本文關(guān)鍵詞： 自動(dòng)圖像分割 前景關(guān)鍵點(diǎn) 局部形狀匹配 星形形狀先驗(yàn) 剪影風(fēng)格化　出處：《北京交通大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：圖像分割是計(jì)算機(jī)視覺、模式識(shí)別和數(shù)字圖像處理領(lǐng)域的熱點(diǎn)研究問題。圖像分割可分為交互式分割和自動(dòng)分割兩大類別。近年來,交互式分割雖然取得了很大的進(jìn)展,但是處理大量圖片時(shí)存在操作復(fù)雜、耗時(shí)耗力、對(duì)交互區(qū)域敏感等問題,因此自動(dòng)分割方法受到研究者的廣泛關(guān)注。為此,本文設(shè)計(jì)了一種自動(dòng)圖像分割算法,通過顯著性檢測(cè)算法和局部形狀匹配算法自動(dòng)檢測(cè)前景的關(guān)鍵點(diǎn),并將其應(yīng)用到星形先驗(yàn)分割算法中,從而實(shí)現(xiàn)了圖像的自動(dòng)分割。本文主要內(nèi)容和創(chuàng)新點(diǎn)如下:(1)前景關(guān)鍵點(diǎn)的提取對(duì)圖像自動(dòng)分割起決定性作用。為了自動(dòng)標(biāo)記圖像前景,提出了一種基于局部形狀匹配的前景關(guān)鍵點(diǎn)提取方法。該方法采用局部形狀匹配來自動(dòng)標(biāo)記前景,并與基于顯著性檢測(cè)的前景標(biāo)記方法相結(jié)合,能檢測(cè)出更多的前景關(guān)鍵點(diǎn),有利于后續(xù)的自動(dòng)分割。(2)分割時(shí)結(jié)合形狀先驗(yàn)知識(shí)能提高圖像分割的準(zhǔn)確性。星形形狀是一種普適的先驗(yàn)知識(shí),適用于自然界中的很多物體。本文實(shí)現(xiàn)了一種結(jié)合多星形形狀先驗(yàn)的Graph Cuts分割算法,有效地提高了分割質(zhì)量。(3)將提出的圖像自動(dòng)分割算法應(yīng)用于圖像的特效處理中,提出了一種基于樣例的圖像剪影風(fēng)格化算法。該算法在圖像分割的基礎(chǔ)上,對(duì)前景和背景采取不同的色調(diào)處理策略,使生成的圖像具有與樣例圖像類似的風(fēng)格。實(shí)驗(yàn)結(jié)果驗(yàn)證了方法的有效性。
[Abstract]:Image segmentation is a hot research problem in the field of computer vision, pattern recognition and digital image processing. Image segmentation can be divided into two categories: interactive segmentation and automatic segmentation. Although great progress has been made in interactive segmentation, there are some problems such as complicated operation, time-consuming and labor-consuming, sensitive to interactive region, etc., so automatic segmentation method has been widely concerned by researchers. In this paper, an automatic image segmentation algorithm is designed, which detects the key points of the foreground automatically by the salience detection algorithm and the local shape matching algorithm, and applies it to the star prior segmentation algorithm. The main content and innovation of this paper are as follows: 1) extraction of foreground key points plays a decisive role in automatic image segmentation. In order to automatically mark the image foreground. This paper presents a method of extracting the key points of foreground based on local shape matching, which uses local shape matching to mark the foreground automatically, and combines with the foreground marking method based on salience detection. It can detect more foreground key points and can improve the accuracy of image segmentation by combining shape priori knowledge with subsequent automatic segmentation. Star shape is a kind of universal prior knowledge. It is suitable for many objects in nature. In this paper, a Graph Cuts segmentation algorithm combining multi-star shape priori is implemented. The proposed automatic image segmentation algorithm is applied to the special effect processing of the image. An image silhouette stylization algorithm based on sample is proposed. Based on image segmentation, different hue processing strategies are adopted for foreground and background. The generated image has a similar style to the sample image. The experimental results show that the method is effective.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 楊建功;汪西莉;李虎;;融合Kernel PCA形狀先驗(yàn)信息的變分圖像分割模型[J];中國圖象圖形學(xué)報(bào);2015年08期

2 陳添丁;金煒煒;陳英旦;徐先力;余長宏;;輪廓線優(yōu)化的多通道三維水墨渲染模型[J];電子與信息學(xué)報(bào);2015年02期

3 黃華;程威;;實(shí)時(shí)圖像素描風(fēng)格化[J];計(jì)算機(jī)學(xué)報(bào);2009年10期

4 李旭超;朱善安;;圖像分割中的馬爾可夫隨機(jī)場(chǎng)方法綜述[J];中國圖象圖形學(xué)報(bào);2007年05期

5 周仁琴;周經(jīng)野;陳益強(qiáng);劉軍發(fā);;基于特征發(fā)現(xiàn)的卡通人臉肖像生成[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2006年09期

6 趙國英,向世明,李華;高階矩在顏色傳輸中的應(yīng)用[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2004年01期

，

本文編號(hào)：1473239