Jiheon Ok

Towards standardized 3DTV QoE assessment: cross-lab study on display technology and viewing environment parameters

Subjective assessment of Quality of Experience in stereoscopic 3D requires new guidelines for the environmental setup as existing standards such as ITU-R BT.500 may no longer be appropriate. A first step is to perform cross-lab experiments in different viewing conditions on the same video sequences. Three international labs performed Absolute Category Rating studies on a freely available video database containing degradations that are mainly related to video quality degradations. Different conditions have been used in the labs: Passive polarized displays, active shutter displays, differences in viewing distance, the number of parallel viewers, and the voting device. Implicit variations were introduced due to the three different languages in Sweden, South Korea, and France. Although the obtained Mean Opinion Scores are comparable, slight differences occur in function of the video degradations and the viewing distance. An analysis on the statistical differences obtained between the MOS of the video sequences revealed that obtaining an equivalent number of differences may require more observers in some viewing conditions. It was also seen that the alignment of the meaning of the attributes used in Absolute Category Rating in different languages may be beneficial. Statistical analysis was performed showing influence of the viewing distance on votes and MOS results.

HDR tone mapping algorithm based on difference compression with adaptive reference values

A new local tone mapping method using adaptive reference is proposed.The detailness metric is proposed to measure detail loss in bright and dark regions.An objective quality assessment is developed to optimize parameters.The proposed method shows a good balance between detailness and naturalness. Tone mapping remains a challenging problem since tone mapping operators need to produce high perceptual quality under all conditions. In this paper, we propose a new local tone mapping method based on difference compression with adaptive reference values, which can effectively reproduce the details of bright and shadow regions. We also use a global tone mapping method and blend the output images produced by the global and local methods based on objective quality metrics. To quantitatively measure output images, we developed a new objective quality metric for the tone mapped images. The proposed detailness metric measures detail loss in the bright and shadow regions, and shows good correlations with subjective quality. We combined this metric with the recently proposed tone mapped image quality index (TMQI) that may not sufficiently reflect the amount of local detail loss. The experiments show that the proposed algorithm provides better perceptual quality than existing methods.

Paper check image quality enhancement with Moire reduction

Paper checks may have complex background features including fine lines and patterns, which make forgery more difficult. Also, halftoning techniques are used to produce continuous tones and to prevent copies with void pantograph features. When these kinds of checks are scanned, Moire patterns may occur. These patterns make it difficult for customers to examine the scanned check images on ATM (Automated Teller Machine) displays. They also can decrease the classification accuracy of check recognition systems. In this paper, we propose an algorithm to enhance the perceptual quality of scanned check images by reducing the Moire patterns. The proposed algorithm consists of foreground extraction, Moire detection and Moire removal. Subjective image quality assessment was performed to evaluate the degree of improvement. Experimental results show that the proposed algorithm improves perceptual quality while maintaining check recognition accuracy.

Shadow Removal for Background Subtraction Using Illumination Invariant Measures

In this paper, we propose methods for shadow removal in static background environment. Accurate background subtraction is essential to detect and track various objects. Shadow and objects similar in color are major problems in background subtraction and tracking. In order to address these problems, we propose shadow removal method for background subtraction using illumination invariant measures. First, we computed a reference background image and the illumination invariant measures were applied to the reference background image and an input image. We compared the proposed method with some existing background subtraction methods. The experimental results showed that the proposed method produced more accurate results.

Fast Country Classification of Banknotes

In this paper, we present a fast algorithm for country classification of banknotes. The algorithm can be used as an initial step for conventional banknote classification methods developed for a single currency in multi-country environment. We assume that the input image is a Contact Image Sensor (CIS) scan image with de-skewing and Region of Interest (ROI) extraction. In the training process, after size normalization we extract eigenimage for a banknote group based on overall context similarity. With the dominant eigenimage of each banknote group, we compute correlation metrics between the dominant eigenimage and test images. We tested the algorithm with four currencies: USD, KRW, CNY and EUR. The proposed method shows 100% accuracy and it took about 0.37ms for a banknote.

Low complexity pixel-based halftone detection

With the rapid advances of the internet and other multimedia technologies, the digital document market has been growing steadily. Since most digital images use halftone technologies, quality degradation occurs when one tries to scan and reprint them. Therefore, it is necessary to extract the halftone areas to produce high quality printing. In this paper, we propose a low complexity pixel-based halftone detection algorithm. For each pixel, we considered a surrounding block. If the block contained any flat background regions, text, thin lines, or continuous or non-homogeneous regions, the pixel was classified as a non-halftone pixel. After excluding those non-halftone pixels, the remaining pixels were considered to be halftone pixels. Finally, documents were classified as pictures or photo documents by calculating the halftone pixel ratio. The proposed algorithm proved to be memory-efficient and required low computation costs. The proposed algorithm was easily implemented using GPU.

Objective perceptual quality assesment and depth perception of 3D media

In this paper, we investigate the applicability of existing objective perceptual video quality measurement methods, which were developed for 2D video, to measure the perceptual quality of 3D video programs. We tested two methods: a reduced-reference HDTV model (ITU-T Rec. J.342) and a hybrid NR method (ITU-T Rec. J.343). As more mobile devices support autostereoscopic displays, crosstalk emerges as an important issue. We also investigate the effects of crosstalk on depth perception. Experimental results show promising performance and it appears that 2D video quality measurement methods can be used for 3D contents with potential improvements by taking into account 3D characteristics.

Remote logo detection using angle-distance histograms

Among all the various computer vision applications, automatic logo recognition has drawn great interest from industry as well as various academic institutions. In this paper, we propose an angle-distance map, which we used to develop a robust logo detection algorithm. The proposed angle-distance histogram is invariant against scale and rotation. The proposed method first used shape information and color characteristics to find the candidate regions and then applied the angle-distance histogram. Experiments show that the proposed method detected logos of various sizes and orientations.

Vertical resolution loss and perceptual 3D video quality

Most currently available 3DTV displays use either shutter glasses or polarized glasses. Each display type has distinct advantages and disadvantages. 3D display monitors with polarized glasses provide a comfortable viewing experience, but can suffer from vertical resolution loss. On the other hand, since 3D UHD display monitors are now widely available, it is possible to offer full HD 3D programs without any vertical resolution loss by using UHD 3D display monitors with polarized glasses. In this paper, we performed several subjective tests to compare the perceptual 3D video quality obtained with HD and UHD monitors in order to investigate the impact of vertical resolution loss on perceptual 3D video quality.

Communication target object recognition for D2D connection with feature size limit

Recently, a new concept of device-to-device (D2D) communication, which is called “point-and-link communication” has attracted great attentions due to its intuitive and simple operation. This approach enables user to communicate with target devices without any pre-identification information such as SSIDs, MAC addresses by selecting the target image displayed on the user’s own device. In this paper, we present an efficient object matching algorithm that can be applied to look(point)-and-link communications for mobile services. Due to the limited channel bandwidth and low computational power of mobile terminals, the matching algorithm should satisfy low-complexity, low-memory and realtime requirements. To meet these requirements, we propose fast and robust feature extraction by considering the descriptor size and processing time. The proposed algorithm utilizes a HSV color histogram, SIFT (Scale Invariant Feature Transform) features and object aspect ratios. To reduce the descriptor size under 300 bytes, a limited number of SIFT key points were chosen as feature points and histograms were binarized while maintaining required performance. Experimental results show the robustness and the efficiency of the proposed algorithm.