吸引視神經(jīng)的性質(zhì),被稱為視覺顯著性。因此,對人類視覺神經(jīng)系統(tǒng)進(jìn)行模擬,能夠構(gòu)造出圖像的顯著性目標(biāo)檢測模型�，F(xiàn)在,國內(nèi)外很多研究團(tuán)體都在致力于這一工作。本研究針對的圖像類型是自然場景類的圖像,從顏色空間對比度信息的角度深入探索,主要完成了以下工作:針對已有的基于色彩空間對比度信息的顯著性檢測方法進(jìn)行了優(yōu)化。已知減少顏色數(shù)量能夠極大加快算法運(yùn)行效率,指出已有方法在減少顏色數(shù)量上存在一定的瑕疵:簡單的把RGB三個(gè)通道各自進(jìn)行了量化限制,沒有從圖像整體的角度針對顏色統(tǒng)計(jì)進(jìn)行量化,這就有可能造成量化后圖像一定程度上的失真。明確問題后,提出把八叉樹運(yùn)用到顏色表示中,用以統(tǒng)計(jì)顏色出現(xiàn)頻率,進(jìn)而形成調(diào)色板完成顏色量化的工作。然后經(jīng)過直方圖加速和去噪平滑操作后得到最終的顯著圖,因?yàn)槭д媲闆r已有改善,故可以使顯著圖較原方法效果更好,而且因?yàn)槭褂昧税瞬鏄渌惴?在時(shí)間復(fù)雜度上也會有所優(yōu)化。將本文方法同幾種不同原理的經(jīng)典算法進(jìn)行了對比,結(jié)果證明本文方法效果較好,同時(shí)在時(shí)間成本上有一定優(yōu)勢。將模糊C均值聚類算法應(yīng)用于圖像處理中,根據(jù)聚類結(jié)果進(jìn)行分割。模糊C均值聚類(FCM)算法是一種基于模糊理論的軟聚類算法,將該算法應(yīng)用到圖像分割當(dāng)中,可以獲得比傳統(tǒng)硬聚類算法更好的效果。對比分析原始圖像進(jìn)行基于FCM算法的分割中選擇各個(gè)參數(shù)的不同情況,提出將顯著性檢測結(jié)果與基于FCM算法的分割過程相結(jié)合,通過結(jié)果證明,的確可以得到更好地效果。本文提出的方法可以勝任通用顯著性目標(biāo)檢測工作,且在效果和時(shí)間方面有較為出色的表現(xiàn);顯著性檢測與FCM圖像分割算法的結(jié)合應(yīng)用提升了兩者的效果;本文的工作可以作為圖像內(nèi)容感知和圖像檢索等應(yīng)用的基礎(chǔ)。
[Abstract]:The human visual nervous system can handle the natural scene subjectively, because of the limitation of computational power and the need for high timeliness, the process will be simplified: the optic nerve will choose the part of the scene that attracts attention in the scene to take the lead in understanding. This mechanism is called the selective attention mechanism. In turn, the natural field can be displayed. The image of the scene, which reflects the nature of the optic nerve, is called the visual significance. Therefore, it simulates the human visual nervous system and can construct a significant target detection model of the image. Now, many research groups at home and abroad are working on this work. The image type is a natural scene class. From the point of view of color space contrast information, the following work has been completed: the significant detection method based on the color space contrast information has been optimized. It is known that reducing the number of colors can greatly speed up the operation efficiency of the algorithm, and points out that the existing methods have some defects in reducing the number of colors. Fault: the quantitative restriction of the three channels of the RGB is simply carried out, and the color statistics are not quantified from the angle of the whole image. This may cause a certain degree of distortion of the quantized image. After the problem, the octree is applied to the color representation to count the frequency of color, and then the color palette is completed. The work of color quantization. Then after the histogram acceleration and de-noising smooth operation, the final significant graph is obtained, because the distortion has been improved, so the significant image can be better than the original method, and because of the octree algorithm, the time complexity will also be optimized. This method is the same with several different principles of the classic. The algorithm has been compared. The results show that the method has good effect and has some advantages in time cost. Fuzzy C means clustering algorithm is applied to image processing and segmentation according to clustering results. Fuzzy C mean clustering (FCM) algorithm is a soft clustering algorithm based on fuzzy theory, and the algorithm is applied to image segmentation. We can obtain better results than traditional hard clustering algorithms. Compare and analyze the different conditions of the selection of the original image based on FCM algorithm, the results are combined with the segmentation process based on the FCM algorithm, and the results prove that the results can be better. The method proposed in this paper can win. The work of universal significant target detection has been performed well in effect and time; the combination of significant detection and FCM image segmentation improves the effect of both. The work of this paper can be used as the basis for the application of image content perception and image retrieval.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 廖維猛;;線性八叉樹的鄰域?qū)ふ业男滤惴╗J];數(shù)字技術(shù)與應(yīng)用;2010年04期

