本文選題：顯著檢測(cè)　切入點(diǎn)：全局顏色對(duì)比　出處：《中國(guó)圖象圖形學(xué)報(bào)》2017年09期

【摘要】：目的為了解決圖像顯著性檢測(cè)中存在的邊界模糊,檢測(cè)準(zhǔn)確度不夠的問(wèn)題,提出一種基于目標(biāo)增強(qiáng)引導(dǎo)和稀疏重構(gòu)的顯著檢測(cè)算法(OESR)。方法基于超像素,首先從前景角度計(jì)算超像素的中心加權(quán)顏色空間分布圖,作為前景顯著圖;由圖像邊界的超像素構(gòu)建背景模板并對(duì)模板進(jìn)行預(yù)處理,以?xún)?yōu)化后的背景模板作為稀疏表示的字典,計(jì)算稀疏重構(gòu)誤差,并利用誤差傳播方式進(jìn)行重構(gòu)誤差的校正,得到背景差異圖;最后,利用快速目標(biāo)檢測(cè)方法獲取一定數(shù)量的建議窗口,由窗口的對(duì)象性得分計(jì)算目標(biāo)增強(qiáng)系數(shù),以此來(lái)引導(dǎo)兩種顯著圖的融合,得到最終顯著檢測(cè)結(jié)果。結(jié)果實(shí)驗(yàn)在公開(kāi)數(shù)據(jù)集上與其他12種流行算法進(jìn)行比較,所提算法對(duì)具有不同背景復(fù)雜度的圖像能夠較準(zhǔn)確的檢測(cè)出顯著區(qū)域,對(duì)顯著對(duì)象的提取也較為完整,并且在評(píng)價(jià)指標(biāo)檢測(cè)上與其他算法相比,在MSRA10k數(shù)據(jù)集上平均召回率提高4.1%,在VOC2007數(shù)據(jù)集上,平均召回率和F檢驗(yàn)分別提高18.5%和3.1%。結(jié)論本文提出一種新的顯著檢測(cè)方法,分別利用顏色分布與對(duì)比度方法構(gòu)建顯著圖,并且在顯著圖融合時(shí)采用一種目標(biāo)增強(qiáng)系數(shù),提高了顯著圖的準(zhǔn)確性。實(shí)驗(yàn)結(jié)果表明,本文算法能夠檢測(cè)出更符合視覺(jué)特性的顯著區(qū)域,顯著區(qū)域更加準(zhǔn)確,適用于自然圖像的顯著性目標(biāo)檢測(cè)、目標(biāo)分割或基于顯著性分析的圖像標(biāo)注。
[Abstract]:Aim in order to solve the problem of edge blur and poor detection accuracy in image salience detection, a significant detection algorithm based on target enhancement guidance and sparse reconstruction is proposed. The method is based on super-pixel. Firstly, the center weighted color space distribution of the super-pixel is calculated from the perspective of the foreground, and the background template is constructed by the super-pixel of the edge of the image, and the template is preprocessed, and the optimized background template is used as the sparse representation dictionary. The sparse reconstruction error is calculated, and the error propagation is used to correct the reconstruction error, and the background difference map is obtained. Finally, a certain number of suggested windows are obtained by using the fast target detection method. The object enhancement coefficient is calculated from the object score of the window to guide the fusion of the two salient graphs, and the final significant detection results are obtained. Results the experiment is compared with the other 12 popular algorithms on the open data set. The proposed algorithm can detect salient regions accurately for images with different background complexity, and extract salient objects more completely, and compared with other algorithms in evaluation index detection. The average recall rate on the MSRA10k dataset was increased by 4.1%, and the average recall rate and F test on the VOC2007 dataset were increased by 18.5% and 3.1%, respectively. Conclusion A new significant detection method is proposed in this paper, which uses the color distribution and contrast method to construct the salient map, respectively. The accuracy of salient map is improved by using a target enhancement coefficient in the fusion of salient map. The experimental results show that the proposed algorithm can detect the salient region more in accordance with visual characteristics, and the salient region is more accurate. It can be used to detect salient targets, segment objects or annotate images based on salience analysis.
【作者單位】： 遼寧工程技術(shù)大學(xué)軟件學(xué)院;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(61172144) 遼寧省教育廳科學(xué)技術(shù)研究一般基金項(xiàng)目(L2015216)~~
【分類(lèi)號(hào)】：TP391.41
，

本文編號(hào)：1676333