Editing Algorithm Research Articles

Image editing with varying intensities of processing

Current image editing algorithms prevailingly involve specific processing intensities. After the network training phase, the definite mapping is carried on testing images, which leads to under- or over-editing in certain cases. However, for many real problems, having access to diverse intensities of processing of the output is preferable. The hypothesis is that the part of parameters that correspond to the intensity of processing of the network are implicitly embedded in the whole parameter set and can be explicitly extracted and utilized, even with limited supervision. In this paper, we introduce the concept of Intensity of Processing, termed as IP, and propose image editing with Varying Intensities of Processing, termed as VIP. Given the input and corresponding fully-edited output, we would like to not only figure out the particular mapping from input to output, but also be able to obtain multiple continuous intermediate states with in-between intensities of processing. Refer to the network that deals with the original image editing operation as Base Network. By adding an extra module, which we call Condition Encoder, to condition and regulate the Base Network, we make the whole image editing process controllable. Moreover, we develop a triplet loss and construct the sequentiality of generated intermediate states with limited supervision. A significant advantage of our method is that it does not require groundtruth images of the middle states during training, which substantially relaxes the range of applicable problems. Extensive experiments demonstrate the effectiveness and potentiality of the proposed framework; discussion and future work are also provided.

Efficacy and Safety of Self-Titration Algorithms of Insulin Glargine 300 units/mL in Individuals with Uncontrolled Type 2 Diabetes Mellitus (The Korean TITRATION Study): A Randomized Controlled Trial.

BackgroundTo compare the efficacy and safety of two insulin self-titration algorithms, Implementing New Strategies with Insulin Glargine for Hyperglycemia Treatment (INSIGHT) and EDITION, for insulin glargine 300 units/mL (Gla-300) in Korean individuals with uncontrolled type 2 diabetes mellitus (T2DM).MethodsIn a 12-week, randomized, open-label trial, individuals with uncontrolled T2DM requiring basal insulin were randomized to either the INSIGHT (adjusted by 1 unit/day) or EDITION (adjusted by 3 units/week) algorithm to achieve a fasting self-monitoring of blood glucose (SMBG) in the range of 4.4 to 5.6 mmol/L. The primary outcome was the proportion of individuals achieving a fasting SMBG ≤5.6 mmol/L without nocturnal hypoglycemia at week 12.ResultsOf 129 individuals (age, 64.1±9.5 years; 66 [51.2%] women), 65 and 64 were randomized to the INSIGHT and EDITION algorithms, respectively. The primary outcome of achievement was comparable between the two groups (24.6% vs. 23.4%, P=0.876). Compared with the EDITION group, the INSIGHT group had a greater reduction in 7-point SMBG but a similar decrease in fasting plasma glucose and glycosylated hemoglobin. The increment of total daily insulin dose was significantly higher in the INSIGHT group than in the EDITION group (between-group difference: 5.8±2.7 units/day, P=0.033). However, body weight was significantly increased only in the EDITION group (0.6±2.4 kg, P=0.038). There was no difference in the occurrence of hypoglycemia between the two groups. Patient satisfaction was significantly increased in the INSIGHT group (P=0.014).ConclusionThe self-titration of Gla-300 using the INSIGHT algorithm was effective and safe compared with that using the EDITION algorithm in Korean individuals with uncontrolled T2DM (ClinicalTrials.gov number: NCT03406663).

Bio‐signal‐processing‐based convolutional neural networks model for music program scene editing

SummaryPopular songs have evolved from vinyl records (voice files) to music videos. Sound and video can be mixed and presented in such a manner that only sound is heard. Scenes from music programs require continuous editing to maximize audience immersion. Music program scene editing is developed through the expertise of a television program director (PD). The PD considers detailed editing methods by the analyzing lyrics and the singer's choreography to express a song in a rhythmic video. This study presents an algorithm for music program scene editing that determines the size of a shot, evaluating the psychological distance between singer and viewers after measuring the pitch contour of a song.

