• International Journal of Contents
• /
• v.7 no.4
• /
• pp.24-29
• /
• 2011

In this paper, we propose a method to segment the bottle label in images taken by mobile phones using multi-gradient approaches. In order to segment the label region of interest-object, the saliency map method and Hough Transformation method are first applied to the original images to obtain the candidate region. The saliency map is used to detect the most salient area based on three kinds of features (color, orientation and illumination features). The Hough Transformation is a technique to isolated features of a particular shape within an image. Therefore, we utilize it to find the left and right border of the bottle. Next, we segment the label based on the gradient information obtained from the structure tensor method and edge method. The experimental results have shown that the proposed method is able to accurately segment the labels as the first step of product label recognition system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4665-4683
• /
• 2019

Previous methods build image annotation model by leveraging three basic dependencies: relations between image and label (image/label), between images (image/image) and between labels (label/label). Even though plenty of researches show that multiple dependencies can work jointly to improve annotation performance, different dependencies actually do not "work jointly" in their diagram, whose performance is largely depending on the result predicted by image/label section. To address this problem, we propose the adaptive attention annotation model (AAAM) to associate these dependencies with the prediction path, which is composed of a series of labels (tags) in the order they are detected. In particular, we optimize the prediction path by detecting the relevant labels from the easy-to-detect to the hard-to-detect, which are found using Binary Cross-Entropy (BCE) and Triplet Margin (TM) losses, respectively. Besides, in order to capture the inforamtion of each label, instead of explicitly extracting regional featutres, we propose the self-attention machanism to implicitly enhance the relevant region and restrain those irrelevant. To validate the effective of the model, we conduct experiments on three well-known public datasets, COCO 2014, IAPR TC-12 and NUSWIDE, and achieve better performance than the state-of-the-art methods.

• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.2853-2864
• /
• 2018

Discriminant analysis predicts a class label of a new observation with an unknown label, using information from the existing labeled data. Hence, observed labels play a critical role in the analysis and we usually assume that these labels are correct. If the observed label contains an error, the data has label noise. Label noise can frequently occur in real data, which would affect classification performance. In order to resolve this, a comparative study was carried out using simulated data with label noise. In particular, we considered 4 different classification techniques such as LDA (linear discriminant analysis classifiers), QDA (quadratic discriminant analysis classifiers), KNN (k-nearest neighbour), and SVM (support vector machine). Then we evaluated each method via average accuracy using generated data from various scenarios. The effect of label noise was investigated through its occurrence rate and type (noise location). We confirmed that the label noise is a significant factor influencing the classification performance.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.4
• /
• pp.29-38
• /
• 2020

In this research, we proposed the active pulse classification algorithm using multi-label convolutional neural networks for active sonar system. The proposed algorithm has the advantage of being able to acquire the information of the active pulse at a time, unlike the existing single label-based algorithm, which has several neural network structures, and also has an advantage of simplifying the learning process. In order to verify the proposed algorithm, the neural network was trained using sea experimental data. As a result of the analysis, it was confirmed that the proposed algorithm converged, and through the analysis of the confusion matrix, it was confirmed that it has excellent active pulse classification performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3211-3230
• /
• 2014

Recently, sparse coding has achieved remarkable success in image representation tasks. In practice, the performance of clustering can be significantly improved if limited label information is incorporated into sparse coding. To this end, in this paper, a novel semi-supervised algorithm, called constrained sparse concept coding (CSCC), is proposed for image representation. CSCC considers limited label information into graph embedding as additional hard constraints, and hence obtains embedding results that are consistent with label information and manifold structure information of the original data. Therefore, CSCC can provide a sparse representation which explicitly utilizes the prior knowledge of the data to improve the discriminative power in clustering. Besides, a kernelized version of our proposed CSCC, namely kernel constrained sparse concept coding (KCSCC), is developed to deal with nonlinear data, which leads to more effective clustering performance. The experimental evaluations on the MNIST, PIE and Yale image sets show the effectiveness of our proposed algorithms.

• Journal of Nutrition and Health
• /
• v.39 no.6
• /
• pp.585-591
• /
• 2006

The amount of sodium in the processed foods was evaluated by the information on the nutrition label. One-meal type foods as Ramen, Woodong, Naengmyon provide the most sodium reaching 30 - 70% DV per serving size. In Ramen not much difference was observed for the sodium content by food companies though each company provides various amount of sodium reducing as much as 25% DV. The proportion of female college students who read the nutrition information reached 62% but it remained 32% on the sodium information. They purchase low sodium foods rarely however their intention to buy low sodium foods increased up to 40% in condition that sodium information is given on the food label. Nevertheless 50% of them would not buy low sodium food if the taste is undesirable. Low sodium ramen cooked with 80% soup-base was acceptable by the subjects. Majority of them responded the soup was rather salty indicating the reduction of sodium in ramyeon is possible.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.273-276
• /
• 2019

There is a lot of information in our world, quick access to the most accurate information or finding the information we need is more difficult and complicated. The recommendation system has become important for users to quickly find the product according to user's preference. A social recommendation system using community detection based on label propagation is proposed. In this paper, we applied community detection based on label propagation and collaborative filtering in the movie recommendation system. We implement with MovieLens dataset, the users will be clustering to the community by using label propagation algorithm, Our proposed algorithm will be recommended movie with finding the most similar community to the new user according to the personal propensity of users. Mean Absolute Error (MAE) is used to shown efficient of our proposed method.

• Journal of Nutrition and Health
• /
• v.33 no.7
• /
• pp.763-773
• /
• 2000

On the basis of the concept retained in nutition label(NL) the consumer's perception use and demand on NL nutrition knowledge(NH) purchase of nutrient controlled food and dietary modification for health were examined. The subjects were 1203 house wives mainly in the age of 30-40 and self administered questionnaire was employed. The results were as follows. Subjects' demand on nutrition information was greater while the availablity and usefulness of NL was unsatisfactory. The purchase frequencies of nutrient controlled foods were higher compared to NL reading. The use comprehenison reliability of nutrition information were better in high NK group compared to low NK group except the reliability on health claims. The required nutrients for content information were in the order of calorie Ca cholesterol Fe protein and total fat. The demand for nutrient content information was carrelated with intention of subjects' dietary modification but not the use of NL. These results indicate that NL be a good source of nutrition information and the consumers' demand for NL was based on their dietary purpose though the use of NL was unconfirmed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.8B
• /
• pp.689-698
• /
• 2008

The performance of a TCP protocol on MANETs has been studied in a numerous researches. One of the significant reasons of TCP performance degradation on MANETs is inability to distinguish between packet losses due to congestion from those caused by nodes mobility and as consequence broken routes. This paper presents the Cluster-Label-based Routing (CLR) protocol that is an attempt to compensate source of TCP problems on MANETs - multi-hop mobile environment. By utilizing Cluster-Label-based mechanism for Backbone, the CLR is able to concentrate on detection and compensation of movement of a destination node. The proposed protocol provides better goodput and delay performance than standardized protocols especially in cases of large network size and/or high mobility rate.

• Korean Journal of Remote Sensing
• /
• v.28 no.6
• /
• pp.671-682
• /
• 2012

Strong backscattering features from high-resolution Synthetic Aperture Rader (SAR) image provide useful information to analyze earth surface characteristics such as man-made objects in urban areas. The SAR image has, however, some limitations on description of detail information in urban areas compared to optical images. In this paper, we propose a new classification method using a fused SAR and Electro-Optical (EO) image, which provides more informative classification result than that of a single-sensor SAR image classification. The experimental results showed that the proposed method achieved successful results in combination of the SAR image classification and EO image characteristics.