Using Bezier Curves in Computer Graphics and Computer Vision part2

Monodeep Mukherjee
2 min readJan 16, 2023
Photo by Ricardo Gomez Angel on Unsplash
  1. ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network(arXiv)

Author : Yuliang Liu, Hao Chen, Chunhua Shen, Tong He, Lianwen Jin, Liangwei Wang

Abstract : Scene text detection and recognition has received increasing research attention. Existing methods can be roughly categorized into two groups: character-based and segmentation-based. These methods either are costly for character annotation or need to maintain a complex pipeline, which is often not suitable for real-time applications. Here we address the problem by proposing the Adaptive Bezier-Curve Network (ABCNet). Our contributions are three-fold: 1) For the first time, we adaptively fit arbitrarily-shaped text by a parameterized Bezier curve. 2) We design a novel BezierAlign layer for extracting accurate convolution features of a text instance with arbitrary shapes, significantly improving the precision compared with previous methods. 3) Compared with standard bounding box detection, our Bezier curve detection introduces negligible computation overhead, resulting in superiority of our method in both efficiency and accuracy. Experiments on arbitrarily-shaped benchmark datasets, namely Total-Text and CTW1500, demonstrate that ABCNet achieves state-of-the-art accuracy, meanwhile significantly improving the speed. In particular, on Total-Text, our realtime version is over 10 times faster than recent state-of-the-art methods with a competitive recognition accuracy. Code is available at https://tinyurl.com/AdelaiDet

2. Bezier curves and surfaces based on modified Bernstein polynomials(arXiv)

Author : Khalid Khan, D. K. Lobiyal, Adem Kilicman

Abstract : In this paper, we use the blending functions of Bernstein polynomials with shifted knots for construction of Bezier curves and surfaces. We study the nature of degree elevation and degree reduction for Bezier Bernstein functions with shifted knots. Parametric curves are represented using these modified Bernstein basis and the concept of total positivity is applied to investigate the shape properties of the curve. We get Bezier curve defined on [0, 1] when we set the parameter α=βto the value 0. We also present a de Casteljau algorithm to compute Bernstein Bezier curves and surfaces with shifted knots. The new curves have some properties similar to Bezier curves. Furthermore, some fundamental properties for Bernstein Bezier curves and surfaces are discussed

--

--

Monodeep Mukherjee

Universe Enthusiast. Writes about Computer Science, AI, Physics, Neuroscience and Technology,Front End and Backend Development