Deep Learning-Based Forgery Attack on Document Images

With the ongoing popularization of online services, the digital document images have been used in various applications. Meanwhile, there have emerged some deep learning-based text editing algorithms which alter the textual information of an image . In this work, we present a document forgery algorithm to edit practical document images. To achieve this goal, the limitations of existing text editing algorithms towards complicated characters and complex background are addressed by a set of network design strategies. First, the unnecessary confusion in the supervision data is avoided by disentangling the textual and background information in the source images. Second, to capture the structure of some complicated components, the text skeleton is provided as auxiliary information and the continuity in texture is considered explicitly in the loss function. Third, the forgery traces induced by the text editing operation are mitigated by some post-processing operations which consider the distortions from the print-and-scan channel. Quantitative comparisons of the proposed method and the exiting approach have shown the advantages of our design by reducing the about 2/3 reconstruction error measured in MSE, improving reconstruction quality measured in PSNR and in SSIM by 4 dB and 0.21, respectively. Qualitative experiments have confirmed that the reconstruction results of the proposed method are visually better than the existing approach. More importantly, we have demonstrated the performance of the proposed document forgery algorithm under a practical scenario where an attacker is able to alter the textual information in an identity document using only one sample in the target domain. The forged-and-recaptured samples created by the proposed text editing attack and recapturing operation have successfully fooled some existing document authentication systems.

Differentiable vector graphics rasterization for editing and learning

We introduce a differentiable rasterizer that bridges the vector graphics and raster image domains, enabling powerful raster-based loss functions, optimization procedures, and machine learning techniques to edit and generate vector content. We observe that vector graphics rasterization is differentiable after pixel prefiltering. Our differentiable rasterizer offers two prefiltering options: an analytical prefiltering technique and a multisampling anti-aliasing technique. The analytical variant is faster but can suffer from artifacts such as conflation. The multisampling variant is still efficient, and can render high-quality images while computing unbiased gradients for each pixel with respect to curve parameters. We demonstrate that our rasterizer enables new applications, including a vector graphics editor guided by image metrics, a painterly rendering algorithm that fits vector primitives to an image by minimizing a deep perceptual loss function, new vector graphics editing algorithms that exploit well-known image processing methods such as seam carving, and deep generative models that generate vector content from raster-only supervision under a VAE or GAN training objective.

110-LB: The Korean Titration: A Randomized Controlled Trial to Evaluate the Efficacy and Safety of Self-Titration Algorithms of Insulin Glargine 300 Units/ml in Patients with Uncontrolled Type 2 Diabetes

Background: In the Canadian TITRATION study, the INSIGHT algorithm was as effective as the EDITION algorithm for insulin dose titration in patients with type 2 diabetes. However, these algorithms have not been evaluated in Asian patients. Objective: To compare the efficacy and safety of two algorithms, the INSIGHT and EDITION, for insulin glargine 300 units/mL (Gla-300) in patients with uncontrolled type 2 diabetes treated with basal insulin Methods: The Korean TITRATION was a 12-week, single-center, open-label, randomized, treat-to-target, and pragmatic trial. We randomly assigned 130 patients to either the INSIGHT (self-titration by 1 unit/day) or EDITION (self-titration no more than every 3 days) groups to achieve a fasting self-monitored blood glucose (SMBG) in the range of 4.4 to 5.6 mmol/L. The primary endpoint was a proportion of patients reaching fasting SMBG ≤5.6 mmol/L without hypoglycemia. Results: A total of 129 patients were included in the study. At week 12, patients achieving the primary endpoint were 24.6% (INSIGHT) and 23.4% (EDITION) (P = 0.961). Fasting SMBG were 102.0 mg/dL (INSIGHT) and 111.2 mg/dL (EDITION) (P = 0.110). Proportions of patients with HbA1c ≤7% were 23.1% (INSIGHT) and 20.3% (EDITION) (P = 0.867). There was no difference in changes in fasting plasma glucose, HbA1c, and body weight between the two groups. Mean changes in total daily insulin doses were significantly higher in the INSIGHT group than in the EDITION group (12.83 units/day vs. 6.81 units/day, P = 0.030). However, the incidence of hypoglycemia was comparable between the two groups. In addition, adherence to the algorithm tended to be higher in the INSIGHT group than in the EDITION group (45.7% vs. 35.9%, P = 0.109). Conclusion: The self-titration of Gla-300 with the INSIGHT algorithm is effective and safe compared to that with the EDITION algorithm in Korean patients with uncontrolled type 2 diabetes. Disclosure J. Bae: None. C. Ahn: None. Y. Yang: None. S. Moon: None. S. Kwak: None. H. Jung: None. K. Park: None. Y. Cho: None.

