An Enhanced Video Inpainting Technique with Grey Wolf Optimization for Object Removal Application

Abstract

Video inpainting is the most trending research topic from the last decade. Video inpainting is the process of restoring the damaged parts of the vintage video or the filling of the regions by removing the unwanted objects with sophisticated techniques. The video inpainting is achieved by dividing the video into frames and the motion of the moving objects in the frames are tracked by applying the motion tracking method. The existing inpainting method proposed by the Criminisi, neglected the local similarities in the images so it suffered from dropping effect in the priority computation. This paper proposed a new priority computation method by introducing gradient operation with the addition of curvature in the data term and local structure measurement function with structure tensor theory as an additional term. Later, the patch matching is achieved with the Sum of Absolute Difference (SAD) distance method. Further, the optimal patch is selected by applying the Grey Wolf Optimization (GWO) algorithm. The efficiency of the proposed video inpainting technique is evaluated with the performance metrics, viz., Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), and Edge Similarity (ESIM) executed in MATLAB. The PSNR and SSIM of the proposed method for Fontaine_chatelet video is improved by 18.9% and 4.19% than existing method. The proposed method is compared with other existing methods also and it outperformed the existing methods.

Development of Image Inpainting for object removal using Enhanced Patch Priority and Matching Measures

“…Zhang et al [16] employed the combination of mean squared diffrerence and square of mean differences as a similarity metric to find the exemplar patch. The video inpainting using exemplar based methods are also evevated in recent years [17][18][19][20][21][22][23][24]. This study aimed to determine highest priority patch enhanced method to avoid dropping effect and new patch selection proces that yield favorable inpainting outcomes.…”

Adaptive Optimized Discriminative Learning based Image Deblurring using Deep CNN

“…Whereas MLP [9], SRCNN [10] and DCNN [11] are some of the discriminative learning approaches used for the above applications with the help of different training methods. Discriminative approaches have very fast testing speed but with the loss of flexibility, but optimization model-based approaches are generally time consuming with sophisticated estimation of priors to achieve excellent performance [10][11][12][13][14]. Consequently, considering the integration of these two approaches in an efficient manner to deblur the given degraded images is still a challenging task.…”