Semin Kim

Rotation and flipping robust region binary patterns for video copy detection

Many video fingerprints have been proposed to handle the video transformations problems when the original contents are copied and redistributed. However, most of them did not take into account flipping and rotation transformations. In this paper, we propose a novel video fingerprint based on region binary patterns, aiming to realize robust and fast video copy detection against video transformations including rotation and flipping. We extract two complementary region binary patterns from several rings in keyframes. These two kinds of binary patterns are converted into a new type of patterns for the proposed video fingerprint which is robust against rotation and flipping. The experimental results demonstrated that the proposed video fingerprint is effective for video copy detection particularly in the case of rotation and flipping. Furthermore, our experimental results proved that the proposed method allows for high storage efficiency and low computation complexity, which is suitable for practical video copy system.

Adaptive weighted fusion with new spatial and temporal fingerprints for improved video copy detection

In this paper, we propose a new and novel modality fusion method designed for combining spatial and temporal fingerprint information to improve video copy detection performance. Most of the previously developed methods have been limited to use only pre-specified weights to combine spatial and temporal modality information. Hence, previous approaches may not adaptively adjust the significance of the temporal fingerprints that depends on the difference between the temporal variances of compared videos, leading to performance degradation in video copy detection. To overcome the aforementioned limitation, the proposed method has been devised to extract two types of fingerprint information: (1) spatial fingerprint that consists of the signs of DCT coefficients in local areas in a keyframe and (2) temporal fingerprint that computes the temporal variances in local areas in consecutive keyframes. In addition, the so-called temporal strength measurement technique is developed to quantitatively represent the amount of the temporal variances; it can be adaptively used to consider the significance of compared temporal fingerprints. The experimental results show that the proposed modality fusion method outperforms other state-of-the-arts fusion methods and popular spatio-temporal fingerprints in terms of video copy detection. Furthermore, the proposed method can save 39.0%, 25.1%, and 46.1% time complexities needed to perform video fingerprint matching without a significant loss of detection accuracy for our synthetic dataset, TRECVID 2009 CCD Task, and MUSCLE-VCD 2007, respectively. This result indicates that our proposed method can be readily incorporated into the real-life video copy detection systems.

Malicious content filtering based on semantic features

This paper proposes a method to filtering malicious contents using semantic features. In conventional content based approach, low-level features such as color and texture are used to filter malicious contents. But, it is difficult to detect them because of semantic gaps between the low-level features and global concepts. In this paper, global concepts are divided into several semantic features. These semantic features are used to classify the global concept of malicious contents. We design semantic features and construct semantic classifier. In experiment, we evaluate the performance to filter malicious contents by comparing low-level features and semantic features. Results show that our proposed method has better performance than the method using only low-level features.

Semantic Detection of Adult Image Using Semantic Features

Recently, in the fields of internet and social networking, the classification and filtering of naked images has been receiving a significant amount of attention. In this paper, we propose a novel naked image classification which can make effective use of semantic features of a naked image. In addition, a novel measurement, termed accumulated distance ratio (ADR), is proposed in order to systematically analyze the effect of semantic features on improving classification performance, compared to the approach relying on low-level visual features. Extensive experiments have been carried out to assess the effectiveness of semantic features in naked image classification with realistic and challenging data set. The experimental result of the proposed approach using semantic features, for challenging data set, shows improvement up to 14% than the approach using low-level visual feature. Further, the proposed ADR measure has proven to be useful measure for analyzing the effect of semantic features for naked image classification.

Image-based coin recognition using rotation-invariant region binary patterns based on gradient magnitudes

We propose a new feature which is robust against rotation and has high accuracies for image-based coin recognition.The proposed feature used gradient magnitudes for improved image-based coin recognition.We provide results comparing the state-of-the arts for image-based coin recognition. Most features of image-based coin recognition have been based on histogram information to achieve rotation-invariant property. However, discrimination of the features based on histogram information can be reduced by ignoring local spatial structure. In this paper, we propose a novel feature of image-based coin recognition that exploits a spatial structure. In order to consider the structure of a coin, rotation-and-flipping-robust region binary patterns (RFR) is adopted. The proposed method computes gradient magnitudes in a coin image, and extracts RFR using local difference magnitude transform to increase the accuracy of coin recognition. Comparative experiments with a number of state-of-the-art methods have been performed on the MUSCLE CIS-Benchmark Preview data set. The experimental results showed that the proposed method outperformed the state of the art methods in terms of recognition accuracy, smaller feature dimension, and shorter feature extraction time.