Harnessing semantic segmentation masks for accurate facial attribute editing

SummaryIn recent years, with the rapid development of adversarial learning technology, facial attribute editing has made great success in a number of areas. Realistic visual effect, invariant identity information, and accurate editing area are the three key issues of facial attribute editing. Unfortunately, most researches focus on the former two problems. However, lack of awareness of the accurate editing area in the task is the main reason for damaging attribute‐irrelevant details. To address this issue, this article proposes a novel facial attribute editing algorithm—a generative adversarial network (GAN) with semantic masks—from the perspective of editing location accuracy. By generating the mask with respect to attribute‐related areas, the semantic segmentation network can only constrain the manipulation in the target region while not harming any attribute‐irrelevant details. The GAN is then combined with the semantic segmentation network to formulate the entire framework, which is referred to as SM‐GAN. Extensive experiments on the public datasets CelebA and LFWA prove that the presented method can not only ensure that the attribute manipulation is realistic, but also allow attribute‐irrelevant regions to remain unchanged. Moreover, it can also simultaneously edit multiple facial attributes.

A comparison of automated and manual sleep staging and respiratory event recognition in a portable sleep diagnostic device with in-lab sleep study.

The objectives were to develop and validate an algorithm for editing WatchPAT scoring and assess the accuracy in an unselected clinical population as well as age and sex substrata. Two hundred sixty-two participants were enrolled to undergo WatchPAT simultaneously with in-lab polysomnography (PSG) recordings for developing (n = 30), optimizing (n = 62), and validating (n = 170) an algorithm to review and edit respiratory events and sleep architecture of WatchPAT recordings, which was based on visual inspection of WatchPAT signals. Apnea-hypopnea index (AHI) and sleep indices were compared with PSG-derived and automated WatchPAT indices. Although estimation of total sleep time (TST) was comparable between automated and manual algorithm, estimation of rapid eye movement (REM) sleep time was markedly improved with manual editing from 0.48, 23.0 min (-43.9 to 89.8) to 0.64, 18.3 min (-32.6 to 69.1) (correlation with PSG, mean difference [reference range] from PSG, respectively). Manual scoring also improved correlation and agreement with PSG AHI from 0.65, 2.5 events/h (-24.0 to 28.9) to 0.81, -4.5 events/h (-22.5 to 13.6) as well as concordance for categorical agreement of sleep-disordered breathing severity and concordance for detecting severe REM-related sleep-disordered breathing. Interscorer reliabilities were excellent for TST and AHI, while good for REM sleep time. The automated algorithm performed better in younger than in older patients, while performed similarly between men and women with respect to concordance statistics. The manual algorithm markedly improved concordances more in older patients and women than in their counterparts. Our manual editing algorithm improves correlation and agreement with PSG-derived sleep and breathing indices. Sex and age influence the accuracy of automated analysis and the performance of manual editing on AHI concordance.

Simplifying TugGraph using zipping algorithms

Graphs are an invaluable modelling tool in many domains, but visualising large graphs in their entirety can be difficult. Hierarchical graph visualisation – recursively clustering a graph’s nodes to view it at a higher level of abstraction – has thus become popular. However, this can hide important information that a user needs to understand a graph’s topology, e.g. nodes’ neighbourhoods. TugGraph addressed this by ‘separating out’ a given node’s neighbours from their hierarchy ancestors to visualise them independently. Its original implementation was straightforward, but copied parts of the hierarchy, making it slow and memory-hungry. An optimised later version, which we refer to as FastTug, avoided this, but at a cost in clarity. Optimising TugGraph without sacrificing clarity is difficult because of the need to keep every hierarchy node connected, a common challenge for graph hierarchy editing algorithms. Recently, this problem has been addressed by ‘zipping’ algorithms, multi-level split/merge algorithms that preserve hierarchy node connectedness and can be built upon for higher-level editing. In this paper, we generalise the original unzipping algorithms to implement SimpleTug, a simple, modular version of TugGraph that is easy to understand and implement, and even faster and more memory-efficient than FastTug. We formally prove its equivalence to FastTug, and show how both can be parallelised. Using our millipede hierarchical image segmentation system, we show experimentally that both the serial and parallel versions of SimpleTug are around 25% faster than their FastTug counterparts, whilst using considerably less memory. Finally, we discuss the interesting theoretical connections between TugGraph and zipping, and suggest ideas for further work.

