以直方圖為基礎之多閥值搜尋演算法應用於彩色多物體切割

A Histogram-Based Multi-Threshold Searching Algorithm for Multiple Color Objects Segmentation

陳煒傑(Wei-Chieh Chen)

指導教授 ： 蔡奇謚

淡江大學/工學院/電機工程學系碩士班/碩士(2012年)

https://doi.org/10.6846/TKU.2012.00898

摘要

本論文設計了一種無監督式搜尋多色彩閥值的方法，並且可應用於彩色多物體的切割。現有的色彩閥值切割技術大多需要利用各顏色通道資訊，透過人工調整方式選擇適當的參數，將所感興趣的彩色物體與背景分離。本論文中提出了一種無監督式多閥值搜尋的演算法，其可自動搜尋各彩色物體的最佳門檻值，並利用此資訊從影像中切割出感興趣的彩色物體。為了達到此目的，首先將提出一個新穎的ratio-map影像計算方法，其能夠有效的提高前景像素與背景像素的對比度。接著套用傳統Otsu演算法於ratio-map影像中，即可使得影像中前景彩色物體能從背景中被切割出來。最後，本論文亦提出了一個新的以直方圖為基礎之多閥值搜尋演算法，用來搜尋色調、飽和度以及明亮度三通道的最佳上限與下限門檻值，進而切割影像中所有的彩色物體。在實驗結果的部分，將呈現以本論文所提出的方法之切割結果。實驗證明本論文的方法可以成功地切割出所有感興趣的彩色物體，達到色彩切割或色彩建模的目的。

關鍵字

多物體切割 ； 彩色影像閥值技術 ； 多閥值搜尋 ； ratio-map影像

並列摘要

This thesis addresses the issue of unsupervised multi-color thresholding design for color-based multiple objects segmentation. Most of the current color thresholding techniques require setting threshold values of each color channel for multiple colors-of-interest in a supervised way. In this thesis, an unsupervised multi-threshold searching algorithm is proposed to automatically search the optimal threshold values for segmenting multiple color objects. To achieve this, a novel ratio-map image computation method is proposed to efficiently enhance the contrast between foreground and background pixels. The Otsu’s method is then applied to the ratio-map image to extract all foreground color objects from the background image. Finally, a new histogram-based multi-threshold searching algorithm is proposed to search the optimal upper-bound and lower-bound threshold values of hue, saturation and brightness components for each color object. Experimental results show that the proposed method succeeds to separate all color objects-of-interest in a realistic scenario.

並列關鍵字

Multi-object segmentation ； color image thresholding ； multilevel thresholding ； multi-threshold searching ； ratio-map image

參考文獻

[1] A. Y. Yang, J. Wright, Y. Ma, and S. S. Sastry, “Unsupervised Segmentation of Natural Images via Lossy Data Compression,” Computer Vision and Image Understanding, Vol. 110, No. 2, pp. 212-225, May 2008.

[2] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE Transactions on Systems, Man and Cybernetics, Vol. 9, No. 1, pp. 62-66, Jan. 1979.

[4] Y. Wu, Q. Liu, and T. S. Huang, “Robust Real-Time Human Hand Localization by Self-Organizing Color Segmentation,” International Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, Greece, pp. 161-166, 1999.

[5] S. H. Hamed and R. S, “Automatic Multilevel Thresholding for Image Segmentation by the Growing Time Adaptive Self-Organizing Map,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 10, pp. 1388-1393, Oct. 2002.

[6] Z. Yu, O. Au, R. Zou, W. Yu, and J. Tian, “An Adaptive Unsupervised Approach toward Pixel Clustering and Color Image Segmentation,” Pattern Recognition, Vol. 43, No. 5, pp. 1889–1906, May 2010.