Seong Soo Chun

Perception-based image transcoding for universal multimedia access

We propose a novel scheme for generating transcoded (e.g. scaled and cropped) image to fit the size of the respective client display when an image is transmitted to a variety of client devices with different display sizes. The scheme has two key components: (i) perceptual hint for each image block, and (ii) an image transcoding algorithm. For a given semantically important block in an image, the perceptual hint provides the information on the minimum allowable spatial resolution reduction. The image transcoding algorithm that is basically a content adaptation process selects the best image representation to meet the client capabilities while delivering the largest content value. The content value is defined as a quantitative measure of the information on importance and spatial resolution for the transcoded version of an image. Experimental results demonstrate the feasibility of the proposed scheme with a variety of client devices having different display sizes.

An efficient method for text detection in video based on stroke width similarity

Text appearing in video provides semantic knowledge and significant information for video indexing and retrieval system. This paper proposes an effective method for text detection in video based on the similarity in stroke width of text (which is defined as the distance between two edges of a stroke). From the observation that text regions can be characterized by a dominant fixed stroke width, edge detection with local adaptive thresholds is first devised to keep text- while reducing background-regions. Second, morphological dilation operator with adaptive structuring element size determined by stroke width value is exploited to roughly localize text regions. Finally, to reduce false alarm and refine text location, a new multi-frame refinement method is applied. Experimental results show that the proposed method is not only robust to different levels of background complexity, but also effective to different fonts (size, color) and languages of text.

Intra prediction mode selection for flicker reduction in H.264/AVC

The H.264/AVC adopted an intra prediction scheme that enables high coding efficiency for intra-coded frames. However, the intra prediction scheme of H.264/AVC may cause flicker in intra-coded frames if the intra prediction modes are not appropriately selected for coding. In this paper, we propose an intra prediction mode selection method for H.264/AVC by using a modified distortion measure for rate distortion optimized mode selection that does not only consider the distortion between the input and the reconstructed macroblocks, but also the between-frame consistency of distortion between two successive frames to reduce flicker in intra-coded frames. Experimental results demonstrate that our proposed method reduces significant amount of flicker with a negligible change in PSNR and bitrate

Flicker Reduction in Intra Coded Frames of H.264/AVC

The H.264/AVC video coding standard adopted a new intra prediction technique that enables high coding efficiency for intra coded frames. However, it is known to produce more flickers in intra coded frames when the modes are selected based on conventional rate distortion optimized mode decision methods. In this paper, we propose to use a modified distortion measure for rate distortion optimized mode decision to reduce flicker in intra coded frames of H.264/AVC. Experimental results show that our proposed method can reduce significant amount of flicker maintaining similar PSNR and bitrate.

Efficient intra prediction mode decision for h.264 video

In this paper, we propose an efficient 4×4 intra prediction mode decision method for the complexity reduction of H.264 video coding. Based on the observation that a good prediction could be achieved when local edge direction of a block is in the same direction as the intra prediction mode, local edge direction of block is obtained in transform domain to filter out majority of intra prediction modes. By filtering out majority of intra prediction modes, we only have to consider a candidate set of most highly probable 4×4 intra prediction modes for which the rate distortion optimization process should be performed. Experimental results show that the proposed method can achieve a considerable reduction of computation while maintaining similar PSNR and bit rate.

Real-Time Video Indexing System for Live Digital Broadcast TV Programs

In this paper, we introduce a real-time metadata service system that is implemented for live digital broadcast TV programs. The system is composed of three parts: an indexing host which indexes broadcast programs in real-time, a broadcaster where the segmentation metadata delivered from the indexing host is multiplexed into the broadcast stream and transferred to clients, and a client PVR that receives the metadata and locates a segment of interest from the recorded stream according to the time description of the delivered metadata. We propose to utilize broadcasting time for a time description of the segmentation metadata, so as to be free from the media localization problems in broadcast environment. In addition, we utilize a spatiotemporal visual pattern of a video for a verification tool of real-time indexing, such that we can reduce the false alarms of video segmentation caused by lack of an efficient tool for verifying video segment. As a result, we show the real experiments that are performed without requiring a return channel and demonstrate the feasibility of the proposed system.

Fast Text Caption Localization on Video Using Visual Rhythm

In this paper, a fast DCT-based algorithm is proposed to efficiently locate text captions embedded on specific areas in a video sequence through visual rhythm, which can be fast constructed by sampling certain portions of a DC image sequence and temporally accumulating the samples along time. Our proposed approach is based on the observations that the text captions carrying important information suitable for indexing often appear on specific areas on video frames, from where sampling strategies are derived for a visual rhythm. Our method then uses a combination of contrast and temporal coherence information on the visual rhythm to detect text frames such that each detected text frame represents consecutive frames containing identical text strings, thus significantly reducing the amount of text frames needed to be examined for text localization from a video sequence. It then utilizes several important properties of text caption to locate the text caption from the detected frames.

Efficient image down-conversion for mixed field/frame-mode macroblocks

An efficient image resizing algorithm in the compressed domain with mixed field/frame-mode macroblocks is proposed. A 16/spl times/16 field/frame-mode macroblock is converted into an 8/spl times/8 reduced block in the discrete cosine transform (DCT) domain using a modified inverse DCT (IDGT) kernel which performs stronger lowpass filtering than the simple truncation in the DCT domain. Experimental results show that the proposed algorithm provides the resized image quality similar to an existing method with significantly lower computational complexity.

Scalable Hierarchical Summarization of News Using Fidelity in MPEG-7 Description Scheme

The notion of fidelity is an attribute in MPEG-7 FDIS (Final Draft International Standard [1]) that can be used for scalable hierarchical summarization and search [2]. The fidelity is the information on how well a parent key frame represents its child key frames in a tree-structured key frame hierarchy [1- 5]. The use of fidelity was demonstrated for scalable hierarchical summarization [2] based on the low-level features such as color, but the temporal information was not used. Content of a video such as news and golf is temporally well structured and it is desirable to utilize such information. In this paper, we demonstrate the use of fidelity for the summarization of a well-structured news by using temporal information as well as low-level features.