Patch-based image vectorization with automatic curvilinear feature alignment

Vector image representation methods that can faithfully reconstruct objects and color variations in a raster image are desired in many practical applications. This article presents triangular configuration B-spline (referred to as TCB-spline)-based vector graphics for raster image vectorization. Based on this new representation, an automatic raster image vectorization paradigm is proposed. The proposed framework first detects sharp curvilinear features in the image and constructs knot meshes based on the detected feature lines. It iteratively optimizes color and position of control points and updates the knot meshes. By using collinear knots at feature lines, both smooth and discontinuous color variations can be efficiently modeled by the same set of quadratic TCB-splines. A variational knot mesh generation method is designed to adaptively introduce knots and update their connectivity to satisfy the local reconstruction quality. Experiments and comparisons show that our framework outperforms the existing state-of-the-art methods in providing more faithful reconstruction results. In particular, our method is able to model undetected features and subtle or complicated color variations in-between features, which the previous methods cannot handle efficiently. Our vectorization representation also facilitates a variety of editing operations performed directly over vector images.

This paper presents a subdivision-based vector graphics for image representation and creation. The graphics representation is a subdivision surface defined by a triangular mesh augmented with color attribute at vertices and feature attribute at edges. Special cubic B-splines are proposed to describe curvilinear features of an image. New subdivision rules are then designed accordingly, which are applied to the mesh and the color attribute to define the spatial distribution and piecewise-smoothly varying colors of the image. A sharpness factor is introduced to control the color transition across the curvilinear edges. In addition, an automatic algorithm is developed to convert a raster image into such a vector graphics representation. The algorithm first detects the curvilinear features of the image, then constructs a triangulation based on the curvilinear edges and feature attributes, and finally iteratively optimizes the vertex color attributes and updates the triangulation. Compared with existing vector-based image representations, the proposed representation and algorithm have the following advantages in addition to the common merits (such as editability and scalability): 1) they allow flexible mesh topology and handle images or objects with complicated boundaries or features effectively; 2) they are able to faithfully reconstruct curvilinear features, especially in modeling subtle shading effects around feature curves; and 3) they offer a simple way for the user to create images in a freehand style. The effectiveness of the proposed method has been demonstrated in experiments.

Image vectorization involves two major problems: how to extract proper geometric descriptors from the raster image and how to rasterize the vector representation for display. In this paper, we propose a novel image vectorization approach using diffusion curves as the geometric primitives. Our approach automatically extracts accurate diffusion curves from the input image without user interaction. We first segment the input image into a set of superpixels by a multi-layer algorithm. Then, boundary positions of these superpixels are explored to locate control points for diffusion curves, and color information is properly sampled to generate our double-boundary representation. To render the vector graphics, we formulate color diffusion as a random walk process. Experiments on different categories of photographs show that our approach successfully reveals detail contents in the reconstructed image, and that the rendering process can be performed nearly in realtime on a modern CPU.

A surgeon typically uses information from a number of tomographic imaging methods (e.g., CT, MR, PET) during the course of a surgical procedure. These imaging techniques represent three-dimensional information as a set of two-dimensional images. To use this information, the surgeon is required to mentally construct a three-dimensional visualization from the set of two- dimensional images. The formation of the mental image becomes more complicated with the inclusion of multiple imaging modalities and multiple imaging planes. We have developed a technique to enhance the mental three-dimensional visualization process through simultaneous graphics and multislice raster image display. The composite display, capable of displaying up to three raster images along with a patient-specific graphics model, is viewed on a 1280 X 1024 monitor. The raster images, displayed in a 512 X 512 format, may be any combination of imaging methods and imaging planes. The graphics model, determined from the imaging data, may be freely rotated as a depth-cued wireframe or shaded-surface model. Regions-of-interest may be incorporated into the graphics model for additional visual cues. Trajectory information may be obtained by moving a three-dimensional cursor in any raster image space or in the graphics model with instantaneous update of the remaining display area. This design allows the surgeon to interactively obtain orientation and visualization information from the images in the operating room. Because the classic imaging planes are used, the surgeon is not required to deal with a new information format or a loss of resolution.© (1991) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

This paper presents a new model, MUSCLE (Multidirectional Scanning for Line Extraction), for automatic vectorization of raster images with straight lines. The algorithm of the model implements the line thinning and the simple neighborhood methods to perform vectorization. The model allows users to define specified criteria which are crucial for acquiring the vectorization process. In this model, various raster images can be vectorized such as township plans, maps, architectural drawings, and machine plans. The algorithm of the model was developed by implementing an appropriate computer programming and tested on a basic application. Results, verified by using two well known vectorization programs (WinTopo and Scan2CAD), indicated that the model can successfully vectorize the specified raster data quickly and accurately.