2 張佳杰;黃海端;;基于密集型區(qū)域的八叉樹劃分算法[J];科技傳播;2012年02期

3 沈永增;劉東岳;徐均;;基于八叉樹的虛擬場景管理器的設(shè)計(jì)與實(shí)現(xiàn)[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2012年03期

4 劉璇;田麗亞;傅毓;梁艷艷;劉玉婷;;一種三維八叉樹等級歸并算法[J];現(xiàn)代制造工程;2012年09期

5 陳中原;溫來祥;賈金原;;基于八叉樹的輕量級場景結(jié)構(gòu)構(gòu)建[J];系統(tǒng)仿真學(xué)報(bào);2013年10期

6 許志明;線性八叉樹及其上的集合運(yùn)算[J];計(jì)算機(jī)工程;1987年03期

7 儲鴻慶;;一個(gè)粗加工用的八叉樹的方法[J];模具技術(shù);1990年04期

8 朱建飛，，沈錦林，顏暉;線性八叉樹的一種構(gòu)造算法[J];計(jì)算機(jī)工程與科學(xué);1994年01期

9 馬文華;從空間矩陣產(chǎn)生線性八叉樹編碼的算法[J];西南民族學(xué)院學(xué)報(bào)(自然科學(xué)版);1996年03期

10 賈根蓮;基于八叉樹的顏色減少方法[J];內(nèi)蒙古大學(xué)學(xué)報(bào)(自然科學(xué)版);1998年03期

相關(guān)會議論文 前2條

1 傅由甲;;動態(tài)八叉樹在復(fù)雜場景設(shè)計(jì)中的應(yīng)用[A];中國系統(tǒng)仿真學(xué)會第五次全國會員代表大會暨2006年全國學(xué)術(shù)年會論文集[C];2006年

2 陳瑜;蔡慶東;;基于樹網(wǎng)格的格子玻爾茲曼方法及其在滲流等問題中的應(yīng)用[A];第五屆全國青年計(jì)算物理學(xué)術(shù)交流會論文摘要[C];2008年

相關(guān)碩士學(xué)位論文 前5條

1 王昊;基于視覺顯著性和非監(jiān)督學(xué)習(xí)的目標(biāo)檢測[D];吉林大學(xué);2017年

2 楊霄鵬;基于動態(tài)八叉樹的三維離散元法鄰居搜索方法研究[D];吉林大學(xué);2007年

3 吳艷;基于八叉樹遍歷的幾何壓縮[D];中國科學(xué)院研究生院（軟件研究所）;2005年

4 丑強(qiáng);虛擬環(huán)境中基于八叉樹的碰撞檢測問題[D];吉林大學(xué);2007年

5 劉俸維;實(shí)時(shí)渲染系統(tǒng)MRRS的設(shè)計(jì)與實(shí)現(xiàn)[D];電子科技大學(xué);2004年

本文編號：1982893