Fast Segmentation of Foreign Fiber Image - Computer and Computing Technologies in Agriculture V - Part III Access content directly
Conference Papers Year : 2012

Fast Segmentation of Foreign Fiber Image

Abstract

In the textile industry, different types of foreign fibers may be mixed in cotton, and the foreign fibers seriously affect the quality of cotton products. The step of image segmentation is of vital importance in the process of the foreign fibers identification, which is, in the same way, the foundation for cotton foreign fiber automated inspection. This paper presents a new approach for fast segmentation of foreign fiber images. This approach includes four main steps, i.e., image transformation, image block, image background extraction, image enhancement and segmentation. In the first step, we transform the captured color images into gray-scale images, and invert the color of the transformed images. In the second step, the proportion relationship between target image and background was analyzed, and then the whole foreign fibers image was divided into several blocks based on the analysis results. In the third step, the background of foreign fiber image was extracted by image corrosion and gray-level correction. In the final step, the histogram of the gray-scale image was analyzed, and a piecewise linear transform model was proposed to enhance the image blocks based on the analysis results, and then the image blocks were segmented by Otsu’s method. The experiment results indicate that the proposed method can segment the foreign fiber image directly and precisely, and the speed of image processing is much faster than that of the conventional methods.
Fichier principal
Vignette du fichier
978-3-642-27275-2_53_Chapter.pdf (4 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01361174 , version 1 (06-09-2016)

Licence

Attribution

Identifiers

Cite

Yutao Wu, Wenzhu Yang, Zhenbo Li, Daoliang Li. Fast Segmentation of Foreign Fiber Image. 5th Computer and Computing Technologies in Agriculture (CCTA), Oct 2011, Beijing, China. pp.469-483, ⟨10.1007/978-3-642-27275-2_53⟩. ⟨hal-01361174⟩
61 View
101 Download

Altmetric

Share

Gmail Facebook X LinkedIn More