An approach for color image segmentation is proposed based on the contributions of color features to segmentation rather than the choice of a particular color space. It is different from the pervious methods where SOFM is used for construct the feature encoding so that the feature-encoding can self-organize the effective features for different color images. Fuzzy clustering is applied for the final segmentation when the well-suited color features and the initial parameter are available. The proposed method has been applied in segmenting different types of color images and the experimental results show that it outperforms the classical clustering method. Our study shows that the feature encoding approach offers great promise in automating and optimizing color image segmentation.
Quantitative estimation of tissue labeling heavily depends on the efficiency of image segmentation technique. In this paper, an encoder-segmented neural network was proposed to improve the efficiency of image segmentation. The features are ranked according to the encoder indicators by which the insignificant feature vector will be eliminated from the original feature vectors and the important feature vectors can be re-organized as the encoded feature vectors for the subsequent clustering. ESNN developed can improve the exist FCM algorithm in feature extraction and the cluster's number selection. This method was successfully implemented automatic labeling of tissue in brain MRIs. Examples of the results are also presented for diagnosis of brain using MR images.
Most of region-based image segmentation approaches suffered from the problem of different thresholds selecting for different images. In this paper, an new adaptive image segmentation approach based on an encoder-segmented neural network (ESNN) is presented. The novel ESNN combines the advantages of self-organizing feature map (SOFM) and fuzzy c- means clustering (FCM) algorithm. Feature encoder implemented by SOFM for vector quantization using the competitive learning where the feature vectors can be encoded as the definite sequence by which the most of the available feature vectors can be extracted for the final segmentation using encoded feature-based fuzzy c-means (EFFCM) algorithm. Since the contribution of feature encoder, ESNN can reduce the complexion of computation when processing a large number of multi-spectral images. ESNN have been applied for brain MRI segmentation. Comparing with FCM algorithm, experimental results have shown ESNN method for segmentation makes better performance on computation and adaptability.
Neural networks have been applied to many kinds of image processing with well performance. When dealing with the large image, a large number of neurons is required so as to (1) make the construction model more complex, (2) make the speed of processing slower than the traditional methods due to heavy computation load. In this paper, an encoder- segmented neural network is constructed for image segmentation in which the available data can be obtained by a weight matrix containing maximum region information when a large number of input data are compressed by encoder network, meantime, the fuzzy clustering strategy applied on Hopfield neural network for the fine segmentation eliminates the tedious work of finding weighting factors. The experimental results indicate the performance of image segmentation can be improved effectively.
Extract tissue from a computer aided tomography (CT) image is decided by segmentation. In this paper, a method to select multi-threshold automatically from gray level histogram for image segmentatin is presented. With a hierarchical data structure, we can not only obtain the better results of multithresholding, but also speed up the processing operations. Experimental results have shown that our algorithm is more effective for the CT image segmentation.