In this paper, a solution for detecting scratches in old films and videos is presented. The focus is on automation and to enable fast, cost-effective processing of mass archives enabling a later reuse and repurposing.

Scratch detection supported by coherency analysis of motion vector fields

A complete system for old picture restoration is described: in particular, a frame alignment method, a simple deblotching algorithm and a nonlinear approach for contrast enhancement are proposed. The frame alignment uses a global motion compensation, with a logarithmic search for the correction vector. The blotch removal step consists of two stages. Blotches are first detected using two suitable morphological operators; the resulting pixel maps are merged and then validated using an estimate of the motion. Secondly, a multilevel median filter is used to replace sets of pixels identified as blotches. For contrast enhancement we use a rational unsharp masking technique which is able to effectively treat the high resolution images. To comply with the film properties the sharpening operator acts strongly in the dark regions and weakly in the bright ones. It can also reduce noise in homogeneous areas.

Blotches correction and contrast enhancement for old film pictures

Removing noise from the any processed images is very important. Noise should be removed in such a way that important information of image should be preserved. A decisionbased nonlinear algorithm for elimination of band lines, drop lines, mark, band lost and impulses in images is presented in this paper. The algorithm performs two simultaneous operations, namely, detection of corrupted pixels and evaluation of new pixels for replacing the corrupted pixels. Removal of these artifacts is achieved without damaging edges and details. However, the restricted window size renders median operation less effective whenever noise is excessive in that case the proposed algorithm automatically switches to mean filtering. The performance of the algorithm is analyzed in terms of Mean Square Error [MSE], Peak-Signal-to-Noise Ratio [PSNR], Signal-to-Noise Ratio Improved [SNRI], Percentage Of Noise Attenuated [PONA], and Percentage Of Spoiled Pixels [POSP]. This is compared with standard algorithms already in use and improved performance of the proposed algorithm is presented. The advantage of the proposed algorithm is that a single algorithm can replace several independent algorithms which are required for removal of different artifacts. Keywords—Filtering, Decision Based Algorithm, noise, image restoration.

Adaptive Non-linear Filtering Technique for Image Restoration

A decision-based nonlinear algorithm for removal of strip lines, drop lines, blotches, band missing, and impulses in images is presented. The algorithm performs two simultaneous operations, namely, detection of corrupted pixels and estimation of new pixels for replacing the corrupted pixels. Removal of these artifacts is achieved without damaging edges and details. The algorithm uses an adaptive length window whose maximum size is 5 × 5 to avoid blurring due to large window sizes. However, the restricted window size renders median operation less effective whenever noise is excessive in which case the proposed algorithm automatically switches to mean filtering. The performance of the algorithm is analyzed in terms of mean square error [MSE], peak-signal-to-noise ratio [PSNR], and image enhancement factor [IEF] and compared with standard algorithms already in use. Improved performance of the proposed algorithm is demonstrated. The advantage of the proposed algorithm is that a single algorithm can replace several independent algorithms required for removal of different artifacts.

https://link.springer.com/content/pdf/10.1155%2F2008%2F485921.pdf

A Nonlinear Decision-Based Algorithm for Removal of Strip Lines, Drop Lines, Blotches, Band Missing and Impulses in Images and Videos

We propose a novel framework which is aimed to process gray images. By appropriately converting digital colors to intuitionistic fuzzy numbers in a generalized framework, the algorithm tends to remove noise impairments while processing the damaged images. A new entropy measure on intuitionistic fuzzy sets is introduced for determining the uncertainty of each pixel and consequently, to recognize the best processed image which has the least noise. We conclude by discussing two illustrative examples for verifying the developed approach.

Removing noise in a digital image using a new entropy method based on intuitionistic fuzzy sets

Line scratches and blotches are two of the most common and annoying artifacts of image sequences. A digital restoration chain for the removal of these artifacts was conceived and implemented. The basic elements of the chain are the digital encoder, the artifact generator, the artifact detectors, the interpolators and the quality measurer. The digital encoder has the mission to convert analogue sequences into digital ones and, if necessary, to make a format conversion. The artifact generator allows quantitative and qualitative tests of the restoration algorithms. If we have access to the original non-degraded sequence we can add, in a controlled way, artifacts with the generator, and then measure efficiently the quality of the restoration algorithms, since we have the original, the degraded and the restored sequences to compare. In a real restoration process, the degraded sequence is directly applied to the artifact detector. The artifact detector finds the degraded regions in the image and, somehow, marks them. The interpolator replaces the marked degraded pixels with others that are the result of an interpolation algorithm. Finally, the quality measurer rates the quality of the restored sequence.

/pdf/removal-of-blotches-and-line-scratches-from-film-and-video-2upvmc9frf.pdf

Alexandre Ulisses Silva

Papers

Removal of blotches and line scratches from film and video sequences using a digital restoration chain.