• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.332-333
• /
• 2021

In this paper, we propose a new image classification method based on several trainings, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small data sets and to improve classification accuracy.

• 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.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.445-454
• /
• 2014

In recent days, trend technologies for cloud, bigdata, or mobile, as the important marketable keywords or paradigm in Information Communication Technology (ICT), are widely used and interrelated each other in the various types of platforms and web-based services. Especially, the combination of cloud and mobile is recognized as one of a profitable business models, holding benefits of their own. Despite these challenging aspects, there are a few application cases of this model dealing with geo-based data sets or imageries. Among many considering points for geo-based cloud application on mobile, this study focused on a performance test of mobile cloud of Bayesian image fusion algorithm with satellite images. Two kinds of cloud platform of Amazon and OpenStack were built for performance test by CPU time stamp. In fact, the scheme for performance test of mobile cloud is not established yet, so experiment conditions applied in this study are to check time stamp. As the result, it is revealed that performance in two platforms is almost same level. It is implied that open source mobile cloud services based on OpenStack are enough to apply further applications dealing with geo-based data sets.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1067-1076
• /
• 2020

In this paper, an unsupervised saliency guided change detection method using UAV and aerial imagery is proposed. Regions that are more different from other areas are salient, which make them more distinct. The existence of the substantial difference between two images makes saliency proper for guiding the change detection process. Change Vector Analysis (CVA), which has the capability of extracting of overall magnitude and direction of change from multi-spectral and temporal remote sensing data, is used for generating an initial difference image. Combined with an unsupervised CVA and the saliency, Principal Component Analysis(PCA), which is possible to implemented as the guide for change detection method, is proposed for UAV and aerial images. By implementing the saliency generation on the difference map extracted via the CVA, potentially changed areas obtained, and by thresholding the saliency map, most of the interest areas correctly extracted. Finally, the PCA method is implemented to extract features, and K-means clustering is applied to detect changed and unchanged map on the extracted areas. This proposed method is applied to the image sets over the flooded and typhoon-damaged area and is resulted in 95 percent better than the PCA approach compared with manually extracted ground truth for all the data sets. Finally, we compared our approach with the PCA K-means method to show the effectiveness of the method.

• International Journal of Computer Science & Network Security
• /
• v.24 no.6
• /
• pp.8-16
• /
• 2024

Communication with the deaf has always been crucial. Deaf and hard-of-hearing persons can now express their thoughts and opinions to teachers through sign language, which has become a universal language and a very effective tool. This helps to improve their education. This facilitates and simplifies the referral procedure between them and the teachers. There are various bodily movements used in sign language, including those of arms, legs, and face. Pure expressiveness, proximity, and shared interests are examples of nonverbal physical communication that is distinct from gestures that convey a particular message. The meanings of gestures vary depending on your social or cultural background and are quite unique. Sign language prediction recognition is a highly popular and Research is ongoing in this area, and the SVM has shown value. Research in a number of fields where SVMs struggle has encouraged the development of numerous applications, such as SVM for enormous data sets, SVM for multi-classification, and SVM for unbalanced data sets.Without a precise diagnosis of the signs, right control measures cannot be applied when they are needed. One of the methods that is frequently utilized for the identification and categorization of sign languages is image processing. African Buffalo Optimization using Support Vector Machine (ABO+SVM) classification technology is used in this work to help identify and categorize peoples' sign languages. Segmentation by K-means clustering is used to first identify the sign region, after which color and texture features are extracted. The accuracy, sensitivity, Precision, specificity, and F1-score of the proposed system African Buffalo Optimization using Support Vector Machine (ABOSVM) are validated against the existing classifiers SVM, CNN, and PSO+ANN.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.331-336
• /
• 1999