ELS: A Fast Parameter-Free Edition Algorithm With Natural Neighbors-Based Local Sets for k Nearest Neighbor

The instance reduction is one of the data preprocessing methods and aims to remove noises and (or) redundant instances from the training set. In the instance reduction, one of the most representative techniques is the edition method which can remove harmful instances from the training set to improve the prediction accuracy of k nearest neighbor (KNN). Nevertheless, most of existing edition methods still have some drawbacks, such as the parameter dependency, high computational time and relatively low accuracy. To solve these problems, we present a new fast parameter-free edition method based on local sets with natural neighbors (ELS). In ELS, we define a new concept of local sets by introducing natural neighbors. ELS can use the local sets to keep more reasonable class boundaries and effectively filtering out noisy instances (including global outliers). The main advantages of ELS are that (a) it is parameter-free; (b) it can remove global outliers and noisy instances; (c) it is relatively fast. Experiments clearly verify that (a) ELS outperforms existing representative edition methods in improving the prediction accuracy of KNN; (b) ELS can improve the performance of the condensation method and hybrid method in terms of both accuracy and reduction; (c) ELS consumes relatively low running time.

Developing a Parametric 3D Face Model Editing Algorithm

In the fields of computer graphics and computer vision, a great amount of research and analysis has been conducted on expression-carrying face models. How to construct more realistic and effective 3D face models has become an immense challenge to researchers. This paper proposes a parametric 3D face model editing algorithm based on existing 3D face models. The algorithm takes a number of existing 3D face models with different expressions as input, edits the models through mostly through model deformation and interpolation, and generates a new 3D face model. In particular, the face model editing process begins with selecting multiple face models with different expressions as input. Second, with one of the selected models as the source model and others as the target models, the source model and all target models are registered one by one; meanwhile, the vertex correspondence between the registered models is established. Third, the selected 3D models are parameterized to a planar disc through quasi-conformal mapping. Fourth, relying on the vertex correspondence, a set of corresponding control points between different models are established. The model is then deformed and interpolated under the guidance of the control points and by using the quasi-conformal iteration method, which produces the 2D face models with transitional expressions between the source model and the target models. Finally, the 2D models are restored to the corresponding 3D face models using the model restoration algorithm. Additionally, this paper proposes to use the Beltrami coefficient to guide the quasi-conformal iteration in performing the mapping between two planes. This coefficient then serves as a measure to evaluate the similarity between the edited model and the original one. The proposed algorithm has been evaluated through extensive experiments. The results suggest that compared with existing editing methods, the proposed method is more effective and efficient in constructing various 3D face models.

Screen-Shooting Resilient Watermarking

This paper proposes a novel screen-shooting resilient watermarking scheme, which means that if the watermarked image is displayed on the screen and the screen information is captured by the camera, we can still extract the watermark message from the captured photo. To realize such demands, we analyzed the special distortions caused by the screen-shooting process, including lens distortion, light source distortion, and moire distortion. To resist the geometric deformation caused by lens distortion, we proposed an intensity-based scale-invariant feature transform (I-SIFT) algorithm which can accurately locate the embedding regions. As for the loss of image details caused by light source distortion and moire distortion, we put forward a small-size template algorithm to repeatedly embed the watermark into different regions, so that at least one complete information region can survive from distortions. At the extraction side, we designed a cross-validation-based extraction algorithm to cope with repeated embedding. The validity and correctness of the extraction method are verified by hypothesis testing. Furthermore, to boost the extraction speed, we proposed a SIFT feature editing algorithm to enhance the intensity of the keypoints, based on which, the extraction accuracy and extraction speed can be greatly improved. The experimental results show that the proposed watermarking scheme achieves high robustness for screen-shooting process. Compared with the previous schemes, our algorithm provides significant improvement in robustness for screen-shooting process and extraction efficiency.

