• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.3
• /
• pp.522-538
• /
• 2013

Content based image retrieval has become an increasingly important research topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The retrieval systems rely on a key component, the predefined or learned similarity measures over images. We note that, the similarity measures can be potential improved if the data distribution information is exploited using a more sophisticated way. In this paper, we propose a similarity measure learning approach for image retrieval. The similarity measure, so called Fisher kernel, is derived from the probabilistic distribution of images and is the function over observed data, hidden variable and model parameters, where the hidden variables encode high level information which are powerful in discrimination and are failed to be exploited in previous methods. We further propose a discriminative learning method for the similarity measure, i.e., encouraging the learned similarity to take a large value for a pair of images with the same label and to take a small value for a pair of images with distinct labels. The learned similarity measure, fully exploiting the data distribution, is well adapted to dataset and would improve the retrieval system. We evaluate the proposed method on Corel-1000, Corel5k, Caltech101 and MIRFlickr 25,000 databases. The results show the competitive performance of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2895-2912
• /
• 2014

Content-based image retrieval has been the most important technique for managing huge amount of images. The fundamental yet highly challenging problem in this field is how to measure the content-level similarity based on the low-level image features. The primary difficulties lie in the great variance within images, e.g. background, illumination, viewpoint and pose. Intuitively, an ideal similarity measure should be able to adapt the data distribution, discover and highlight the content-level information, and be robust to those variances. Motivated by these observations, we in this paper propose a probabilistic similarity learning approach. We first model the distribution of low-level image features and derive the free energy kernel (FEK), i.e., similarity measure, based on the distribution. Then, we propose a learning approach for the derived kernel, under the criterion that the kernel outputs high similarity for those images sharing the same class labels and output low similarity for those without the same label. The advantages of the proposed approach, in comparison with previous approaches, are threefold. (1) With the ability inherited from probabilistic models, the similarity measure can well adapt to data distribution. (2) Benefitting from the content-level hidden variables within the probabilistic models, the similarity measure is able to capture content-level cues. (3) It fully exploits class label in the supervised learning procedure. The proposed approach is extensively evaluated on two well-known databases. It achieves highly competitive performance on most experiments, which validates its advantages.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.4
• /
• pp.1424-1440
• /
• 2015

It is a challenging problem to search the intended images from a large number of candidates. Content based image retrieval (CBIR) is the most promising way to tackle this problem, where the most important topic is to measure the similarity of images so as to cover the variance of shape, color, pose, illumination etc. While previous works made significant progresses, their adaption ability to dataset is not fully explored. In this paper, we propose a similarity learning method on the basis of probabilistic generative model, i.e., probabilistic latent semantic analysis (PLSA). It first derives Fisher kernel, a function over the parameters and variables, based on PLSA. Then, the parameters are determined through simultaneously maximizing the log likelihood function of PLSA and the retrieval performance over the training dataset. The main advantages of this work are twofold: (1) deriving similarity measure based on PLSA which fully exploits the data distribution and Bayes inference; (2) learning model parameters by maximizing the fitting of model to data and the retrieval performance simultaneously. The proposed method (PLSA-FK) is empirically evaluated over three datasets, and the results exhibit promising performance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.3
• /
• pp.203-210
• /
• 2000

In this paper, we propose a new unsupervised learning network and competitive learning algorithm for pattern classification. The proposed network is based on relative similarity, which is similarity measure between input data and cluster group. So, the proposed network and algorithm is called relative similarity network(RSN) and learning algorithm. According to definition of similarity and learning rule, structure of RSN is designed and pseudo code of the algorithm is described. In general pattern classification, RSN, in spite of deletion of learning rate, resulted in the identical performance with those of WTA, and SOM. While, in the patterns with cluster groups of unclear boundary, or patterns with different density and various size of cluster groups, RSN produced more effective classification than those of other networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2527-2545
• /
• 2016

Measuring the similarity of given samples is a key problem of recognition, clustering, retrieval and related applications. A number of works, e.g. kernel method and metric learning, have been contributed to this problem. The challenge of similarity learning is to find a similarity robust to intra-class variance and simultaneously selective to inter-class characteristic. We observed that, the similarity measure can be improved if the data distribution and hidden semantic information are exploited in a more sophisticated way. In this paper, we propose a similarity learning approach for retrieval and recognition. The approach, termed as LDA-FEK, derives free energy kernel (FEK) from Latent Dirichlet Allocation (LDA). First, it trains LDA and constructs kernel using the parameters and variables of the trained model. Then, the unknown kernel parameters are learned by a discriminative learning approach. The main contributions of the proposed method are twofold: (1) the method is computationally efficient and scalable since the parameters in kernel are determined in a staged way; (2) the method exploits data distribution and semantic level hidden information by means of LDA. To evaluate the performance of LDA-FEK, we apply it for image retrieval over two data sets and for text categorization on four popular data sets. The results show the competitive performance of our method.

