Removing specular reflections from images is critical for improving the performance of computer vision algorithms. Recently, state-of-the-art methods have demonstrated remarkably good performance at removing specular reflections from chromatic images. These methods are typically based on the chromatic pixels assumption; therefore, they are prone to failure in the achromatic regions. This paper presents a novel method that is applicable to natural images, because it is effective for both chromatic and achromatic regions. The proposed method is based on modeling the general properties of diffuse and specular reflections in a solid convex optimization framework. Considering the physical constraints, we determine the global optimal solution using the split Bregman method. Experimental results demonstrate the effectiveness of the proposed method, particularly for the achromatic regions, and its competence as a state-of-the-art method for removing specular reflections from the chromatic regions.

Nearly all 3D displays need calibration for correct rendering. More often than not, the optical elements in a 3D display are misaligned from the designed parameter setting. As a result, 3D magic does not perform well as intended. The observed images tend to get distorted. In this paper, we propose a novel display calibration method to fix the situation. In our method, a pattern image is displayed on the panel and a camera takes its pictures twice at different positions. Then, based on a quantitative model, we extract all display parameters (i.e., pitch, slanted angle, gap or thickness, and offset) from the observed patterns in the captured images. For high accuracy and robustness, our method analyzes the patterns mostly in the frequency domain. We conduct two types of experiments for validation; one with optical simulation for quantitative results and the other with real-life displays for qualitative assessment. Experimental results demonstrate that our method is quite accurate, about a half order of magnitude higher than prior work; is efficient, spending less than 2s for computation; and is robust to noise, working well in the SNR regime as low as 6dB.

In the recent decades, we have witnessed the advent of local or non-local filters for cost aggregation in stereo matching, pushing the envelope of local methods to the degree of global methods, while maintaining the efficiency. A specific filter with a specific parameter setting may have a potential to best work for an image pair, but may not guarantee equally good performance for other image pairs. To address this problem, we propose a mixture-of-experts model, which applies a heterogeneous set of filters on the cost volume and adaptively combines the results. We employ supervised learning to estimate per-pixel mixing coefficients, which are used to adaptively control the weight of the filter responses. Through experiments, we show that the mixture model significantly reduces errors in disparity estimation and even outperforms the strategy of selecting the best per-pixel filter from the pool of filters in the average sense.

The theory of compressed sensing tells a dramatic story that sparse signals can be reconstructed near-perfectly from a small number of random measurements. However, recent work has found the story to be more complicated. For example, the projections based on principal component analysis work better than random projections for some images while the reverse is true for other images. Which feature of images makes such a distinction and what is the optimal set of projections for natural images? In this paper, we attempt to answer these questions with a novel formulation of compressed sensing. In particular, we find that bandwise random projections in which more projections are allocated to low spatial frequencies are near-optimal for natural images and demonstrate using experimental results that the bandwise random projections outperform other kinds of projections in image reconstruction.

For efficient image retrieval, most existing methods that adopt a tree-structured hierarchy exploit a subtree pruning scheme, based on the triangle inequality of a distance metric, during the tree traversal. In this paper, we propose a refined pruning scheme for the tree-structured hierarchy by introducing a novel notion of the node distance to subcluster (NDS) and validate it in both theoretical and experimental aspects. Experimental results demonstrate that the proposed method outperforms the existing ones by 10%-25% in terms of retrieval efficiency at the negligible increase of storage for a retrieval system

Detecting and classifying edge components in images find a wide range of applications from perceptually improved coding schemes to content-based searches. In this paper, a fast and systematic scheme is proposed to classify the edge orientation of each block in discrete cosine transform (DCT)-compressed images. Derived from a simple, but acceptable, pixel-domain algorithm, the proposed scheme performs directly on DCT coefficient domain and, thus, saves the arithmetic operations by a considerable amount. The performance of the proposed method is validated by the experiments against various natural images.

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.

Extracting a small number of key frames that can abstract the content of video is very important for efficient browsing and retrieval in video databases. In this paper, the key frame extraction problem is considered from a set-theoretic point of view, and systematic algorithms are derived to find a compact set of key frames that can represent a video segment for a given degree of fidelity. The proposed extraction algorithms can be hierarchically applied to obtain a tree-structured key frame hierarchy that is a multilevel abstract of the video. The key frame hierarchy enables an efficient content-based retrieval by using the depth-first search scheme with pruning., Intensive experiments on a variety of video sequences are presented to demonstrate the improved performance of the proposed algorithms over the existing approaches.