Extraction of skeletal shape from a 2D dot pattern is discussed. We use a self-organizing neural network model to get a piecewise linear approximation of a skeleton of the pattern. It is found that even without a prop...
详细信息
Extraction of skeletal shape from a 2D dot pattern is discussed. We use a self-organizing neural network model to get a piecewise linear approximation of a skeleton of the pattern. It is found that even without a proper definition of a skeleton, the proposed algorithm is able to produce skeletons that are quite close to what we intuitively feel it should be. In Kohonen's self-organizing model, the set of processors and their neighbourhoods are fixed. We suggest here some modifications of it in which the set of processors and their neighbourhoods change adaptively.
Road networks are important features of satellite imagery. The main contribution of the present road detection method consists of an effective enhancement technique and an efficient segmentation technique that removes...
详细信息
Road networks are important features of satellite imagery. The main contribution of the present road detection method consists of an effective enhancement technique and an efficient segmentation technique that removes non-road pixels step by step from the image where parameters involved: in each step images are determined by the sensor characteristics (like spatial resolution and spectral range) of the satellite. Also, the segmentation process depends not only on the road contrast but also on the road length. Thus, a low contrast but long road segment does not get removed. We have tested the algorithm on a number of images from IRS and SPOT satellites and the results are satisfactory.
This paper considers optical character recognition (OCR) of Bangla, the second most popular script in the indian subcontinent. A complete OCR system is described for documents of single Bangla font, where more than th...
详细信息
This paper considers optical character recognition (OCR) of Bangla, the second most popular script in the indian subcontinent. A complete OCR system is described for documents of single Bangla font, where more than three hundred character shapes are recognized by a combination of template and feature-matching approach. Here the document image captured by a flatbed scanner is subject to tilt correction, line, word and character segmentation, simple and compound character separation, feature extraction and finally character recognition. Some character occurrence statistics have been computed to aid the recognition process. The simple character recognition is done by a feature-based tree classifier, and the compound character recognition involves a template matching approach preceded by a feature-based grouping. At present, recognition accuracy of about 96% is obtained by the system.
The backpropagation algorithm helps a multilayer perceptron to learn to map a set of inputs to a set of outputs. But often its function approximation performance is not impressive. In this paper the authors demonstrat...
详细信息
The backpropagation algorithm helps a multilayer perceptron to learn to map a set of inputs to a set of outputs. But often its function approximation performance is not impressive. In this paper the authors demonstrate that self-adaptation of the learning rate of the backpropagation algorithm helps in improving the approximation of a function. The modified backpropagation algorithm with self-adaptive learning rates is based on a combination of two updating rules-one for updating the connection weights and the other for updating the learning rate. The method for learning rate updating implements the gradient descent principle on the error surface. Simulation results with astrophysical data are presented.
Due to the numerous applications of boundary maps and occlusion orientation maps (ORI-maps) in high-level vision problems, accurate estimation of these maps is a crucial task. The existing deep networks employ a singl...
详细信息
Due to the numerous applications of boundary maps and occlusion orientation maps (ORI-maps) in high-level vision problems, accurate estimation of these maps is a crucial task. The existing deep networks employ a single-stream network to estimate the relation between boundary map and ORI-map estimation. However, these networks fail to explore significant individual information separately. To resolve this problem, in this paper, we propose a novel two-stream generative adversarial network (GAN) for boundary map and ORI-map estimation, named OBP-GAN. The proposed OBP-GAN consists of two streams known as BP-GAN and OR-GAN. The BP-GAN estimates the boundary map, and the OR-GAN predicts the ORI-map. The boundary and ORI-map can also be useful cues for the task of depth-map refinement from single images. Therefore, in this work, we propose a transformer-based depth-map refinement network (TRANSDMR-GAN) for refining the depth estimated from monocular images using boundary and ORI-map. We conducted extensive analyses on indoor and outdoor datasets to validate our proposed OBP-GAN and TRANSDMR-GAN. The extensive experimental analysis and ablation study demonstrate the ability of the proposed OBP-GAN to generate state-of-the-art occlusion boundary maps. Furthermore, we show that the proposed network, TRANSDMR-GAN, can generate an edge-enhanced depth map without degrading the accuracy of the initial depth map.
It is our great pleasure to welcome you to the 11th International Conference on Neural Information Processing (ICONIP 2004) to be held in Calcutta. ICONIP 2004 is organized jointly by the indian Statistical institute ...
详细信息
ISBN:
(数字)9783540304999
ISBN:
(纸本)9783540239314
It is our great pleasure to welcome you to the 11th International Conference on Neural Information Processing (ICONIP 2004) to be held in Calcutta. ICONIP 2004 is organized jointly by the indian Statistical institute (ISI) and Jadavpur University (JU). We are con?dent that ICONIP 2004, like the previous conf- ences in this series,will providea forum for fruitful interactionandthe exchange of ideas between the participants coming from all parts of the globe. ICONIP 2004 covers all major facets of computational intelligence, but, of course, with a primary emphasis on neural networks. We are sure that this meeting will be enjoyable academically and otherwise. We are thankful to the track chairs and the reviewers for extending their support in various forms to make a sound technical program. Except for a few cases, where we could get only two review reports, each submitted paper was reviewed by at least three referees, and in some cases the revised versions were againcheckedbythereferees. Wehad470submissionsanditwasnotaneasytask for us to select papers for a four-day conference. Because of the limited duration of the conference, based on the review reports we selected only about 40% of the contributed papers. Consequently, it is possible that some good papers are left out. We again express our sincere thanks to all referees for accomplishing a great job. In addition to 186 contributed papers, the proceedings includes two plenary presentations, four invited talks and 18 papers in four special sessions. The proceedings is organized into 26 coherent topical groups.
暂无评论