• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1998.11a
• /
• pp.181-185
• /
• 1998

Recently, research and developmental direction of communication system is concurrent adopting voice data and face image in speaking to provide more higher recognition rate then in the case of only voice data. Therefore, we present a method of lipreading in speech image sequence by using the 3-D facial shape model. The method use a feature information of the face image such as the opening-level of lip, the movement of jaw, and the projection height of lip. At first, we adjust the 3-D face model to speeching face image sequence. Then, to get a feature information we compute variance quantity from adjusted 3-D shape model of image sequence and use the variance quality of the adjusted 3-D model as recognition parameters. We use the intensity inclination values which obtaining from the variance in 3-D feature points as the separation of recognition units from the sequential image. After then, we use discrete HMM algorithm at recognition process, depending on multiple observation sequence which considers the variance of 3-D feature point fully. As a result of recognition experiment with the 8 Korean vowels and 2 Korean consonants, we have about 80% of recognition rate for the plosives and vowels.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.5
• /
• pp.783-788
• /
• 2002

Recently, research and developmental direction of communication system is concurrent adopting voice data and face image in speaking to provide more higher recognition rate then in the case of only voice data. Therefore, we present a method of lipreading in speech image sequence by using the 3-D facial shape model. The method use a feature information of the face image such as the opening-level of lip, the movement of jaw, and the projection height of lip. At first, we adjust the 3-D face model to speeching face Image sequence. Then, to get a feature information we compute variance quantity from adjusted 3-D shape model of image sequence and use the variance quality of the adjusted 3-D model as recognition parameters. We use the intensity inclination values which obtaining from the variance in 3-D feature points as the separation of recognition units from the sequential image. After then, we use discrete HMM algorithm at recognition process, depending on multiple observation sequence which considers the variance of 3-D feature point fully. As a result of recognition experiment with the 8 Korean vowels and 2 Korean consonants, we have about 80% of recognition rate for the plosives md vowels.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.118-122
• /
• 2000

Nowadays, it is popular to use the spread spectrum watermarking algorithm for still image. But there is high error probability of the retrieved watermark in the spread spectrum owing to the correlation between image and spreaded watermark sequence. In this paper, two methods are proposed. One is Ordering Map Method and the other is Alteration of Image. Based on pixel value, the order by which the spreaded watermark bits is embedded is created in Ordering Map Method. By the covariance function between image and the spreaded sequence, image is altered in Alteration of Image. Hence, bit error of retrieved watermark is clearly reduced to zero by this two method.

• Journal of information and communication convergence engineering
• /
• v.8 no.5
• /
• pp.539-543
• /
• 2010

We present a random bit generator that uses fingerprint image for the source of random, and random bit generator using fingerprint image for the randomness has not been presented as yet. Fingerprint image is affected by the operational environments including sensing act, nonuniform contact and inconsistent contact, and these operational environments make FPI to be used for the source of random possible. Our generator produces, on the average, 9,334 bits a fingerprint image in 0.03 second. We have used the NIST SDB14 test suite consisting of sixteen statistical tests for testing the randomness of the bit sequence generated by our generator, and as the result, the bit sequence passes all sixteen statistical tests.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.291-292
• /
• 2006

This paper presents rate-distortion optimization that is considered sequence statistics(complexity) to choose the best macroblock mode decision in H.264. In previous work, Lagrange multiplier is derived by the function of constant value 0.85 and QP so that is not the proper Lagrange multilplier for any image sequence. The proposed algorithm solves the problem by changing constant value 0.85 into adaptive value which is influenced by image complexity, and by reducing the encoder complexity to estimate the image statistics with the multiplication of transformed, quantized rate and distortion. Proposed algorithm is achieved the bit-rate saving up to 5% better than previous method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.8C
• /
• pp.775-782
• /
• 2005

In case of 3D reconstruction from dense data in uncalibrated sequence images, we encounter with the problem for searching many correspondences and the computational costs. In this paper, we propose a key frame selection method from uncalibrated images and the effective 3D reconstruction method using the key frames. Namely, it can be performed on smaller number of views in the image sequence. We extract correspondences from selected key frames in image sequences. From the extracted correspondences, camera calibration process will be done. We use the edge image to fed dense correspondences between selected key frames. The method we propose to find dense correspondences can be used for recovering the 3D structure of the scene more efficiently.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.122-128
• /
• 1998

This paper presents compression of image sequences based on the classification of interframe difference image blocks. classification process consists of image activity classification and energy distribution classification. In the activity classification, interframe difference image blocks are classified into activity blocks and non-activity blocks using the edge detection. In the distribution classification, activity blocks are further classified into vertical blocks, horizontal blocks, and small activity blocks using the AC energy distribution features. The RBFN, trained with numerical classification results, successfully classifies difference image blocks according to image details. Image sequence compressing based on the classification of interframe difference image blocks using the RBFN shows better compression results and less training time than the classical sorting method and the MLP network.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.5
• /
• pp.767-774
• /
• 1990

Successive images can be reconstructed without great degradation by using one codebook in vector quantization, because statistics of successive images are sinilar. In this paper, we propose a method to update vector centroids in one slot of an image sequence and reconstruct images with the codebook replenished with the updated vector centroids. To remove the overhead required to transmit the updated vector centroids, we catagorize image blocks into changing blocks and nonchanging blocks, and then transmit only the labels of the changing blocks. Therefore, we can assign the remaining bits to the replenishment of a codebook. By the proposed method, almost the same image as the same image as the one reconstructed by LBG algorithm can be obtained and the bit rate can be reduced to below 0.5 bit/pixel.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.621-624
• /
• 1999

This paper describes a distance estimation method of object's motion in soccer image sequence by tracking field features. And we quantitatively evaluate the estimation accuracy We suppose that the input image sequence is taken with a camera on static axis and includes only zooming and panning transformation between frames. Adaptive template matching is adopted for non-rigid object tracking. For background compensation, feature templates selected from reference frame image are matched in following frames and the matched feature point pairs are used in computing Affine motion parameters. A perspective displacement field model is used for estimating the real distance between two position on Input Image. To quantitatively evaluate the accuracy of the estimation, we synthesized a 3 dimensional virtual stadium with graphic tools and experimented on the synthesized 2 dimensional image sequences. The experiment shows that the average of the error between the actual moving distance and the estimated distance is 1.84%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.1
• /
• pp.193-204
• /
• 1997

In this research we propose the design of the Order Statistic-Adaptive Weighted Average Hybrid(OS-AWAH) filter which can suppress noise from the corrupted image sequence effectively while preserving the image structure. The proposed filter combines the desirable properties of the order static based spatial filter which can preserve the image structure while reducing noise and the adaptive weighted average based temporal filter which can adapt the filtering weights according to the amount of motion without motion estimation. Performance characteristics of the OS-AWAH filter in noisy sequences containing moving step edges are investigated throuth computer simulations and compared with the median based filters such as 3-D WM(weighted median) filter, MMF (multistage median filter), ADCWM(adaptive directional center weighted median) filter. The visual evaluations are also carried out by applyin gthe filters to the real images. The statistical analysis and experimental reslts show that the OS-AWAH filter is effective in preserving image structures while suppressing noise effectively without motion compensation preprocessing.