Presentation is loading. Please wait.

Presentation is loading. Please wait.

Color Clustering and Learning for Image Segmentation Based on Neural Networks Guo Dong, Member, IEEE, and Ming Xie, Member, IEEE 2009.02.23 최지혜.

Similar presentations


Presentation on theme: "Color Clustering and Learning for Image Segmentation Based on Neural Networks Guo Dong, Member, IEEE, and Ming Xie, Member, IEEE 2009.02.23 최지혜."— Presentation transcript:

1 Color Clustering and Learning for Image Segmentation Based on Neural Networks Guo Dong, Member, IEEE, and Ming Xie, Member, IEEE 2009.02.23 최지혜

2 Topic 신경망을 기초로한 영상분할을 위한 컬 러 클러스터링과 학습 주제어 : SOM ( 능동적으로 맵을 구성 ) SA ( 전역 최적 클러스터링 위해 ) HPL( 계층적 초기학습 )

3 요약 정확한 색상차이를 측정하기 위하여 수정 된 컬러공간 L*u*v* 를 사용하였다. 분할 시스템은 supervised/unsupervised segmentation 으로 이루어 졌는데, un- 의 경우 컬러감소와 컬러 클러스터링을 목 표로 할 수 있다. 컬러 클러스터링은 SOM-SA 의 장점들로 취해 저 연산비용으 로 최적의 분할을 이룰 수 있다. HPL 은 색 상 프로토타입들을 목적색상을 위해 좋은 근사처리로 공급된다.

4 Image segmentation system based on neural networks 미리 알기 어려운 이미지 오브젝트의 컬러를 알고 있는 경우

5 Unsupervised segmentation 미리 알기 어려운 이미지 Spatial Compactness Color homogeneity Desirable properties Image-domain Feature-space Segmentation techniques

6 Unsupervised segmentation Watershed transform Self-organizing map Splitting and merging phases SOM

7 SOM is trained to generate the primitive clustering dominant colors of the image

8 Description of Problem To ensure a proper measure of color differences, image colors must be represented in a uniform color space. In unsupervised segmentation, color reduction is indispensable to the segmentation of a large color image. In supervised segmentation, color learning is crucial to build up an accurate classifier for the segmentation of the object of interest.

9 Flow of This paper Appropriate color space color reduction is performed by SOM learning SA seeks the optimal clusters from SOM prototypes New procedure of supervised learning

10 Appropriate color space L* is luminant component u* and v* are color components : u* axis varies from green to red v* axis changes from blue to yellow

11 RGB to L*u*v*

12 Color reduction : SOM learning a two-layer neural network with a rectangular topology Three inputs are fully connected to the neurons on a 2-D plane. Each neuron is a cell containing a weight values.

13 SOM Training Initialization – 16x16 rectangular neighborhood type is Gaussian weight vector –randomly initialize radius r = 16, 5 learning rate = 0.05,0.02 Input - each color point Competitive Process – ‘wining neuron’

14 SOM Training Cooperative Process- The topological neighbors are determined by Gaussian function centered at Adaptive Process - The weights of “winning neuron” and its neighbor neurons are updated within the neighborhood : Effective scope : neighborhood function

15 Sammon mapping of 16x16 weight vectors after SOM training

16 SA seeks the optimal clusters from SOM prototypes Simulated annealing 은 커다란 탐색공간에서 주어진 함수의 전역 최적점에 대한 훌륭한 근사치를 찾으려고 하는 전역 최적화 문제에 대한 일반적인 확률적 휴리스틱 접근방법 고체의 물리적인 담금질과 아주 많은 경우의 수를 가진 조합최적화문 제사이의 밀접한 관계 -> 여러 다른 신경망의 학습과정을 변화시켜줄 수 있다. Simulated annealing 은 커다란 탐색공간에서 주어진 함수의 전역 최적점에 대한 훌륭한 근사치를 찾으려고 하는 전역 최적화 문제에 대한 일반적인 확률적 휴리스틱 접근방법 고체의 물리적인 담금질과 아주 많은 경우의 수를 가진 조합최적화문 제사이의 밀접한 관계 -> 여러 다른 신경망의 학습과정을 변화시켜줄 수 있다. 학습한다 :minimization 과정으로 볼 수 있으며, 이것은 energy function 이나 error function 에서 downward 방향으로 간다. Initial weight 잘못 선택 시 Local minimum SA 의 개념의 도입

17 SA The optimal solution is obtained by consisting in randomly perturbing the system, and gradually decreasing the randomness to a low final level. cluster centers be The criterion of sum-of-squared-error The procedure of SA clustering is to search the appropriate cluster centers = minimize the energy function

18 SA Clustering

19 Clustering

20 Segmentation result by SOM-SA color clustering

21 RCE neural network is a supervised pattern classifier used for the estimation of feature region hyperspherical window New procedure of supervised learning

22 Drawback of RCE learning requirement of a complete sample set for all classes it requires the samples of both the object and the image background. – to segment the object of interest from the image background

23 Hierarchical Prototype Learning In some regions, a small size of prototype is appropriate, Other regions, a large size of prototype is more suitable. >> The proper way of region estimation is to estimate the region by the different sizes of color prototypes.

24 Hierarchical Prototype Learning

25 (a)Original color image. (b) SOM color clustering. Q =5580.824. (c) SA clustering. Q = 182.526. (d) SOM-SA color clustering. Q =244.826. (e) CL-SA color clustering. Q = 376.845. EXPERIMENTAL EVALUATIONS

26 Supervised segmentation (a) Original gesture image. (b) HPL learning. (c) Color threshold. (d) Color histogram. (a) Original hand gesture images. (b) Segmentation of hand gestures.


Download ppt "Color Clustering and Learning for Image Segmentation Based on Neural Networks Guo Dong, Member, IEEE, and Ming Xie, Member, IEEE 2009.02.23 최지혜."

Similar presentations


Ads by Google