СОЗДАНИЕ ЛАБИРИНТА С НЕСКОЛЬКИМИ ПРОХОДАМИ, ПОИСК ВСЕХ ПУТЕЙ В НЕМ И ИХ РЕДАКТИРОВАНИЕ

This article considers the problem of creating a maze with multiple solutions, searching for all solutions and a possibility of editing them. First, we view two algorithms, which generate the most various mazes, and find their positive and negative sides. Then we choose the one most efficient and suitable for the problem. All maze creation algorithms, including two considered, are unable to reveal a definite number of solutions. Here we offer a modification of Wilsons algorithm. Still we tend to think that all maze solving algorithms cannot find all possible solutions. Therefore, we develop a modification of Ant Colony algorithm. To edit mazes the two algorithms were developed: one by solutions lengths and another by similarity of solutions. The research was conducted in order to find dependencies between number of solutions and initial parameters. A computational experiment was made to find optimal number of ants within different initial parameters. Also there were evaluated efficiencies of two maze editing algorithms with different parameters.

Face Swapping: Realistic Image Synthesis Based on Facial Landmarks Alignment

We propose an image-based face swapping algorithm, which can be used to replace the face in the reference image with the same facial shape and features as the input face. First, a face alignment is made based on a group of detected facial landmarks, so that the aligned input face and the reference face are consistent in size and posture. Secondly, an image warping algorithm based on triangulation is presented to adjust the reference face and its background according to the aligned input faces. In order to achieve more accurate face swapping, a face parsing algorithm is introduced to realize the accurate detection of the face-ROIs, and then the face-ROI in the reference image is replaced with the input face-ROI. Finally, a Poisson image editing algorithm is adopted to realize the boundary processing and color correction between the replacement region and the original background, and then the final face swapping result is obtained. In the experiments, we compare our method with other face swapping algorithms and make a qualitative and quantitative analysis to evaluate the reality and the fidelity of the replaced face. The analysis results show that our method has some advantages in the overall performance of swapping effect.

Design and analysis of an effective graphics collaborative editing system

With the rapid development of computer-supported cooperative work (CSCW) technology, graphical collaborative editing plays an increasingly important role in CSCW. The most important technique in graphics co-editing is the consistency of graphics co-editing, which mainly includes causality consistency, consistency of results, and consistency of intention. Most of the previous research was abstract and ineffective, lacking theoretical depth and scalability. However, because the algorithm proposed in this paper can solve the contradictions in the consistency of graphical collaborative editing, the research in this paper has particularity, and the results will be proven by the experiment described in the paper. In order to solve the consistency conflict problem of graphic collaborative editing, the common graphics collaborative editing algorithm (CGCE algorithm) is proposed. It is proposed not only to perfect and expand the definition of graphics collaborative editing but also to merge with HTML5 Canvas, WebSocket, jQuery, Node.js and other network programming languages and technologies. The graphic collaborative editing based on the design and implementation of this paper can effectively solve the consistency conflict problem of many users during the collaborative editing of graphics, which ensures that the graphics of each graphical collaborative editing interface is consistent and the collaborative work can achieve the desired effect.

Supporting selective undo of string-wise operations for collaborative editing systems

With the advancement of distributed computing systems, an increasing number of collaborative systems are developed to support real-life collaborative work. As a typical representative of collaborative systems, collaborative editing systems have been one of the major researches within CSCW(Computer Supported Cooperative Work) areas. In collaborative editing systems, selective undo is a key feature that permits users to undo any operation at anywhere and anytime. Recently, with the extensive popularity of big data and cloud computing, collaborative editing systems increasingly tend to massive-scale collaborations, which have to face new technical challenges. How to support selective undo of string-wise operations has become one of significant challenges in future generation collaborative editing systems. Although CRDT (Commutative Replicated Data Type) is a new generation of collaborative editing algorithms, most CRDT algorithms do not support selective undo of string-wise operations. Currently, existing works take time logarithmic or even linear in the number of operation nodes to undo an operation, which would be suboptimal in which a large amount of operations may accumulate. In addition, how to formally prove the correctness of the algorithm is necessary. This paper proposes an efficient CRDT algorithm that supports integrated do and selective undo of string-wise operations. Formal proofs are provided to prove the correctness of the proposed approach and the intentions preserving of do/undo operations. Theoretical analysis and experimental evaluation show that our algorithm outperforms the existing CRDT algorithms to support selective undo.

