Denoising of defect on feather image

Defects on the feather leaf are mainly scar, wormhole and stain. Accurate segmentation of these defects on feather leaf will improve largely the quality of the feather. In this study, this paper analyses brightness distribution characteristic of feather image, proposes a denoising method based on th...

Full description

Saved in:
Bibliographic Details
Main Authors: Yue, Hongwei, Dong, Chaojun, He, Yuebang, Wang, Keqiang, Man, Hong, Cao, Lu
Format: Conference Proceeding
Language:English
Subjects:
Defects
feather image
Feathers
Feature extraction
Image color analysis
image defect
Image segmentation
Kernel
mean shift
Noise reduction
Object segmentation
Segments
Surface layer
Texture
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Defects on the feather leaf are mainly scar, wormhole and stain. Accurate segmentation of these defects on feather leaf will improve largely the quality of the feather. In this study, this paper analyses brightness distribution characteristic of feather image, proposes a denoising method based on the improved mean shift . The outstanding of differences between feather leaf and feather defect can be gotten by this proposed method. Experimental results with both better value of evaluation index and improved visual quality indicated the successful implementation of the proposed method in the denoising of feather images. Moreover, the algorithm can accurately segment feather image and effectively suppress the undesired background texture information to segment feather image with unclear color information.
ISSN:2161-2927
1934-1768
DOI:10.1109/ChiCC.2016.7554981