Color image segmentation is an important technique in image processing, pattern recognition and computer vision. Many segmentation algorithms have been proposed. However, it is still a complex task especially when there are noises in the images, which have not been studied in much detail. Neutrosophic set (NS) studies the origin, nature, and scope of neutralities. In this paper, we apply NS in the color image and define some new concepts. A directional α-mean operation is proposed to reduce the set indeterminacy. The fuzzy c-means clustering method is improved by integrating with NS and employed for the color image segmentation. The computation of membership and the clustering termination criterion are redefined accordingly. Moreover, a validity criterion is employed to determine the optimal clustering number. Numerical experiments serve to illustrate the effectiveness and reliability of the proposed approach. Experimental results demonstrate that our approach can segment color images automatically and effectively, produce good results as favorably compared to some existing algorithms. The optimal clustering number is determined automatically and no prior knowledge is required. Especially, it can segment both images with the simple and distinct objects and the images with complex and noisy objects, which is the most difficult task for color image segmentation. 相似文献
Texture can be defined as a local statistical pattern of texture primitives in observer’s domain of interest. Texture classification aims to assign texture labels to unknown textures, according to training samples and classification rules. In this paper a novel method, which is an intelligent system for texture classification is introduced. It used a combination of genetic algorithm, discrete wavelet transform and neural network for optimum feature extraction from texture images. An algorithm called the intelligent system, which processes the pattern recognition approximation, is developed. We tested the proposed method with several texture images. The overall success rate is about 95%. 相似文献
Anti-slip control systems are essential for railway vehicle systems with traction. In order to propose an effective anti-slip control system, adhesion information between wheel and rail can be useful. However, direct measurement or observation of adhesion condition for a railway vehicle in operation is quite demanding. Therefore, a proportional–integral controller, which operates simultaneously with a recently proposed swarm intelligence-based adhesion estimation algorithm, is proposed in this study. This approach provides determination of the adhesion optimum on the adhesion-slip curve so that a reference slip value for the controller can be determined according to the adhesion conditions between wheel and rail. To validate the methodology, a tram wheel test stand with an independently rotating wheel, which is a model of some low floor trams produced in Czechia, is considered. Results reveal that this new approach is more effective than a conventional controller without adhesion condition estimation.
Automatic key concept identification from text is the main challenging task in information extraction, information retrieval, digital libraries, ontology learning, and text analysis. The main difficulty lies in the issues with the text data itself, such as noise in text, diversity, scale of data, context dependency and word sense ambiguity. To cope with this challenge, numerous supervised and unsupervised approaches have been devised. The existing topical clustering-based approaches for keyphrase extraction are domain dependent and overlooks semantic similarity between candidate features while extracting the topical phrases. In this paper, a semantic based unsupervised approach (KP-Rank) is proposed for keyphrase extraction. In the proposed approach, we exploited Latent Semantic Analysis (LSA) and clustering techniques and a novel frequency-based algorithm for candidate ranking is introduced which considers locality-based sentence, paragraph and section frequencies. To evaluate the performance of the proposed method, three benchmark datasets (i.e. Inspec, 500N-KPCrowed and SemEval-2010) from different domains are used. The experimental results show that overall, the KP-Rank achieved significant improvements over the existing approaches on the selected performance measures.
The wavelet domain association rules method is proposed for efficient texture characterization. The concept of association rules to capture the frequently occurring local intensity variation in textures. The frequency of occurrence of these local patterns within a region is used as texture features. Since texture is basically a multi-scale phenomenon, multi-resolution approaches such as wavelets, are expected to perform efficiently for texture analysis. Thus, this study proposes a new algorithm which uses the wavelet domain association rules for texture classification. Essentially, this work is an extension version of an early work of the Rushing et al. [10], [11], where the generation of intensity domain association rules generation was proposed for efficient texture characterization. The wavelet domain and the intensity domain (gray scale) association rules were generated for performance comparison purposes. As a result, Rushing et al. [10], [11] demonstrated that intensity domain association rules performs much more accurate results than those of the methods which were compared in the Rushing et al. work. Moreover, the performed experimental studies showed the effectiveness of the wavelet domain association rules than the intensity domain association rules for texture classification problem. The overall success rate is about 97%. 相似文献
Neural Computing and Applications - A model for an intelligent tutoring system (ITS) that uses fuzzy logic and a constraint-based student model (CBM) is proposed. The goal of the ITS is to teach... 相似文献
This study investigates an application of genetic programming (GP) for the prediction of peak ground acceleration (PGA) using strong-ground-motion data from Turkey. The input variables in the developed GP model are the average shear-wave velocity, earthquake source to site distance and earthquake magnitude, and the output is the PGA values. The proposed GP model is based on the most reliable database compiled for earthquakes in Turkey. The results show that the consistency between the observed PGA values and the predicted ones by the GP model yields relatively high correlation coefficients (R2=0.75). The proposed model is also compared with an existing attenuation relationship and found to be more accurate. 相似文献
One of the most important processes in the diagnosis of breast cancer, which is the leading mortality rate in women, is the detection of the mitosis stage at the cellular level. In literature, many studies have been proposed on the computer-aided diagnosis (CAD) system for detecting mitotic cells in breast cancer histopathological images. In this study, comparative evaluation of conventional and deep learning based feature extraction methods for automatic detection of mitosis in histopathological images are focused. While various handcrafted features are extracted with textural/spatial, statistical and shape-based methods in conventional approach, the convolutional neural network structure proposed on the deep learning approach aims to create an architecture that extracts the features of small cellular structures such as mitotic cells. Mitosis detection/counting is an important process that helps us assess how aggressive or malignant the cancer’s spread is. In the proposed study, approximately 180,000 non-mitotic and 748 mitotic cells are extracted for the evaluations. It is obvious that the classification stage cannot be performed properly due to the imbalanced numbers of mitotic and non-mitotic cells extracted from histopathological images. Hence, the random under-sampling boosting (RUSBoost) method is exploited to overcome this problem. The proposed framework is tested on mitosis detection in breast cancer histopathological images dataset provided from the International Conference on Pattern Recognition (ICPR) 2014 contest. In the results obtained with the deep learning approach, 79.42% recall, 96.78% precision and 86.97% F-measure values are achieved more successfully than handcrafted methods. A client/server-based framework has also been developed as a secondary decision support system for use by pathologists in hospitals. Thus, it is aimed that pathologists will be able to detect mitotic cells in various histopathological images more easily through necessary interfaces.
