Correction Method for Line Extraction in Vision Measurement

Abstract

Over-exposure and perspective distortion are two of the main factors underlying inaccurate feature extraction. First, based on Steger’s method, we propose a method for correcting curvilinear structures (lines) extracted from over-exposed images. A new line model based on the Gaussian line profile is developed, and its description in the scale space is provided. The line position is analytically determined by the zero crossing of its first-order derivative, and the bias due to convolution with the normal Gaussian kernel function is eliminated on the basis of the related description. The model considers over-exposure features and is capable of detecting the line position in an over-exposed image. Simulations and experiments show that the proposed method is not significantly affected by the exposure level and is suitable for correcting lines extracted from an over-exposed image. In our experiments, the corrected result is found to be more precise than the uncorrected result by around 45.5%. Second, we analyze perspective distortion, which is inevitable during line extraction owing to the projective camera model. The perspective distortion can be rectified on the basis of the bias introduced as a function of related parameters. The properties of the proposed model and its application to vision measurement are discussed. In practice, the proposed model can be adopted to correct line extraction according to specific requirements by employing suitable parameters.

Dynamic projection theory for fringe projection profilometry

“…In Ref. [24], a method is proposed to extract curvilinear from overexposed images with Steger's method and perspective distortion. Although it has high precision, it only works for linear extraction and is not suitable for complex 3D objects.…”

Comparação De Métodos De Extração De Curvas De Dispersão Baseados Em Transformada De Fourier 2-D E Através Do Método Matriz Pencil

“…Esse algoritmo, proposto por Steger (51), se baseia na detecção de estruturas curvilíneas por meio da criação de um modelo matemático que pode representar linhas no espaço da imagem. Inicialmente, modela-se linhas em imagens considerando a característica de uma seção unidimensional (1-D) perpendicular a sua direção, uma vez que esse perfil é apresentado ao longo de todos os pontos da linha (80). Em 1-D, uma linha com o perfil denominado bar-shaped, de espessura 2w, pode ser descrita pela equação…”