Seungjoon Yang

Block-based noise estimation using adaptive Gaussian filtering

We propose a fast noise estimation algorithm using a Gaussian pre-filter. The coefficients of the Gaussian filter are selected according to the standard deviation of the Gaussian noise estimated from an input noisy image. The standard deviation is estimated from the difference image between the noisy input image and its filtered image. This algorithm can be applied to noise reduction in commercial image- or video-based applications such as digital cameras and digital television (DTV) for its performance and simplicity.

Maximum-likelihood parameter estimation for image ringing-artifact removal

At low bit rates, image compression codecs based on overlapping transforms introduce spurious oscillations known as ringing artifacts in the vicinity of major edges. Unlike previous works, we present a maximum-likelihood approach to the ringing-artifact removal problem. Our approach employs a parameter estimation method based on the k-means algorithm with the number of clusters determined by a cluster-separation measure. The proposed algorithm and its simplified approximation are applied to JPEG2000 compressed images. Our results show effective and efficient removal of ringing artifacts.

Contrast enhancement using histogram equalization with bin underflow and bin overflow

The histogram equalization (HE) is a widely used contrast enhancement method. But what is missing from the HE is a mechanism to control the rate of enhancement. The enhanced image always follows the uniform distribution. This paper presents a simple enhancement rate control mechanism for the HE. The gradient of the mapping function is controlled by putting constraints on the probability density function with the bin underflow (BU) and bin overflow (BO). The BUBO operation can provide the rate of enhancement from non to the full HE with a single parameter. With the enhancement rate control mechanism available, the HE can be used to perform image processing tasks such as black/white level stretch or automatic brightness control as well as variable rate contrast enhancement.

Maximum likelihood parameter estimation for image ringing artifact removal

At low bit rates, image compression codecs based on overlapping transforms introduce spurious oscillation known as ringing artifacts in the vicinity of major edges. The image quality can be enhanced considerably by removing the artifacts. We present a maximum likelihood approach to the ringing artifact removal problem. Our approach employs a parameter estimation method based on the k-means algorithm with the number of clusters determined by a cluster separation measure. The proposed algorithm and its simplified approximation are applied to JPEG2000 compressed images to demonstrate their effectiveness.

An effective de-interlacing technique using two types of motion information

In this paper, we propose a new de-interlacing algorithm using two types of motion information, i.e., the block-based and the pixel-based motion information. In the proposed scheme, block-wise motion is first calculated using the frame differences. Then, it is refined by the pixel-based motion information. The results of hardware implementation show that the proposed scheme using block-wise motion is more robust to noise than the conventional schemes using pixel-wise motion. Also, the proposed spatial interpolation provides a good visual performance in the case of moving diagonal edges.

Image interpolation using interpolative classified vector quantization

According to advances in digital imaging technology, interest in high-resolution (HR) images has been increased. Various methods that convert low-resolution (LR) images to HR ones have been presented. In this paper, to reduce the computational load we propose a vector quantization (VQ) based algorithm that reconstructs an interpolation image by adding to an initially interpolated image high-frequency components predicted from training with a number of example image sets. The proposed interpolative classified VQ (ICVQ) algorithm combines interpolative VQ with classified VQ. With a number of (LR and HR) example image sets, we construct two types of (LR and HR) codebooks. Comparative experiments with three conventional image interpolation algorithms show that the proposed interpolation algorithms using ICVQ effectively preserve edges to which the human visual system is sensitive. The proposed algorithm can be applicable to various image- and video-based applications such as digital camera and digital television.

Bilateral interpolation filters for image size conversion

This paper presents an image size conversion method based on bilateral filtering. We formulate interpolation with bilateral filters by an optimization problem, with which we can enforce the interpolation constraint as well as smoothness constraint. The designed bilateral filter can be used in image size conversion, providing better pass-band characteristics and less artifacts from aliasing.

Motion compensation assisted motion adaptive interlaced-to-progressive conversion

This paper presents a novel interlaced-to-progressive conversion (IPC) method based on the motion adaptive IPC (MA-IPC) with its adaptation assisted by the motion compensation. The motion adaptation is performed with respect to a motion selected from a limited set based on the accuracy evaluated with a reduced and overlapped block. The use of the reduced and overlapped blocks makes the evaluation of the accuracy more precise, and the implementation less costly. The motion adaptation structure ensures that any possible error occurs pixel-wise, so that block-wise spurious error can be eliminated. The estimation of the motion is performed efficiently with data already available for the motion adaptation. The proposed motion compensation assisted motion adaptive IPC (MoMA-IPC) method provides image quality similar to the motion compensated IPC (MC-IPC) for those images the MC-IPC offers significant improvement over the MA-IPC, yet at the considerably lower computational and implementation cost.

Deep belief network based statistical feature learning for fingerprint liveness detection

This work presents local discriminative feature learning for fingerprint liveness detection.Our method does not require specific knowledge regarding live or fake fingerprints.Our method does not require specific knowledge on recognition systems.Our method can be performed with relatively low computation complexity.Our method achieves good accuracy on various sensor datasets of the LivDet2013 test. Fingerprint recognition systems are vulnerable to impersonation by fake or spoof fingerprints. Fingerprint liveness detection is a step to ensure whether a scanned fingerprint is live or fake prior to a recognition step. This paper presents a fingerprint liveness detection method based on a deep belief network (DBN). A DBN with multiple layers of restricted Boltzmann machine is used to learn features from a set of live and fake fingerprints and also to detect the liveness. The proposed method is a systematic application of a deep learning technique, and does not require specific domain expertise regarding fake fingerprints or recognition systems. The proposed method provides accurate detection of the liveness with various sensor datasets collected for the international fingerprint liveness detection competition.

Resolution enhancement by prediction of the high-frequency image based on the Laplacian pyramid

According to recent advances in digital image processing techniques, interest in high-quality images has been increased. This paper presents a resolution enhancement (RE) algorithm based on the pyramid structure, in which Laplacian histogram matching is utilized for high-frequency image prediction. The conventional RE algorithms yield blurring near-edge boundaries, degrading image details. In order to overcome this drawback, we estimate an HF image that is needed for RE by utilizing the characteristics of the Laplacian images, in which the normalized histogram of the Laplacian image is fitted to the Laplacian probability density function (pdf), and the parameter of the Laplacian pdf is estimated based on the Laplacian image pyramid. Also, we employ a control function to remove overshoot artifacts in reconstructed images. Experiments with several test images show the effectiveness of the proposed algorithm.