摘要 :
Recent development of various domains of Artificial Intelligence including Information Retrieval and Text/Image Understanding created demand on new, sophisticated, contextual methods for data analysis. This article formulates Neur...
展开
Recent development of various domains of Artificial Intelligence including Information Retrieval and Text/Image Understanding created demand on new, sophisticated, contextual methods for data analysis. This article formulates Neuronal Group and Extended Neuron Somatic concepts that can be vastly used in creating such methods. Neural interrelations are described using graphs, construction of which is done in parallel with neural network learning. Prototype technique based on Growing Neural Gas is also presented to give more detailed view.
收起
摘要 :
Together with fast development of different areas of Pattern Analysis, an increasing demand on new models and techniques is observed. Especially new Information Retrieval tasks, oriented on data meaning rather than layout, prove t...
展开
Together with fast development of different areas of Pattern Analysis, an increasing demand on new models and techniques is observed. Especially new Information Retrieval tasks, oriented on data meaning rather than layout, prove to be demanding for most known techniques. Neuronal Group Learning concept presented in this article, together with prototype implementation gives flexibility of utilization of any kind of expert knowledge about the problem to ease classifier inference process. It can also be used to acquire structural knowledge about an object, which can later be used for solving a segmentation problem- often addressed in semantics-oriented text and image processing.
收起
摘要 :
Together with fast development of different areas of Pattern Analysis, an increasing demand on new models and techniques is observed. Especially new Information Retrieval tasks, oriented on data meaning rather than layout, prove t...
展开
Together with fast development of different areas of Pattern Analysis, an increasing demand on new models and techniques is observed. Especially new Information Retrieval tasks, oriented on data meaning rather than layout, prove to be demanding for most known techniques. Neuronal Group Learning concept presented in this article, together with prototype implementation gives flexibility of utilization of any kind of expert knowledge about the problem to ease classifier inference process. It can also be used to acquire structural knowledge about an object, which can later be used for solving a segmentation problem- often addressed in semantics-oriented text and image processing.
收起
摘要 :
Together with fast development of different areas of Pattern Analysis, an increasing demand on new models and techniques is observed. Especially new Information Retrieval tasks, oriented on data meaning rather than layout, prove t...
展开
Together with fast development of different areas of Pattern Analysis, an increasing demand on new models and techniques is observed. Especially new Information Retrieval tasks, oriented on data meaning rather than layout, prove to be demanding for most known techniques. Neuronal Group Learning concept presented in this article, together with prototype implementation gives flexibility of utilization of any kind of expert knowledge about the problem to ease classifier inference process. It can also be used to acquire structural knowledge about an object, which can later be used for solving a segmentation problem- often addressed in semantics-oriented text and image processing.
收起
摘要 :
Digital contours in a binary image can be described as an ordered vector set. In this paper an extension of the string edit distance is defined for its computation between a pair of ordered sets of vectors. This way, the differenc...
展开
Digital contours in a binary image can be described as an ordered vector set. In this paper an extension of the string edit distance is defined for its computation between a pair of ordered sets of vectors. This way, the differences between shapes can be computed in terms of editing costs. In order to achieve efficency a dominant point detection algorithm should be applied, removing redundant data before coding shapes into vectors. This edit distance can be used in nearest neighbour classification tasks. The advantages of this method applied to isolated handwritten character classification are shown, compared to similar methods based on string or tree representations of the binary image.
收起
摘要 :
At present, ID card identification technology plays a very important role in our society which is used to establish information database file in the various departments. In this paper, we design an ID card identification system wh...
展开
At present, ID card identification technology plays a very important role in our society which is used to establish information database file in the various departments. In this paper, we design an ID card identification system which includes these parts image pretreatment, character segmentation, the processing of single character, character recognition and information preservation. The system can achieve the requirements of the ID card recognition and have some reference significance.
收起
摘要 :
A syntactic pattern recognition technique is described based upon a mathematical principle associated with finite sequences of symbols. The technique allows for fast recognition of patterns within strings, including the ability to...
展开
A syntactic pattern recognition technique is described based upon a mathematical principle associated with finite sequences of symbols. The technique allows for fast recognition of patterns within strings, including the ability to recognize expected symbols that are close to the desired symbols, and mutations as well as both local and global substring matching. This allowance of deviation permits sequences to be subject to error and still be recognized. Some examples are provided illustrating the technique.
收起
摘要 :
A syntactic pattern recognition technique is described based upon a mathematical principle associated with finite sequences of symbols. The technique allows for fast recognition of patterns within strings, including the ability to...
展开
A syntactic pattern recognition technique is described based upon a mathematical principle associated with finite sequences of symbols. The technique allows for fast recognition of patterns within strings, including the ability to recognize expected symbols that are close to the desired symbols, and mutations as well as both local and global substring matching. This allowance of deviation permits sequences to be subject to error and still be recognized. Some examples are provided illustrating the technique.
收起
摘要 :
Widely used in the evaluation of retrieval systems, the pooling method collects top ranked images from submitted retrieval systems resulting in possibly a very large pool of images. Inevitably, the pool may contain outliers. Human...
展开
Widely used in the evaluation of retrieval systems, the pooling method collects top ranked images from submitted retrieval systems resulting in possibly a very large pool of images. Inevitably, the pool may contain outliers. Human experts then manually annotate the relevance of them to create a ground truth for evaluation. Studies show that this annotation is time-consuming, tedious and inconsistent. To reduce human workload, this paper introduces an automatic method to detect outliers. Different from traditional detection methods using unsupervised techniques only, we utilize both supervised and unsupervised techniques sequentially as both positive and negative examples are (partially) available in this context. Specifically, support vector machines (SVMs) and fuzzy c-means clustering are used to predict data relevance and "outlier-ness". Performance improvements using our method after outlier removal have been validated on the medical image retrieval task in ImageCLEF 2004.
收起
摘要 :
A new theoretical model of Pattern Recognition principles was proposed, which is based on "matter cognition" instead of "matter classification" in traditional statistical Pattern Recognition. This new model is closer to the functi...
展开
A new theoretical model of Pattern Recognition principles was proposed, which is based on "matter cognition" instead of "matter classification" in traditional statistical Pattern Recognition. This new model is closer to the function of human being, rather than traditional statistical Pattern Recognition using "optimal separating" as its main principle. So the new model of Pattern Recognition is called the Biomimetic Pattern Recognition (BPR). Its mathematical basis is placed on topological analysis of the sample set in the high dimensional feature space. Therefore, it is also called the Topological Pattern Recognition (TPR). The fundamental idea of this model is based on the fact of the continuity in the feature space of any one of the certain kinds of samples. We experimented with the Biomimetic Pattern Recognition (BPR) by using artificial neural networks, which act through covering the high dimensional geometrical distribution of the sample set in the feature space. Omnidirectionally cognitive tests were done on various kinds of animal and vehicle models of rather similar shapes. For the total 8800 tests, the correct recognition rate is 99.87%. The rejection rate is 0.13% and on the condition of zero error rates, the correct rate of BPR was much better than that of RBF-SVM.
收起
原文获取