Scalable Vector Graphics (SVG) is a popular vector image format that offers good support for interactivity and animation. Despite its appealing characteristics, creating custom SVG content can be challenging for users due to the steep learning curve required to understand SVG grammars or get familiar with professional editing software. Recent advancements in text-to-image generation have inspired researchers to explore vector graphics synthesis using either image-based methods (i.e., text → raster image → vector graphics) combining text-to-image generation models with image vectorization, or language-based methods (i.e., text → vector graphics script) through pretrained large language models. Nevertheless, these methods suffer from limitations in terms of generation quality, diversity, and flexibility. In this paper, we introduce IconShop, a text-guided vector icon synthesis method using autoregressive transformers. The key to success of our approach is to sequentialize and tokenize SVG paths (and textual descriptions as guidance) into a uniquely decodable token sequence. With that, we are able to exploit the sequence learning power of autoregressive transformers, while enabling both unconditional and text-conditioned icon synthesis. Through standard training to predict the next token on a large-scale vector icon dataset accompanied by textural descriptions, the proposed IconShop consistently exhibits better icon synthesis capability than existing image-based and language-based methods both quantitatively (using the FID and CLIP scores) and qualitatively (through formal subjective user studies). Meanwhile, we observe a dramatic improvement in generation diversity, which is validated by the objective Uniqueness and Novelty measures. More importantly, we demonstrate the flexibility of IconShop with multiple novel icon synthesis tasks, including icon editing, icon interpolation, icon semantic combination, and icon design auto-suggestion.

The field of smooth vector graphics explores the representation, creation, rasterization, and automatic generation of light-weight image representations, frequently used for scalable image content. Over the past decades, several conceptual approaches on the representation of images with smooth gradients have emerged that each led to separate research threads, including the popular gradient meshes and diffusion curves. As the computational models matured, the mathematical descriptions diverged and article started to focus more narrowly on subproblems, such as on the representation and creation of vector graphics, or the automatic vectorization from raster images. Most of the work concentrated on a specific mathematical model only. With this survey, we describe the established computational models in a consistent notation to spur further knowledge transfer, leveraging the recent advances in each field. We therefore categorize vector graphics article from the last decades based on their underlying mathematical representations as well as on their contribution to the vector graphics content creation pipeline, comprising representation, creation, rasterization, and automatic image vectorization. This survey is meant as an entry point for both artists and researchers. We conclude this survey with an outlook on promising research directions and challenges to overcome in the future.

We present a fully automated technique that segments raster images into smooth shaded regions and reconstructs them using an optimal mix of solid fills, linear gradients, and radial gradients. Our method leverages a novel discontinuity‐aware segmentation strategy and gradient reconstruction algorithm to accurately capture intricate shading details and produce compact Bézier curve representations. Extensive evaluations on both designer‐created art and generative images demonstrate that our approach achieves high visual fidelity with minimal geometric complexity and fast processing times. This work offers a robust and versatile solution for converting detailed raster images into scalable vector graphics, addressing the evolving needs of modern design workflows.

Satellite imagery provides a unique opportunity for oceanic fronts’ identification and the observation of the synoptic variability of the fronts. Top quality interpretative frontal maps are compiled by expert oceanographers from satellite and in situ data aided by numerical models of the ocean’s circulation. To be used for the initialization and data assimilation in numerical models, these frontal maps have to be digitized and vectorized. Here, we present an algorithm that automatically recognizes oceanic structures (fronts, eddies, filaments) in frontal maps formatted as raster images. The algorithm is based on a formalized description of the structure of the frontal zone, the image vectorization, and the detection of significant structural elements based on the classification of these elements. The classification of the structural elements was first developed by analyzing once-a-week satellite-derived sea surface temperature (SST) images for the western North Atlantic from 2010. The structural elements are then recognized based on their invariant spatial characteristics and their positions relative to one another in any new SST image. The algorithm outputs a set of digital arrays that are vector descriptors of all the significant structural elements of the frontal map.

