• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2171-2195
• /
• 2017

When purchasing an online product, a customer tends to be influenced strongly by its reputation, the aggregation of other customers' ratings on it. The reputation, however, is not always trustable since it can be manipulated easily by attackers who intentionally give unfair ratings to their target products. In this paper, we first address identifying trustable users who tend to give fair ratings to products in online rating systems and then propose a method of computing true reputation of a product by aggregating only those trustable users' ratings. In order to identify the trustable users, we list some candidate features that seem related significantly to the trustworthiness of users and verify the robustness of each of the features through extensive experiments. By finding and exploiting these robust features, we are able to identify trustable users and to compute true reputation effectively and efficiently based on fair ratings of those trustable users.

• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.820-828
• /
• 2013

Extracting unique features from an image is a fundamental issue when making panorama images, acquiring stereo images, recognizing objects and analyzing images. Generally, the task to compare features to other images requires much computing time because some features are formed as a vector which has many elements. In this paper, we present a method that compares features after reducing the feature dimension extracted from an image using PCA(principal component analysis) and sorting the features in a linked list. SURF(speeded up robust features) is used to describe image features. When the dimension reduction method is applied, we can reduce the computing time without decreasing the matching accuracy. The proposed method is proved to be fast and robust in experiments.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.1
• /
• pp.57-64
• /
• 2013

In this paper, we propose the classification method of medicine bottle images using the features with color and size information. It is difficult to classify with size feature only, because there are many similar sizes of bottles. Therefore, we suggest a classification method based on color information, which robust to illumination variations. First, we extract MBR(Minimum Boundary Rectangle) of medicine bottle area using Binary Threshold of Red, Green, and Blue in image and classify images with size. Then, hue information and RGB color average rate are used to classify image, which features are robust to lighting variations. Finally, using SURF(Speed Up Robust Features) algorithm, corresponding image can be found from candidates with previous extracted features. The proposed method makes to reduce execution time and minimize the error rate and is confirmed to be reliable and efficient from experiment.

• Journal of Information Processing Systems
• /
• v.12 no.1
• /
• pp.83-99
• /
• 2016

The latest research on the image-based fingerprint matching approaches indicates that they are less complex than the minutiae-based approaches when it comes to dealing with low quality images. Most of the approaches in the literature are not robust to fingerprint rotation and translation. In this paper, we develop a robust fingerprint matching system by extracting the circular region of interest (ROI) of a radius of 50 pixels centered at the core point. Maximizing their orientation correlation aligns two fingerprints that are to be matched. The modified Euclidean distance computed between the extracted orientation features of the sample and query images is used for matching. Extensive experiments were conducted over four benchmark fingerprint datasets of FVC2002 and two other proprietary databases of RFVC 2002 and the AITDB. The experimental results show the superiority of our proposed method over the well-known image-based approaches in the literature.

• ETRI Journal
• /
• v.28 no.4
• /
• pp.502-505
• /
• 2006

A new class-based histogram equalization method is proposed for robust speech recognition. The proposed method aims at not only compensating the acoustic mismatch between training and test environments, but also at reducing the discrepancy between the phonetic distributions of training and test speech data. The algorithm utilizes multiple class-specific reference and test cumulative distribution functions, classifies the noisy test features into their corresponding classes, and equalizes the features by using their corresponding class-specific reference and test distributions. Experiments on the Aurora 2 database proved the effectiveness of the proposed method by reducing relative errors by 18.74%, 17.52%, and 23.45% over the conventional histogram equalization method and by 59.43%, 66.00%, and 50.50% over mel-cepstral-based features for test sets A, B, and C, respectively.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.276-279
• /
• 2011

최근 스마트폰의 카메라를 이용한 시각 검색(Visual Search) 어플리케이션(Application)을 많은 사람들이 이용하고 있고, 이러한 시각 검색 어플리케이션은 여러 가지 특징 추출 방법을 사용하고 있다. 본 논문에서는 특징 추출 방법 중 하나인 Speeded Up Robust Features (SURF)를 사용하여 모바일 환경에 적합한 특징 추출 및 정합 방법에 대하여 기술한다. 모바일 기기들은 기존의 일반 PC환경에 비해 비교적 낮은 성능의 하드웨어 조건을 가지고 있다. 하지만 SURF 특징점 추출 방법 및 정합 방법은 계산량이 많고 복잡하여 실시간 및 모바일 환경에 사용하기엔 제약이 따른다. 모바일 환경에서 높은 성능을 내기 위해 기술자(Descriptor) 차원 감소와 라플라시안(Laplacian) 부호를 이용한 정합, 그리고 최적의 거리 비율로 정합하는 방법을 제안한다.

• MALSORI
• /
• no.60
• /
• pp.145-164
• /
• 2006

This paper proposes class histogram equalization (CHEQ) to compensate noisy acoustic features for robust speech recognition. CHEQ aims to compensate for the acoustic mismatch between training and test speech recognition environments as well as to reduce the limitations of the conventional histogram equalization (HEQ). In contrast to HEQ, CHEQ adopts multiple class-specific distribution functions for training and test environments and equalizes the features by using their class-specific training and test distributions. According to the class-information extraction methods, CHEQ is further classified into two forms such as hard-CHEQ based on vector quantization and soft-CHEQ using the Gaussian mixture model. Experiments on the Aurora 2 database confirmed the effectiveness of CHEQ by producing a relative word error reduction of 61.17% over the baseline met-cepstral features and that of 19.62% over the conventional HEQ.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.381-389
• /
• 2022

Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.

• Journal of Korea Multimedia Society
• /
• v.7 no.7
• /
• pp.877-885
• /
• 2004

In this paper, we propose an enhancement shot change detection method using the neural net and the robust feature selection out of multiple features. The previous shot change detection methods usually used single feature and fixed threshold between consecutive frames. However, contents such as color, shape, background, and texture change simultaneously at shot change points in a video sequence. Therefore, in this paper, we detect the shot changes effectively using robust features, which are supplementary each other, rather than using single feature. In this paper, we use the typical CART (classification and regression tree) of data mining method to select the robust features, and the backpropagation neural net to determine the threshold of the each selected features. And to evaluation the performance of the robust feature selection, we compare the proposed method to the PCA(principal component analysis) method of the typical feature selection. According to the experimental result. it was revealed that the performance of our method had better that than the PCA method.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.31-33
• /
• 2009

Face detection using AdaBoost algorithm is capable of processing images rapidly while having high detection rates. It seemed to be the fastest and the most robust and it is still today. Many improvements or extensions of this method have been proposed. However, previous approaches only deal with upright faces. They suffer from limited discriminant capability for rotated faces as these methods apply the same features for both upright and rotated faces. To solve this problem, it is necessary that we rotate input images or make independently trained detectors. However, this can be slow and can require a lot of training data, since each classifier requires the computation of many different image features. This paper proposes a robust algorithm for finding rotated faces within an image. It reduces the computational and sample complexity, by finding common features that can be shared across the classes. And it will be able to apply with multi-class object detection.