Tubagus Maulana Kusuma

A reduced-reference perceptual quality metric for in-service image quality assessment

User-oriented image quality assessment has become a key factor in multimedia communications. However, existing image quality metrics such as peak signal-to-noise ratio (PSNR) are inappropriate for in-service quality monitoring, since they require the original image to be available at the receiver. Although PSNR and others are objective metrics, they are not based on human visual perception. In order to overcome these problems, we propose a novel reduced-reference objective hybrid image quality metric (HIQM) that accounts for human visual perception and does not require a reference image at the receiver. This approach is based on a combination of various image artifact measures. The result is a single number, which represents an overall image quality. Experimental results indicate that HIQM outperforms PSNR.

On the development of a reduced-reference perceptual image quality metric

User-oriented image quality assessment has become a key factor in wireless multimedia communications. In particular, perceptual quality assessment methods are required to measure the overall perceived service quality based on the grading given by human subjects. This paper focuses on the development of a reduced-reference perceptual image quality metric, which can be applied for in-service quality monitoring and link adaptation purposes. In contrast to the conventional image fidelity metrics such as the peak signal-to-noise ratio (PSNR), the proposed hybrid image quality metric (HIQM) takes the human perception into account. In addition, HIQM does not rely on the availability of the full reference of the original image at the receiver.

Unequal error protection for ROI coded images over fading channels

Region of interest (ROI) coding is a feature supported by the Joint Photographic Experts Group 2000 (JPEG 2000) image compression standard and allows particular regions of interest within an image to be compressed at a higher quality than the rest of the image. In this paper, unequal error protection (UEP) is proposed for ROI coded JPEG 2000 images as a technique for providing increased resilience against the effects of transmission errors over a wireless communications channel. The hierarchical nature of an ROI coded JPEG 2000 code-stream lends itself to the use of UEP whereby the important bits of the code-stream are protected with a strong code while the less important bits are protected with a weaker code. Simulation results obtained using symbol-by-symbol maximum a posteriori probability (MAP) decoding demonstrate that the use of UEP offers significant gains in terms of the peak signal to noise ratio (PSNR) and the percentage of readable files. Moreover the use of ROI-based UEP leads to reduced computational complexity at the receiver.

Utilising objective perceptual image quality metrics for implicit link adaptation

An implicit link adaptation technique based on hybrid automatic repeat request (H-ARQ) using a soft-combining algorithm is considered for image transmission over wireless channels. Instead of the conventional link-level metrics such as bit error rate and frame error rate that do not correlate well with the quality as perceived by the end user, adaptation is carried out using metrics obtained from models that take the human perception into account. In this paper, a novel reduced-reference hybrid image quality metric (RR-HIQM) is proposed and used as a criterion to terminate the retransmission request in link adaptation. Numerical results show that the use of RR-HIQM in link adaptation provides robust link performance while meeting satisfactory quality constraints.

Classification of X-Ray Images Using Grid Approach

The process of medical image classification is still carried out manually using the knowledge of the physician or radiologist, which leads to inaccurate and slow process of object identification. Thus, we need an automatic system that can classify medical images, accurately and faster from query images into one of the pre-defined classes. In this research, we are dealing with the classification of medical image to the image classes that are defined in the database. We focus on managing the shape of X-ray image to perform the classification process and use the Euclidean distance and Jeffrey Divergence techniques to obtain image similarity.We use Freeman Code to represent the shape of X-ray images. This paper shows the development of the Freeman Code representation by simplifying the shape of X-ray image conducts to obtain the best recognition rate.

Objective Hybrid Image Quality Metric for In-Service Quality Assessment

User-oriented image quality assessment has become a key factor in multimedia communications as a means of monitoring perceptual service quality. However, existing image quality metrics such as Peak Signal-to-Noise Ratio (PSNR) are inappropriate for in-service quality monitoring since they require the original image to be available at the receiver. Although PSNR and others are objective metrics, they are not based on human visual perception and are typically designed to measure the fidelity. On the other hand, the human visual system (HVS) is more sensitive to perceptual quality than fidelity. In order to overcome these problems, we propose a novel objective reduced-reference hybrid image quality metric (RR-HIQM) that accounts for the human visual perception and does not require a reference image at the receiver. This metric is based on the combination of several image artifact measures. The result is a single number, which represents overall image quality.

Improvement of Fingerprint Sensor Reading Using FPGA Devices

In order to realize fingerprint recognition system in real time environment, we describe in this paper signal controller to read fingerprint sensor generated in FPGA devices. Basically this signal is generated using state machine. The simulation result for behavioral simulation and signal generation read by logic analyzer are presented in this paper. Initialization and reading time for 76800 pixels are 50.99 mS. It is faster than fingerprint sensor using USB connection, which is more than 250 ms.

Perceptual evaluation of motion JPEG2000 quality over wireless channels

In this paper, we investigate the applicability of perceptual image quality metrics for quality assessment of motion JPEG2000 (MJ2) video streams over wireless channels. A performance evaluation of MJ2 quality for different levels of source compression and channel coding settings is provided. This reveals insights into the characteristics and suitability of the considered perceptual quality metrics for wireless video quality assessment. In particular, a reduced-reference hybrid image quality metric (HIQM) is identified as the most favorable metric with respect to supporting real-time applications. The findings obtained from the considered scenarios may also guide the design of efficient physical layer functions for wireless video systems

Utilizing perceptual image quality metrics for link adaptation based on region of interest

An implicit link adaptation technique based on hybrid automatic repeat request (H-ARQ) and soft-combining is considered for transmission of joint photographic experts group 2000 (JPEG2000) images over wireless channels. Adaptation is carried out utilizing an objective perceptual image quality metric that takes into account the human perception. Retransmissions focus on the region of interest (ROI) part of the JPEG2000 image to efficiently utilize the bandwidth. Numerical results show that the combination of the proposed perceptual image quality metric with link adaptation provides robust link performance while meeting satisfactory quality constraints.