• Journal of KIISE
• /
• v.43 no.6
• /
• pp.653-661
• /
• 2016

The existing pattern-based triple generation systems based on distant supervision could be flawed by assumption of distant supervision. For resolving flaw from an excessive assumption, statistics information has been commonly used for measuring confidence of patterns in previous studies. In this study, we proposed a more accurate confidence measure based on semantic similarity between patterns and properties. Unsupervised learning method, word embedding and WordNet-based similarity measures were adopted for learning meaning of words and measuring semantic similarity. For resolving language discordance between patterns and properties, we adopted CCA for aligning bilingual word embedding models and a translation-based approach for a WordNet-based measure. The results of our experiments indicated that the accuracy of triples that are filtered by the semantic similarity-based confidence measure was 16% higher than that of the statistics-based approach. These results suggested that semantic similarity-based confidence measure is more effective than statistics-based approach for generating high quality triples.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.212-217
• /
• 2009

There are rule-based learning method and statistic based learning method and so on which represent learning method for hierarchy relation between domain term. In this paper, we propose to leveling and similarity measure using the extended AHP of fuzzy term in Information system. In the proposed method, we extract fuzzy term in document and categorize ontology structure about it and level priority of fuzzy term using the extended AHP for specificity of fuzzy term. the extended AHP integrates multiple decision-maker for weighted value and relative importance of fuzzy term. and compute semantic similarity of fuzzy term using min operation of fuzzy set, dice's coefficient and Min+dice's coefficient method. and determine final alternative fuzzy term. after that compare with three similarity measure. we can see the fact that the proposed method is more definite than classification performance of the conventional methods and will apply in Natural language processing field.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.51-55
• /
• 2020

In this paper, an improved FAM is proposed by adopting similarity learning in the existing FAM (Fuzzy Associative Memory) used in image restoration. Image restoration refers to the recovery of the latent clean image from its noise-corrupted version. In serious application like face recognition, this process should be noise-tolerant, robust, fast, and scalable. The existing FAM is a simple single layered neural network that can be applied to this domain with its robust fuzzy control but has low capacity problem in real world applications. That similarity measure is implied to the connection strength of the FAM structure to minimize the root mean square error between the recovered and the original image. The efficacy of the proposed algorithm is verified with significant low error magnitude from random noise in our experiment.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.3
• /
• pp.1025-1031
• /
• 2000

Pre-existing pattern recognition techniques, in the case of character recognition, have limited on the application field. But CAI character learning system and writer's recognition system are very important parts. The application field of pre-existing system can be expanded in the content that the learning of characters and the recognition of writers in the proposed paper. In order to achieve these goals, the development contents are the following: Firstly, pre-processing method by understanding the image structure is proposed, secondly, recognition of characters are accomplished b the histogram distribution characteristics. Finally, similarity measure functions are defined from standard character pattern for matching of the input character pattern. Also the effectiveness of this system is demonstrated by experimenting the standard primitive image.

• Industrial Engineering and Management Systems
• /
• v.11 no.1
• /
• pp.87-93
• /
• 2012

This paper discusses a new weighting method for text analyzing from the view point of supervised learning. The term frequency and inverse term frequency measure (tf-idf measure) is famous weighting method for information retrieval, and this method can be used for text analyzing either. However, it is an experimental weighting method for information retrieval whose effectiveness is not clarified from the theoretical viewpoints. Therefore, other effective weighting measure may be obtained for document classification problems. In this study, we propose the optimal weighting method for document classification problems from the view point of supervised learning. The proposed measure is more suitable for the text classification problem as used training data than the tf-idf measure. The effectiveness of our proposal is clarified by simulation experiments for the text classification problems of newspaper article and the customer review which is posted on the web site.