A Study for Improved Human Action Recognition using Multi-classifiers

Recently, human action recognition have been developed for various broadcasting and video process. Since a video can consist of various scenes, keypoint approaches have been more attracted than template based methods for real application. Keypoint approahces tried to find regions having motion in video, and made 3-dimensional patches. Then, descriptors using histograms were computed from the patches, and a classifier based on machine learning method was applied to detect actions in video. However, a single classifier was difficult to handle various human actions. In order to improve this problem, approaches using multi classifiers were used to detect and to recognize objects. Thus, we propose a new human action recognition using decision-level fusion with support vector machine and sparse representation. The proposed method extracted descriptors based on keypoint approach from a video, and acquired results from each classifier for human action recognition. Then, we applied weights which were acquired by training stage to fuse each results from two classifiers. The experiment results in this paper show better result than a previous fusion method. Keyword : Human action recognition, Multi classifiers, Decision-level fusion, Support vector machine, Sparse representation. 특집논문 (Special Paper) 방송공학회논문지 제19권 제2호, 2014년 3월 (JBE Vol. 19, No. 2, March 2014) http://dx.doi.org/10.5909/JBE.2014.19.2.166 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) 김세민 외 1인 : 비디오 행동 인식을 위하여 다중 판별 결과 융합을 통한 성능 개선에 관한 연구 167 (Semin Kim et al. : A Study for Improved Human Action Recognition using Multi-classifiers)

Using the fusion of spatial and temporal features for malicious video classification

Recently, malicious video classification and filtering techniques are of practical interest as ones can easily access to malicious multimedia contents through the Internet, IPTV, online social network, and etc. Considerable research efforts have been made to developing malicious video classification and filtering systems. However, the malicious video classification and filtering is not still being from mature in terms of reliable classification/filtering performance. In particular, the most of conventional approaches have been limited to using only the spatial features (such as a ratio of skin regions and bag of visual words) for the purpose of malicious image classification. Hence, previous approaches have been restricted to achieving acceptable classification and filtering performance. In order to overcome the aforementioned limitation, we propose new malicious video classification framework that takes advantage of using both the spatial and temporal features that are readily extracted from a sequence of video frames. In particular, we develop the effective temporal features based on the motion periodicity feature and temporal correlation. In addition, to exploit the best data fusion approach aiming to combine the spatial and temporal features, the representative data fusion approaches are applied to the proposed framework. To demonstrate the effectiveness of our method, we collect 200 sexual intercourse videos and 200 non-sexual intercourse videos. Experimental results show that the proposed method increases 3.75% (from 92.25% to 96%) for classification of sexual intercourse video in terms of accuracy. Further, based on our experimental results, feature-level fusion approach (for fusing spatial and temporal features) is found to achieve the best classification accuracy.

A Statistical and Iterative Method for Data Hiding in Palette-Based Images

This paper proposes an improved iterative method for data hiding in palette-based images, taking into account the statistics of the data that need to be embedded in an image. In particular, the proposed method considers the distribution of the number of zeroes and ones in the input message, as well as how the message bits are distributed over the colors in the image palette. First, according to the statistics of the input message, the proposed method modifies the pixel indexes and the color palette using an enhanced version of an iterative image pre-processing method, replacing less frequent colors by colors that are close to frequently used colors. In a next step, the actual message bits are embedded into the parity bits of the remaining colors. Finally, the proposed method applies a post-processing step, adjusting particular colors in order to further reduce the amount of image distortion. Experimental results show that the proposed method preserves image quality better than previously proposed techniques for data hiding in palette-based images.