Study on Adaptive Threshold Segmentation Method Based on Brightness

• Autorzy: Zhao, D. , Dai, X. , Sun, G. , Lu, T.

Warianty tytułu

PL

Adaptacyjna progowa segmentacja obrazu bazująca na analizie jasności

• Języki publikacji: EN

Abstrakty

EN

Image segmentation is one of the most important steps before the image data analysis, which divided the image into several areas that have strong similarity. With the more and more widely application of the mesh fabric, the quality requirements are more stringent. As the impact of uneven illumination, the image brightness is inconsistent, which bring a great difficulty to the image segmentation of the mesh fabric. In order to eliminate the effect of uneven illumination in the image acquisition of linear CCD camera, the adaptive threshold segmentation method based on brightness is proposed. Compared with the Otsu method, it is better to eliminate the influence of the uneven illumination and provide a good foundation for subsequent data analysis.

PL

Analizowano system segmentacji obrazu polegający na podziale obrazu na obszary o dużym podobieństwie. Przy nierównym naświetleniu powstaje problem segmentacji. Zaproponowano adaptacyjny system progowej segmentacji bazujący na analizie jasności.

Słowa kluczowe

PL

przetwarzanie obrazów; segmentacja; jasność

EN

image segmentation; illumination; segmentation method

• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2012
• Tom: R. 88, nr 9b
• Strony: 150-152
• Opis fizyczny: Bibliogr. 12 poz., rys., tab.

Twórcy

autor

Zhao, D.

• School of Mechanical Engineering, Hubei University of Technology, Wuhan, China,

autor

Dai, X.

• School of Mechanical Engineering, Hubei University of Technology, Wuhan, China,

autor

Sun, G.

• School of Mechanical Engineering, Hubei University of Technology, Wuhan, China,

autor

Lu, T.,

Bibliografia

• [1] Yang Zhiling, Wang Kai, Visual C++ digital image acquisition, processing and practical application, China: Posts & Telecom Press, 2003
• [2] Wiman Hakan, Array algebra polynomial fitting for image segmentation, Journal of Mathematical Imaging and Vision, 6(1996), No. 1, 7-13
• [3] Feng Dengchao, Yang Zhaoxuan, Qiao Xiaojun, Texture Image Segmentation Based on Improved Wavelet Neural Network, Advances in Neural Networks, 4493(2007), No. 3, 869-876
• [4] Liu Jihong, Ma Weina, Lee Sooyoung, A Segmentation Method Based on Dynamic Programming for Breast Mass in MRI Images, Medical Biometrics, 4901(2007), 307-313
• [5] Cheng Junna, Ji Guangrong, Feng Chen, Image Segmentation Based on Chaos Immune Clone Selection Algorithm, Advanced Intelligent Computing Theories and Applications, 4682(2007), 505-512
• [6] Ji Wenhua, Zhou Chang, An Advanced Algorithm for Image Segmentation by Random Seed Region Search, Advances in Intelligent and Soft Computing, 111(2012), 251-257
• [7] Jing Junfeng, Kang Xuejuan, Fabric Pilling Image Segmentation Based on Mean Shift, Communications in Computer and Information Science, 143(2011), No. 1, 80-84
• [8] Chen Chifan, Liang Chiahsin, Spatial Filtering with Multi-scale Segmentation Based on Gaussian Function, Advances in Visual Computing, 5359 (2008), No. 2, 802-812
• [9] Debayle J., Pinoli J. C., General Adaptive Neighborhood Choquet Image Filtering, Journal of Mathematical Imaging and Vision, 35(2009), No. 3, 173-185
• [10] Samoilin E. A., Optimal estimation of the position of non-Gaussian impulse noise in images, Optoelectronics, 45(2009), 243-249
• [11] Zohra Z, Manseur, David C, Wilson, Invertibility of a special class of mean filter operators, Journal of Mathematical Imaging and Vision, 1(1992), 137-143
• [12] Lee Changshing, Kuo Yauhwang, Yu Paota, Weighted fuzzy mean filters for image processing, Fuzzy Sets and Systems. 89(1997), 157–180