The optical sensors of Electro-Optical Camera (EOC) and Ocean Scanning Multi-spectral Imager (OSMI) aboard the Korea Multi-Purpose SATellite (KOMPSAT) will be placed in a sun synchronous orbit in 1999. The EOC and OSMI sensors are expected to produce the land mapping imagery of Korean territory and the ocean color imagery of world oceans, respectively. Utilization of the EOC and OSMI data would encompass the various fields of science and technology such as land mapping, land use and development, flood monitoring, biological oceanography, fishery, and environmental monitoring. Readiness of data support for user community is thus essential to the success of the KOMPSAT program. As part of testing such readiness prior to the KOMPSAT launch, we have performed the preliminary acceptance test for the KOMPSAT data processing system using the simulated EOC and OSMI data sets. The purpose of this paper is to demonstrate the readiness of the KOMPSAT data processing system, and to help data users understand how the KOMPSAT EOC and OSMI data are processed and archived. Test results demonstrate that all requirements described in the data processing specification have been met, and that the image integrity is maintained for all products. It is however noted that since the product accuracy is limited by the simulated sensor data, any quantitative assessment of image products can not be made until actual KOMPSAT images will be acquired.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.96-102
• /
• 2012

An advanced form of the Partitioned Feature-based Classifier with Expertise Table(PFC-ET) is proposed in this paper. As is the case with the PFC-ET, the proposed classifier model, called Classifier Integration Model(CIM), does not use the entire feature vectors extracted from the original data in a concatenated form to classify each datum, but rather uses groups of features related to each feature vector separately. The proposed CIM utilizes a proportion of selected cluster members instead of the expertise table in PFC-ET to minimize the error in confusion table. The proposed CIM is applied to the classification problem on two data sets, Caltech data set and collected terrain data sets. When compared with PFC model and PFC-ET model. the proposed CIM shows improvements in terms of classification accuracy and post processing efforts.

• The Research Journal of the Costume Culture
• /
• v.16 no.5
• /
• pp.841-851
• /
• 2008

The purpose of the study was to examine the effect of motif categories and motif colors on evaluating sensory image of fashion materials with the gestalt theory as the background. The research was conducted on a quasi experimental basis, with subjects numbering 187 male and 207 female college students. Data were collected in the period from march 19th to march 31st, 2007. A set of fabric stimuli and semantic differential scales were developed. The stimuli were thirteen fabric species(each measuring 12 by 13cm). Variables included; (a) motif colour(white, grey, pink and blue) (b) motif categories(plain, paisley, flower, stripes and zebra effect). The semantic differential scale to measure sensory image of fabric stimuli included 23 sets of bi-polar adjectives. The data were analysed by factor analysis and ANOVA and the major finding were as follows. 1) Four sensory dimensions emerged of importance: salience, attractiveness, comfort and softness. 2) The motif category effected on the four sensory image dimensions while the motif colour effected on salience, comfort and softness sensory dimensions. 3) An interaction effect was founded between motif category and motif colour. 4) Motif category showed significant effects on the preference and liking of the fashion, however the motif colour did not show any significant effects on the preference and liking. As a whole the results supported the gestalt theory and the results can be used for the marketing strategy for developing fashion fabrics.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.78.1-78.1
• /
• 2019

There are a huge number of faint objects that have not been observed due to the lack of large and deep surveys. In this study, we demonstrate that a deep learning approach can produce a better quality deep image from a single pass imaging so that could be an alternative of conventional image stacking technique or the expensive large and deep surveys. Using data from the Sloan Digital Sky Survey (SDSS) stripe 82 which provide repeatedly scanned imaging data, a training data set is constructed: g-, r-, and i-band images of single pass data as an input and r-band co-added image as a target. Out of 151 SDSS fields that have been repeatedly scanned 34 times, 120 fields were used for training and 31 fields for validation. The size of a frame selected for the training is 1k by 1k pixel scale. To avoid possible problems caused by the small number of training sets, frames are randomly selected within that field each iteration of training. Every 5000 iterations of training, the performance were evaluated with RMSE, peak signal-to-noise ratio which is given on logarithmic scale, structural symmetry index (SSIM) and difference in SSIM. We continued the training until a GAN model with the best performance is found. We apply the best GAN-model to NGC0941 located in SDSS stripe 82. By comparing the radial surface brightness and photometry error of images, we found the possibility that this technique could generate a deep image with statistics close to the stacked image from a single-pass image.