Dual‐tree complex wavelet transform and super‐resolution based video inpainting application to object removal and error concealment

Tudavekar, Gajanan; Patil, Sanjay R.; Saraf, Santosh S.

doi:10.1049/trit.2019.0045

Cited by 11 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though the exemplar-based classical object removal technique offers advantages such as the capacity to keep image texture and structure characteristics as well as image clarity, it fails to retain the graphical fidelity of inpainted images [85]. To address these shortcomings, the creators of [86] developed a two-stage approach. The dualtree complex wavelet transform is used in the first stage to get sub-bands of wavelets from a low-resolution image.…”

Section: Object Removalmentioning

confidence: 99%

Pareto Optimized Large Mask Approach for Efficient and Background Humanoid Shape Removal

et al. 2023

View full text Add to dashboard Cite

We introduce deep learning-based methodology for removing unwanted human-like shapes in videos. The method uses Pareto-optimized Generative Adversarial Networks (GANs) technology, which is a novel contribution. The system automatically selects the Region of Interest (ROI) for each humanoid shape and uses a skeleton detection module to determine which humanoid shape to retain. The semantic masks of human like shapes are created using a semantic-aware occlusion-robust model that has four primary components: feature extraction, and local, global, and semantic branches. The global branch encodes occlusion-aware information to make the extracted features resistant to occlusion, while the local branch retrieves fine-grained local characteristics. A modified big mask inpainting approach is employed to eliminate a person from the image, leveraging Fast Fourier convolutions and utilizing polygonal chains and rectangles with unpredictable aspect ratios. The inpainter network takes the input image and the mask to create an output image excluding the background humanoid shapes. The generator uses an encoder-decoder structure with included skip connections to recover spatial information and dilated convolution and squeeze and excitation blocks to make the regions behind the humanoid shapes consistent with their surroundings. The discriminator avoids dissimilar structure at the patch scale, and the refiner network catches features around the boundaries of each background humanoid shape. The method is evaluated on two video object segmentation datasets (DAVIS and YouTube-VOS) and a database of 66 distinct video sequences of people behind a desk in an office environment. The efficiency was assessed using the Structural Similarity Index Measure (SSIM), Frechet Inception Distance (FID), and Learned Perceptual Image Patch Similarity (LPIPS) metrics and showed promising results in fully automated background person removal task.

show abstract

Section: Object Removalmentioning

confidence: 99%

Pareto Optimized Large Mask Approach for Efficient and Background Humanoid Shape Removal

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Vignesh et al [20] presented a technique for image quality assessment (IQA) using CNN to take the person's best image. Tudavekar et al [21] proposed video inpainting to fill the missing regions in a video by dual-tree complex wavelet transformation.…”

Section: Average-based Face Modelmentioning

confidence: 99%

A Real-Time Framework for Human Face Detection and Recognition in CCTV Images

Ullah

Hayat

Siddiqui

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper aims to develop a machine learning and deep learning-based real-time framework for detecting and recognizing human faces in closed-circuit television (CCTV) images. The traditional CCTV system needs a human for 24/7 monitoring, which is costly and insufficient. The automatic recognition system of faces in CCTV images with minimum human intervention and reduced cost can help many organizations, such as law enforcement, identifying the suspects, missing people, and people entering a restricted territory. However, image-based recognition has many issues, such as scaling, rotation, cluttered backgrounds, and variation in light intensity. This paper aims to develop a CCTV image-based human face recognition system using different techniques for feature extraction and face recognition. The proposed system includes image acquisition from CCTV, image preprocessing, face detection, localization, extraction from the acquired images, and recognition. We use two feature extraction algorithms, principal component analysis (PCA) and convolutional neural network (CNN). We use and compare the performance of the algorithms K-nearest neighbor (KNN), decision tree, random forest, and CNN. The recognition is done by applying these techniques to the dataset with more than 40K acquired real-time images at different settings such as light level, rotation, and scaling for simulation and performance evaluation. Finally, we recognized faces with a minimum computing time and an accuracy of more than 90%.

show abstract

“…Simultaneously, the output is forced to be temporally reliable with a temporal memory and recurrent feedback model. Tudavekar et al [10] proposed a new 2 phase architecture. Initially, subbands of wavelets of lower resolution images are attained by the dual tree complex WT.…”

Section: Literature Reviewmentioning

confidence: 99%

An Efficient Video Inpainting Approach Using Deep Belief Network

Srinivasan¹,

Chinnadurai²

2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

The video inpainting process helps in several video editing and restoration processes like unwanted object removal, scratch or damage rebuilding, and retargeting. It intends to fill spatio-temporal holes with reasonable content in the video. Inspite of the recent advancements of deep learning for image inpainting, it is challenging to outspread the techniques into the videos owing to the extra time dimensions. In this view, this paper presents an efficient video inpainting approach using beetle antenna search with deep belief network (VIA-BASDBN). The proposed VIA-BASDBN technique initially converts the videos into a set of frames and they are again split into a region of 5*5 blocks. In addition, the VIA-BASDBN technique involves the design of optimal DBN model, which receives input features from Local Binary Patterns (LBP) to categorize the blocks into smooth or structured regions. Furthermore, the weight vectors of the DBN model are optimally chosen by the use of BAS technique. Finally, the inpainting of the smooth and structured regions takes place using the mean and patch matching approaches respectively. The patch matching process depends upon the minimal Euclidean distance among the extracted SIFT features of the actual and references patches. In order to examine the effective outcome of the VIA-BASDBN technique, a series of simulations take place and the results denoted the promising performance.

show abstract

Dual‐tree complex wavelet transform and super‐resolution based video inpainting application to object removal and error concealment

Cited by 11 publications

References 42 publications

Pareto Optimized Large Mask Approach for Efficient and Background Humanoid Shape Removal

Pareto Optimized Large Mask Approach for Efficient and Background Humanoid Shape Removal

A Real-Time Framework for Human Face Detection and Recognition in CCTV Images

An Efficient Video Inpainting Approach Using Deep Belief Network

Contact Info

Product

Resources

About