色彩影像分割演算法之改進與互動式物件擷取

Improvement on Color Image Segmentation Algorithm and Interactive Object Extraction

魏郁珊(Yu-Shan Wai)

指導教授 ： 貝蘇章

國立臺灣大學/電機資訊學院/電信工程學研究所/碩士(2006年)

https://doi.org/10.6342/NTU.2006.00964

摘要

數十年來，自動影像辨識一直是電腦視覺領域中十分渴切希望解決的課題。自動影像辨識，類比於人類對影像的知覺，第一步必須將影像中均質的區塊做分割，才能進一步討論該區塊的形狀質地色彩進而進行辨識。然而，就如同自動影像辨識一般，雖然自動影像分割技術及演算法不斷在進步，卻仍是個尚未完整解決的問題。這是因為一般影像內容的不確定性和複雜程度較高。不過大致上而言，基本影像處理以及樣式辨認技術，將有助於簡化影像切割問題的複雜程度並幫助呈現出更好的切割效果。
論文前半將介紹截至目前為止成效較好的兩種影像切割演算法，實作其演算法並且對架構加以修改，增進效率並且同時保持解析度和準確度。此外，我們也對某些較難切割的影像嘗試了幾種增進準確度的方法，並得到不錯的效果。
若從另外一個角度來看影像切割的問題，既然自動辨識和切割是如此困難，何不退一步，藉由使用者的幫助來解決問題呢?
於是，在論文的後半部份，我們簡短地介紹了目前某些互動式物件擷取系統的概念以及操作方式，並提出一個新的系統架構。使用者只需要做一些簡單的指定，系統便可以快速地找出使用者所想要的物體。這都要感謝使用者的幫助給予了系統足夠的資訊來降低問題的複雜性和不確定性。
在這論文裡所提出的影像切割架構和互動式物件擷取架構都應用到了多層比例 (Multi-Scale) 架構的概念。

關鍵字

影像切割 ； 色彩影像處理 ； 物件擷取

並列摘要

The automatic recognition of images has been a researched topic over decades yet still a difficult task to accomplish. Similar as the process of human perception, the first step of automatic recognition should be image segmentation to segment different homogeneous patches into regions. However, like the automatic recognition, segmentation remains a yet satisfactorily solved problem. This is due to the uncertainty and complexity nature of images. By the aid of various image processing techniques and pattern recognition analysis, this problem may reduced to some less complicated level, thus helps to achieve preferable result.
We first introduce two excellently performed algorithms of color image segmentation up to date, and made some modification on the structural phase and improved their efficiency while preserving resolution and accuracy. Moreover, we experimented on adding some special approaches as pre-processing, tested on specific images which are difficult to segment and get very good results.
From another aspect to look upon this problem, since the recognition and also the segmentation so difficult a problem to solve, why not ask for a little assistance of human specification?
In the latter part of the thesis, interactive object extraction is briefly covered and a new system we proposed is tested. With simple user specification, we could solve the extraction problem by a simpler and faster version of solution. This reduction of complexity should thanks to the prior knowledge given by human specification.
Both the automatic image segmentation and interactive object extraction take the advantage of multi-scale structure.

並列關鍵字

image segmentation ； image processing ； interactive object extraction

參考文獻

[1] “Digital Image Processing” 2nd Edition, by Rafael C. Gonzalez, and Richard E. Woods, Prentice Hall

[5] A. Diplaros, T. Gevers, I, Patras, “Combining Color and Shape Information for Illumination-Viewpoint Invariant Object Recognition”, IEEE Transactions on Image Processing, Vol.15 No.1 January 2006

[2] J.M. Gauch, “Image segmentation and analysis via multi-scale gradient watershed hierarchies” IEEE Transactions on Image Processing Jan 1999, vol.8 issue 1. pp.69-79

[4] D. Comaniciu, M. Peter, “Mean shift analysis and applications”. Proc. IEEE Int.Conf. on Computer Vision, Geece(1999) p.1197-1203

[6] K. Fukunaga, L. Hostetler, “The estimation of the gradient of a density function, with applications in pattern recognition”. IEEE Trans. Information Theory, Volume 21(1975), p.32-40