Current image vectorization techniques mainly deal with images with simple and plain colors. For full-color photographs, many difficulties still exist in object segmentation, feature line extraction, and color distribution reconstruction, etc. In this paper, we propose a high-efficiency image vectorization method based on importance sampling and triangulation. A set of blue-noise sampling points is first generated on the image plane by an improved error-diffusion sampling method. The point set well preserves the features in the image. Then after triangulation on this point set, color information can be recorded on the mesh vertices to form a vector image. After certain image editing, e.g. scaling or transforming, the whole image can be reconstructed by color interpolating inside each triangle. Experiments show that the method has high performing efficiency and abilities in feature-preserving. It will bring benefits to many applications, e.g. image compressing, editing, transmitting and resolution enhancement.

Highly accurate, fully automatic marker-free image alignment plays an important role in nano-tomographic reconstruction, particularly in cases where the spatial resolution of the tomographic system is on the nanometer scale. However, highly accurate marker-free methods such as the projection matching method are computationally complex and time-consuming. Achieving alignment accuracy with reduced computational complexity remains a challenging problem. In this study, we propose an efficient method to achieve marker-free fully automatic alignment. Our method implements three main alignment procedures. First, the frequency-domain common line alignment method is used to correct the in-plane rotational errors of each projection. Second, real-space common line alignment method is used to correct the vertical errors of the projections. Finally, a single layer joint-iterative reconstruction and re-projection method is used to correct the horizontal projection errors. This combined alignment approach significantly reduces the computational complexity of the classical projection matching method, and increases the rate of convergence towards determining the accurate alignment. The total processing time can be reduced by up to 4 orders of magnitude as compared to the classical projection matching method. This suggests that the algorithm can be used to process image alignment of nano-tomographic reconstructions on a conventional personal computer in a reasonable time-frame.

A fully automatic alignment system for a pulsed infrared laser beam (5 ns pulses, 10 Hz repetition rate, 1.3 microm wavelength) was developed and tested. It compensates for long-term fluctuations of the beam initial position and direction-the automatic realignment is performed every 10 min, and lasts typically 1-2 min. The system adjusts the beam initial position with a maximum error of 0.5 mm (10% of the beam diameter) and the beam direction with a maximum error of 50 murad. The solution is based on two InGaAs quadrant photodiodes as the position detectors and two motorized mirrors controlled by a personal computer. The signals from the quadrant detectors are processed by a peak detector and digitized by an analog to digital converter, which is synchronized with the laser pulses.

This paper presents a method of enhancing linear and curvilinear image features, such as those corresponding to tissue discontinuities in medical ultrasound. The method is an extension of a template based technique for line enhancement which produces a test statistic at each point by projecting the pixels near that point onto a line segment, varying the orientation of the segment to maximize the projected value, and retaining the projected value as the test statistic. In the past, we have not made use of information about which angle produced the maximum value at each point. In this paper, we compute a histogram of the angles near each point to gain an indication of the direction of larger scale linear features lying nearby. Mathematically, we wish to estimate a set of prior probabilities for the orientation of line segments that pass through each point. The priors can then be used to improve the power of the Bayesian line detection procedure. In addition, they can also be used to improve the visual quality of the image produced by plotting the test statistics on an image raster. We have found that such an image is revealing because it shows more sharply the edges of the linear components, making them more clearly visible and their fringes more distinguishable from the background. With the incorporation of prior information, the processed image shows a further improvement in visual and machine detectability of linear components, due to increased difference in gray level between points lying on edges and those lying away. This technique has potential to significantly improve the machine detectability of tissue discontinuities in medical ultrasound, as well as linear features in other forms of computed imaging.

This paper presents a new automatic algorithm for extracting vector information from raster images. The algorithm extracts structural information from the lines that is formatted to allow easy processing and evaluation of the image structure. Vectorization results are comparable with commonly used algorithms, however the outlined method differs from prior work by providing information in a more accessible form. This algorithm provides topological information at the cost of visual fidelity. Properties such as line topology and width are important for image processing, including object decomposition, author recognition and line style modification.

Automatic alignment and reconstruction of facial depth images