• 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 IKEEE
• /
• v.22 no.2
• /
• pp.491-494
• /
• 2018

This paper presents a similarity search method based on mixed norm for enhancing self-example-based single image super-resolution. In order to incorporate the local statistical characteristics of the patches into the super-resolution image reconstruction, we propose a method to determine the order of the norm according to the patch inclination and use it as a similarity search between patches. Experimental results demonstrate that the proposed similarity search method has the capability to improve the performance of existing search method.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.4
• /
• pp.6-13
• /
• 2011

Due to its robustness to illumination change, normalized cross-correlation based similarity measurement is widely used in many machine vision applications. However, its inefficient computation structure is not adequate for real-time embedded vision system. In this paper, we present an efficient hardware architecture based on a normalized cross correlation (NCC) for fast image similarity measure. The proposed architecture simplifies window-sum process of the NCC using the integral-image. Relieving the overhead to constructing integral image, we make it possible to process integral image construction at the same time that pixel sequences are inputted. Also the proposed segmented integral image method can reduce the buffer size for storing integral image data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.4
• /
• pp.684-690
• /
• 2009

In this paper, we proposed a new method of the steganography based on bit plane using similarity. Applying a fixed threshold, the insert information into all bit planes showed different image quality. Therefore, we first defined the bit plane of block similarity to solve the fixing threshold problem. We then proposed a new method using the Bit Plane complexity and similarity to insert information into bit planes of block. In the experiment, we inserted information into the standard images with the same image quality and same insertion capacity. Finally analyzed the insertion capacity and image quality. As a result, the proposed method increased the insertion capacity of about 6% and improved the image quality of about 3.3dB than fixing threshold method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.14 no.4 s.38
• /
• pp.71-77
• /
• 2006

Support Vector Machine (SVM) which has roots in a statistical learning theory is a training algorithm based on structural risk minimization. Generally, SVM algorithm uses the kernel for determining a linearly non-separable boundary and classifying the data. But, classical kernels can not apply to effectively the hyperspectral image classification because it measures similarity using vector's dot-product or euclidian distance. So, This paper proposes the spectral similarity kernel to solve this problem. The spectral similariy kernel that calculate both vector's euclidian and angle distance is a local kernel, it can effectively consider a reflectance property of hyperspectral image. For validating our algorithm, SVM which used polynomial kernel, RBF kernel and proposed kernel was applied to land cover classification in Hyperion image. It appears that SVM classifier using spectral similarity kernel has the most outstanding result in qualitative and spatial estimation.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.664-672
• /
• 2009

Recently, studies on utilizing tensor expression on image data analysis and processing have been attracting much interest. The purpose of this study is to develop an efficient system for classifying image patterns by using second order tensor expression. To achieve the goal, we propose a data generation model expressed by class factors and environment factors with second order tensor representation. Based on the data generation model, we define a function for measuring similarities between two images. The similarity function is obtained by estimating the probability density of environment factors using a matrix normal distribution. Through computational experiments on a number of benchmark data sets, we confirm that we can make improvement in classification rates by using second order tensor, and that the proposed similarity function is more appropriate for image data compared to conventional similarity measures.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.35 no.1 s.120
• /
• pp.59-68
• /
• 2007

This article statistically analyzed contributive levels of district image based on an effect and a similarity index through the evaluation of citizens and suggested the efficient management system of a city image according to the results. For this study, Busan City was selected as a case city by the preceding literature and was investigated concerning district image and city image through a questionnaire. The new evaluation method for analysis of a city image was presented in this process. The results of this research are as follows: 1. Busan City has a substantial positive and culturally unique image, and each of its districts have other image characteristics. for example, the CBD district has a positive image, and the sea shore district has a busy and prosperous image, but the backward sea shore district has an image of stagnancy. 2. The image of Yeonje-gu has the largest effect on the image of Busan. Next in influence are Jung-gu, Saha-gu, Suyoung-gu, respectively. The effect index is closely connected with the variance of evaluative adjectives. 3. Busanjin-gu and Haeundae-gu have similar images to Busan City. Next in similarity are Nam-gu, Jung-gu, Youngdo-gu, Suyoung-gu, respectively. The similarity index is closely connected with the correlation of evaluative adjectives. Busan City and its districts can establish their image strategies with the above analyzed results. This study is meaningful in that a statistical evaluative method was proposed. With continued follow-up research, this study may serve as a systematic and logical model to improve the urban landscape and image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.5
• /
• pp.960-966
• /
• 2017

In this paper, we proposed an algorithm that can extract lesion by inputting a medical image. Feature points are extracted using SIFT algorithm to extract genetic training of medical image. To increase the intensity of the feature points, the input image and that raining image are matched using vector similarity and the lesion is extracted. The vector similarity match can quickly lead to lesions. Since the direction vector is generated from the local feature point pair, the direction itself only shows the local feature, but it has the advantage of comparing the similarity between the other vectors existing between the two images and expanding to the global feature. The experimental results show that the lesion matching error rate is 1.02% and the processing speed is improved by about 40% compared to the case of not using the feature point intensity information.

• Journal of Computing Science and Engineering
• /
• v.8 no.2
• /
• pp.65-77
• /
• 2014

To address the problem of multi-target retrieval (MTR) of remote sensing images, this study proposes a new object-level feature representation model. The model provides an enhanced application image representation that improves the efficiency of MTR. Generating the model in our scheme includes processes, such as object-oriented image segmentation, feature parameter calculation, and symbolic image database construction. The proposed model uses the spatial representation method of the extended nine-direction lower-triangular (9DLT) matrix to combine spatial relationships among objects, and organizes the image features according to MPEG-7 standards. A similarity metric method is proposed that improves the precision of similarity retrieval. Our method provides a trade-off strategy that supports flexible matching on the target features, or the spatial relationship between the query target and the image database. We implement this retrieval framework on a dataset of remote sensing images. Experimental results show that the proposed model achieves competitive and high-retrieval precision.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.4
• /
• pp.61-67
• /
• 2009

PACS and Medical Image System use only high level metadata in retrieving desired image nowadays. In order to retrieve Medical Image Data more efficiently, it would be needed to retrieve similarity by utilizing low level metadata as well as keyword retrieval by high level metadata. Thus, In this paper presents that it has realized similarity retrieval by low level metadata on the basis of MPEG-7, and keyword retrieval by high level metadata of DICOM base. It would be also available to look into medical image data in various methods and read accurate image promptly for diagnosis and treatment by retrieval with integrating two metadata.