• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.587-590
• /
• 1999

Gaze detection is to locate the position on a monitor screen where a user is looking at. We implement it by a computer vision system setting a camera above a monitor, and a user move (rotates and or translates) her face to gaze at a different position on the monitor. Up to now, we have tried several different approaches and among them the Two Neural Network approach shows the best result which is described in this paper (1.7 inch error for test data including facial rotation. 3.1 inch error for test data including facial rotation and translation).

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.835-838
• /
• 2008

In this paper, we present automatic face detection and tracking which is robustness in rotation and translation. Detecting a face image, we used Haar-like feature, which is fast detect facial image. Also tracking, we applied Lucas-Kanade feature tracker and KLT algorithm, which has robustness for rotated facial image. In experiment result, we confirmed that face detection and tracking which is robustness in rotation and translation.

• ETRI Journal
• /
• v.30 no.2
• /
• pp.335-337
• /
• 2008

An eye detection method for facial images using Zernike moments with a support vector machine (SVM) is proposed. Eye/non-eye patterns are represented in terms of the magnitude of Zernike moments and then classified by the SVM. Due to the rotation-invariant characteristics of the magnitude of Zernike moments, the method is robust against rotation, which is demonstrated using rotated images from the ORL database. Experiments with TV drama videos showed that the proposed method achieved a 94.6% detection rate, which is a higher performance level than that achievable by the method that uses gray values with an SVM.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.692-702
• /
• 2017

Face detection using the LBP based feature descriptor has issues in that it can not represent spatial information between facial shape and facial components such as eyes, nose and mouth. To address these issues, in previous research, a facial image was divided into a number of square sub-regions. However, since the sub-regions are divided into different numbers and sizes, the division criteria of the sub-region suitable for the database used in the experiment is ambiguous, the dimension of the LBP histogram increases in proportion to the number of sub-regions and as the number of sub-regions increases, the sensitivity to facial orientation rotation increases significantly. In this paper, we present a novel facial region segmentation method that can solve in-plane rotation issues associated with LBP based feature descriptors and the number of dimensions of feature descriptors. As a result, the proposed method showed detection accuracy of 99.0278% from a single facial image rotated in orientation.

• The Journal of the Korea Contents Association
• /
• v.8 no.9
• /
• pp.1-9
• /
• 2008

In this paper, we proposed automatic face detection and tracking which is robustness in rotation. To detect a face image in complicated background and various illuminating conditions, we used face skin color detection. we used Harris corner detector for extract facial feature points. After that, we need to track these feature points. In traditional method, Lucas-Kanade feature tracker doesn't delete useless feature points by occlusion in current scene (face rotation or out of camera). So we proposed the estimation function, which delete useless feature points. The method of delete useless feature points is estimation value at each pyramidal level. When the face was occlusion, we deleted these feature points. This can be robustness to face rotation and out of camera. In experimental results, we assess that using estimation function is better than traditional feature tracker.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.2 s.344
• /
• pp.56-65
• /
• 2006

In this paper, we introduce modified difference type symbol timing detection method of simple structure and show the relations between S/N ratio and timing detection performance which less influenced by multipath channel delay profile and added noise level and it show very exact GI detection performance characteristics. In the computer simulations, 4 symbol time duration of short and long training of IEEE802.11a standard OFDM frame are used for symbol synchronization timing detection. The computer simulation results show the very exact symbol timing detection performance characteristic within 1 sample error of OFDM signal regardless channel delay profile from minimn phase channels of phase rotation ${\pi}/2$ to non-minimum phase channels of phase rotation ${\pi}/2$ of received OFDM signal and added noise level in channel.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.06a
• /
• pp.17-18
• /
• 2008

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.116-128
• /
• 2011

In this paper, we propose the structure of a high-performance face-detection engine that responds well to facial rotating changes using rotation transformation which minimize the required memory usage compared to the previous face-detection engine. The validity of the proposed structure has been verified through the implementation of FPGA. For high performance face detection, the MCT (Modified Census Transform) method, which is robust against lighting change, was used. The Adaboost learning algorithm was used for creating optimized learning data. And the rotation transformation method was added to maintain effectiveness against face rotating changes. The proposed hardware structure was composed of Color Space Converter, Noise Filter, Memory Controller Interface, Image Rotator, Image Scaler, MCT(Modified Census Transform), Candidate Detector / Confidence Mapper, Position Resizer, Data Grouper, Overlay Processor / Color Overlay Processor. The face detection engine was tested using a Virtex5 LX330 FPGA board, a QVGA grade CMOS camera, and an LCD Display. It was verified that the engine demonstrated excellent performance in diverse real life environments and in a face detection standard database. As a result, a high performance real time face detection engine that can conduct real time processing at speeds of at least 60 frames per second, which is effective against lighting changes and face rotating changes and can detect 32 faces in diverse sizes simultaneously, was developed.

• Journal of Korea Multimedia Society
• /
• v.18 no.10
• /
• pp.1197-1204
• /
• 2015

Smoke detection plays an important role for the early detection of fire. In this paper, we suggest a newly developed method that generated LBPV(Local Binary Pattern Variance)s as special feature vectors from RGB contrast images can be applied to detect smoke using SVM(Support Vector Machine). The proposed method rearranges mean value of the block from each R, G, B channel and its intensity of the mean value. Additionally, it generates RGB contrast image which indicates each RGB channel’s contrast via smoke’s achromatic color. Uniform LBPV, Rotation-Invariance LBPV, Rotation-Invariance Uniform LBPV are applied to RGB Contrast images so that it could generate feature vector from the form of LBP. It helps to distinguish between smoke and non smoke area through SVM. Experimental results show that true positive detection rate is similar but false positive detection rate has been improved, although the proposed method reduced numbers of feature vector in half comparing with the existing method with LBP and LBPV.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.309-317
• /
• 2022

In this paper, we propose a machine learning-based copy-move forgery detection network with dual branches. Because the rotation or scaling operation is frequently involved in copy-move forger, the conventional convolutional neural network is not effectively applied in detecting copy-move tampering. Therefore, we divide the input into rotation-invariant and scaling-invariant features based on the wavelet coefficients. Each of the features is input to different branches having the same structure, and is fused in the combination module. Each branch comprises feature extraction, correlation, and mask decoder modules. In the proposed network, VGG16 is used for the feature extraction module. To check similarity of features generated by the feature extraction module, the conventional correlation module used. Finally, the mask decoder model is applied to develop a pixel-level localization map. We perform experiments on test dataset and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.