TITRATION: A Randomized Study to Assess 2 Treatment Algorithms with New Insulin Glargine 300 units/mL.

It was uncertain whether an algorithm that involves increasing insulin dosages by 1 unit/day may cause more hypoglycemia with the longer-acting insulin glargine 300 units/mL (GLA-300). The objective of this study was to compare safety and efficacy of 2 titration algorithms, INSIGHT and EDITION, for GLA-300 in people with uncontrolled type 2 diabetes mellitus, mainly in a primary care setting. This was a 12-week, open-label, randomized, multicentre pilot study. Participants were randomly assigned to 1 of 2 algorithms: they either increased their dosage by 1 unit/day (INSIGHT, n=108) or the dose was adjusted by the investigator at least once weekly, but no more often than every 3 days (EDITION, n=104). The target fasting self-monitored blood glucose was in the range of 4.4 to 5.6 mmol/L. The percentages of participants reaching the primary endpoint of fasting self-monitored blood glucose ≤5.6 mmol/L without nocturnal hypoglycemia were 19.4% (INSIGHT) and 18.3% (EDITION). At week 12, 26.9% (INSIGHT) and 28.8% (EDITION) of participants achieved a glycated hemoglobin value of ≤7%. No differences in the incidence of hypoglycemia of any category were noted between algorithms. Participants in both arms of the study were much more satisfied with their new treatment as assessed by the Diabetes Treatment Satisfaction Questionnaire. Most health-care professionals (86%) preferred the INSIGHT over the EDITION algorithm. The frequency of adverse events was similar between algorithms. A patient-driven titration algorithm of 1 unit/day with GLA-300 is effective and comparable to the previously tested EDITION algorithm and is preferred by health-care professionals.

Approximation polynomial algorithm for the data editing and data cleaning problem

The work considers the mathematical aspects of one of the most fundamental problems of data analysis: search (choice) among a collection of objects for a subset of similar ones. In particular, the problem appears in connection with data editing and cleaning (removal of irrelevant (not similar) elements). We consider the model of this problem, i.e., the problem of searching for a subset of maximal cardinality in a finite set of points of the Euclidean space for which quadratic variation of points with respect to its unknown centroid does not exceed a given fraction of the quadratic variation of points of the input set with respect to its centroid. It is proved that the problem is strongly NP-hard. A polynomial 1/2-approximation algorithm is proposed. The results of the numerical simulation demonstrating the effectiveness of the algorithm are presented.

Development of Computer Algorithm for Editing of Next Generation Sequencing Metagenome Data.

The successful implementation of the advanced sequencing technology, the next generation sequencing (NGS) motivates scientists from diverse fields of biological research especially from genomics and transcriptomics in generating large genomic data set to make their analysis more robust and come up with strong inference. However, exploiting this huge genomic data set becomes a challenge for the molecular biologists. To corroborate this problem, computational software and hardware are being developed in parallel and become an integral part of life science. While executing the "Genomics project of Indian Drosophila species," we found strings of Ns in the whole genome sequences generated on Illumina platform. The present article aims at developing a computer algorithm (MATLAB and Python based) for editing raw sequences mainly eliminating bad residues before submitting to the publicly accessible sequence repository. These algorithms will be helpful to life scientists for analyzing large amount of biological data in short span of time.

Orthology Correction for Gene Tree Reconstruction: Theoretical and Experimental Results

We consider how the orthology/paralogy information can be corrected in order to represent a gene tree, a problem that has recently gained interest in phylogenomics. Interestingly, the problem is related to the Minimum CoGraph Editing problem on the relation graph that represents orthology/paralogy information, where we want to minimize the number of edit operations on the given relation graph in order to obtain a cograph. In this paper we provide both theoretical and experimental results on the Minimum CoGraph Editing problem. On the theoretical side, we provide approximation algorithms for bounded degree relation graphs, for the general problem and for the problem restricted to deletion of edges. On the experimental side, we present a genetic algorithm for Minimum CoGraph Editing and we provide an experimental evaluation of the genetic algorithm on synthetic data.