Young-Su Moon

Ghost-free high dynamic range imaging

Most high dynamic range image (HDRI) algorithms assume stationary scene for registering multiple images which are taken under different exposure settings. In practice, however, there can be some global or local movements between images caused by either camera or object motions. This situation usually causes ghost artifacts which make the same object appear multiple times in the resultant HDRI. To solve this problem, most conventional algorithms conduct ghost detection procedures followed by ghost region filling with the estimated radiance values. However, usually these methods largely depend on the accuracy of the ghost detection results, and thus often suffer from color artifacts around the ghost regions. In this paper, we propose a new robust ghost-free HDRI generation algorithm that does not require accurate ghost detection and not suffer from the color artifact problem. To deal with the ghost problem, our algorithm utilizes the global intensity transfer functions obtained from joint probability density functions (pdfs) between different exposure images. Then, to estimate reliable radiance values, we employ a generalized weighted filtering technique using the global intensity transfer functions. Experimental results show that our method produces the state-of-the-art performance in generating ghost-free HDR images.

Text segmentation based on stroke filter

Most existing methods of text segmentation in video images are not robust because they do not consider the intrinsic characteristics of text. In this paper, we propose a novel method of text segmentation based on stroke filter (SF). First, we give the definition of text, which is realized in the form of stroke filter based on local region analysis. Based on stroke filter response, text polarity determination and local region growing modules are performed successively. The effectiveness of our method is validated by experiments on a challenging database.

Seamless and Fast Panoramic Image Stitching

In this paper, a novel panoramic imaging method is presented which can compensate tone differences between images precisely by estimating ghost pixels in the overlap area. The method compensates the overlapped images bilaterally, then it prevents a panoramic image from getting darker or lighter as images are stitched. Therefore, the proposed method allows the overall panorama to keep the proper mid-tone, offering a high-speed panorama system with only software implementation in spite of its outstanding performance. Experimental results show that the proposed method can correct 95% serious corner cases taking less time than existing methods.

A simple ghost-free exposure fusion for embedded HDR imaging

We propose a simple ghost-free exposure fusion algorithm in which three (over-, mid-, under-) exposures are input for fast embedded HDR imaging. Previous methods in this area require a complicated post-processing, such as morphological operations and large size kernel operations. To remove ghost artifacts successfully even with a low computing power, first of all an over-exposure input is set as a reference image, and non-ghostness probability is applied to acquire a ghost-free fusion weight. Through some experimental analysis, we show that such a reference image setting scheme makes it possible to skip the heavily time consuming post-processing.

A fast low-light multi-image fusion with online image restoration

This paper presents a new low-light multi-frame fusion algorithm to get a bright and clear shot even under dark conditions. To this end, using multiple short-exposure images and one proper-exposure blurry image as an input, a new hierarchical block-wise temporal noise filtering is done. Finally, an online image restoration of the denoising result is conducted along with the blurry image input. Test results on real low-light scene show its effectiveness like fast processing speed and satisfactory visual quality.

A cross-channel bilateral filter for CFA image denoising

High ISO image which is captured at low light environment has serious sensor noise. To avoid this problem, we propose a novel denoising framework for CFA image. We create cross-channel correlation map and explore method to denoise with the map to distinguish the noise from signal. And we propose the modified bilateral filter algorithm with the map. Experimental result show that proposed method has a good balance between denoising noise and edge preservation in high ISO image.

Tone correction with dynamic objects for seamless image mosaic

This paper presents a tone compensation method between images to make a seamless panoramic image. Different camera settings of input images, including white-balance, exposure time, and f-stops, affect the overall color tone of a resultant panoramic image. Although numerous methods have been proposed to deal with such color variations for seamless image stitching, most of them do not properly consider the dynamic scene in which different scene contents exist in input images. In this paper, we propose an efficient method that takes dynamic scene contents into account for compensating color tone difference. The proposed approach consists of three steps. First, we compensate the color tone difference by using the linear color transform with robust local features. Second, we filter out dynamic objects (i.e., dynamic scene contents) by measuring similarity between the linear transformed image and the reference image. Finally, we precisely correct the color variation with detected consistent regions only. The qualitative evaluation shows superior or competitive results compared to commercially available products.

A survey on applications of high dynamic range technologies in consumer electronic devices

High dynamic range (HDR) technology is one of various research topics in computer vision technologies, which has been actively being applied to cutting-edge consumer electronics products such as premium UHDTV, premium smart phones and etc. In case of consumer camera devices or mobile camera phones, HDR scene capture mode is commonly provided by combining differently-exposed images with standard dynamic range (SDR). In consumer premium TVs, there exist two kinds of HDR processing technologies: one is a tone mapping (TM) to render HDR content on SDR display, and the other one is an inverse tone mapping (iTM) to render a SDR content on HDR display. Especially, in the case of HDR ton mapping, some metadata for adjusting radiometric difference between a reference mastering display and various consumer TV displays were standardized as well as HDR signal encoding method. Currently there exist various organizations related to HDR standards: UHD-Alliance, SMPTE, CTA, ITU-R, MPEG, DVB and etc. Those HDR standard ecosystem members include movie studio, broadcasting, OTTs, TV/STB manufacturers, and etc. They have made efforts to create a next big opportunity of brand-new HDR technology on the basis of 4K UHD media. We will here review HDR technologies, standards, delivery system, and its CE industry trends.

A ghost-free pseudo-multiframe HDR

This paper presents a ghosts-free pseudo-multiframe (MF) high dynamic range (HDR) algorithm inputting real on-site multiple exposures. To this end, first a set of synthetic exposures are generated by mapping a reference exposure with onlinemodeled brightness transfer functions (BTFs), which are determined through histogram matching from the reference exposure to other exposures. Such a set of synthetic exposures allows conventional image alignment and ghost removal procedures for the MF HDR to be unnecessary. Particularly, the proposed method can provide more realistic color appearance and details even at low light situations. Test results on various real scenes show the effectiveness of the proposed approach.

A fast spatiotemporal denoising scheme for multi-shot images

In this paper, we propose a new fast spatiotemporal denoising scheme. The noise removal is achieved hierarchically in a multi-resolution framework which is combined with image registration and temporal bilateral filtering. The proposed scheme generates satisfactory results without ghost-artifact and it requires much lower computational complexity compared with other methods.