Unsupervised segmentation of gray level Markov model textures with hierarchical self organizing maps

Goktepe, M.; Yalabik, Nese; Atalay, Volkan

doi:10.1109/icpr.1996.547240

Cited by 10 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be mentioned that there are other hierarchical self-organizing neural networks [21], [22], but the neural network structures and learning process of these networks are different from ours. In [21], there are self-organizing maps at two levels: the state map and the dynamics maps.…”

Section: B Hierarchical Self-organizing Neural Networkmentioning

confidence: 99%

“…Second, the best matching unit from the second map is chosen and its index is the output of the hierarchical network. The existing hierarchical self-organizing map methods have a mul tilayer structure and two training phases (we refer to [21], [22] for more details). In our hierarchical self-organizing structure, all neurons are partitioned into several internal nets; the internal nets and the external net are both in the same layer; and there is no two stage training phase, unlike existing hierarchical self-organizing maps.…”

Section: B Hierarchical Self-organizing Neural Networkmentioning

confidence: 99%

“…The learning process consists of two phases: first the training of the state map and next the training of the dynamics maps. In [22], the hierarchical self-organizing map is composed of two self-organizing maps. [7].…”

Section: B Hierarchical Self-organizing Neural Networkmentioning

confidence: 99%

See 2 more Smart Citations

A Hierarchical Self-Organizing Approach for Learning the Patterns of Motion Trajectories

Xie

Tan

2004

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Abstract-The understanding and description of object behav iors is a hot topic in computer vision. Trajectory analysis is one of the basic problems in behavior understanding, and the learning of trajectory patterns that can be used to detect anomalies and predict object trajectories is an interesting and important problem in tra jectory analysis. In this paper, we present a hierarchical self-orga nizing neural network model and its application to the learning of trajectory distribution patterns for event recognition. The distribu tion patterns of trajectories are learnt using a hierarchical self-or ganizing neural network. Using the learned patterns, we consider anomaly detection as well as object behavior prediction. Compared with the existing neural network structures that are used to learn patterns of trajectories, our network structure has smaller scale and faster learning speed, and is thus more effective. Experimental results using two different sets of data demonstrate the accuracy and speed of our hierarchical self-organizing neural network in learning the distribution patterns of object trajectories.Index Terms-Hierarchical self-organizing neural network, tra jectory analysis and learning, anomaly detection, behavior predic tion.

show abstract

Section: B Hierarchical Self-organizing Neural Networkmentioning

confidence: 99%

Section: B Hierarchical Self-organizing Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

A Hierarchical Self-Organizing Approach for Learning the Patterns of Motion Trajectories

Xie

Tan

2004

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

show abstract

“…The value at each pixel in the lattice is a random variable; for example, for gray scale images with 256 gray levels, each random variable can take a value in the set {0, 1, 2, ..., 255} 9,10 .…”

Section: Gabor Filtersmentioning

confidence: 99%

A comparison of texture models for automatic liver segmentation

et al. 2007

View full text Add to dashboard Cite

Automatic liver segmentation from abdominal computed tomography (CT) images based on gray levels or shape alone is difficult because of the overlap in gray-level ranges and the variation in position and shape of the soft tissues. To address these issues, we propose an automatic liver segmentation method that utilizes low-level features based on texture information; this texture information is expected to be homogenous and consistent across multiple slices for the same organ. Our proposed approach consists of the following steps: first, we perform pixel-level texture extraction; second, we generate liver probability images using a binary classification approach; third, we apply a split-and-merge algorithm to detect the seed set with the highest probability area; and fourth, we apply to the seed set a region growing algorithm iteratively to refine the liver's boundary and get the final segmentation results. Furthermore, we compare the segmentation results from three different texture extraction methods (Co-occurrence Matrices, Gabor filters, and Markov Random Fields (MRF)) to find the texture method that generates the best liver segmentation. From our experimental results, we found that the co-occurrence model led to the best segmentation, while the Gabor model led to the worst liver segmentation. Moreover, co-occurrence texture features alone produced approximately the same segmentation results as those produced when all the texture features from the combined co-occurrence, Gabor, and MRF models were used. Therefore, in addition to providing an automatic model for liver segmentation, we also conclude that Haralick co-occurrence texture features are the most significant texture characteristics in distinguishing the liver tissue in CT scans.

show abstract

“…Especially, random field models such as Gibbs and Markov random fields have been extensively used to model images [16,17,18,19]. …”

Section: Introductionmentioning

confidence: 99%

Texture Classification and Retrieval Using the Random Neural Network Model

Teke

Atalay

2006

CMS

View full text Add to dashboard Cite

Texture is one of the most important characteristics used in computer vision and image processing applications. In this thesis, a new texture classification and retrieval method is proposed for texture analysis applications. The technique makes use of the random neural network model and it is supervised. The main aim is to represent textures with parameters which are the random neural network weights and classify and retrieve textures using this texture definition. The network has neurons that correspond to each image pixel, and the neurons are connected according to neighboring relationship between pixels. The method is tested on artificial images produced by using Brodatz album and texture blocks cut from remotely sensed imagery.

show abstract

Unsupervised segmentation of gray level Markov model textures with hierarchical self organizing maps

Cited by 10 publications

References 11 publications

A Hierarchical Self-Organizing Approach for Learning the Patterns of Motion Trajectories

A Hierarchical Self-Organizing Approach for Learning the Patterns of Motion Trajectories

A comparison of texture models for automatic liver segmentation

Texture Classification and Retrieval Using the Random Neural Network Model

Contact Info

Product

Resources

About