Chiou-Ting Hsu

Hidden signatures in images

An image authentication technique by embedding each image with a signature so as to discourage unauthorized copying is proposed. The proposed technique could actually survive several kinds of image processing and the JPEG lossy compression.

Video forgery detection using correlation of noise residue

We propose a new approach for locating forged regions in a video using correlation of noise residue. In our method, block-level correlation values of noise residual are extracted as a feature for classification. We model the distribution of correlation of temporal noise residue in a forged video as a Gaussian mixture model (GMM). We propose a two-step scheme to estimate the model parameters. Consequently, a Bayesian classifier is used to find the optimal threshold value based on the estimated parameters. Two video inpainting schemes are used to simulate two different types of forgery processes for performance evaluation. Simulation results show that our method achieves promising accuracy in video forgery detection.

Detecting Recompression of JPEG Images via Periodicity Analysis of Compression Artifacts for Tampering Detection

Due to the popularity of JPEG as an image compression standard, the ability to detect tampering in JPEG images has become increasingly important. Tampering of compressed images often involves recompression and tends to erase traces of tampering found in uncompressed images. In this paper, we present a new technique to discover traces caused by recompression. We assume all source images are in JPEG format and propose to formulate the periodic characteristics of JPEG images both in spatial and transform domains. Using theoretical analysis, we design a robust detection approach which is able to detect either block-aligned or misaligned recompression. Experimental results demonstrate the validity and effectiveness of the proposed approach, and also show it outperforms existing methods.

A Generalized Low-Rank Appearance Model for Spatio-temporally Correlated Rain Streaks

In this paper, we propose a novel low-rank appearance model for removing rain streaks. Different from previous work, our method needs neither rain pixel detection nor time-consuming dictionary learning stage. Instead, as rain streaks usually reveal similar and repeated patterns on imaging scene, we propose and generalize a low-rank model from matrix to tensor structure in order to capture the spatio-temporally correlated rain streaks. With the appearance model, we thus remove rain streaks from image/video (and also other high-order image structure) in a unified way. Our experimental results demonstrate competitive (or even better) visual quality and efficient run-time in comparison with state of the art.

Image Retrieval With Relevance Feedback Based on Graph-Theoretic Region Correspondence Estimation

This paper presents a graph-theoretic approach for region-based image retrieval. When dealing with image matching problem, we propose converting the region correspondence estimation into an attributed graph matching problem and measuring the image similarity in terms of both the region correspondence and the low-level features. In addition, during the relevance feedback, we propose using a maximum likelihood method to re-estimate region features and region importance while retaining its inherent spatial organization. Experimental results show that the proposed graph-theoretic matching criterion outperforms other existing methods which include no spatial information in the matching criterion. The experiments also show that the performance can be further improved with our proposed relevance feedback scheme.

Single-Image Dehazing via Optimal Transmission Map Under Scene Priors

The challenge of single-image dehazing mainly comes from double uncertainty of scene radiance and scene transmission. Most existing methods focus on restoring the visibility of hazy images and tend to derive a rough estimate of scene transmission. Unlike previous work, in this paper we advocate the significance of accurate transmission estimation and recast our problem as deriving the optimal transmission map directly from the haze model under two scene priors. We introduce theoretic and heuristic bounds of scene transmission to guide the optimum and show that the proposed theoretic bound happens to justify the well-known dark channel prior of haze-free images. With the constraints on the solution space, we then incorporate two scene priors, including locally consistent scene radiance and context-aware scene transmission, to formulate a constrained minimization problem and solve it by quadratic programming. The global optimality is guaranteed. Simulations on synthetic data set quantitatively verify the accuracy and show that the transmission map successfully captures fine-grained depth boundaries. Experimental results on color/gray-level images demonstrate that our method outperforms most state of the arts in terms of both accurate transmission maps and realistic haze-free images.

Relevance feedback using generalized Bayesian framework with region-based optimization learning

This paper presents a generalized Bayesian framework for relevance feedback in content-based image retrieval. The proposed feedback technique is based on the Bayesian learning method and incorporates a time-varying user model into the formulation. We define the user model with two terms: a target query and a user conception. The target query is aimed to learn the common features from relevant images so as to specify the users ideal query. The user conception is aimed to learn a parameter set to determine the time-varying matching criterion. Therefore, at each feedback step, the learning process updates not only the target distribution, but also the target query and the matching criterion. In addition, another objective of this paper is to conduct the relevance feedback on images represented in region level. We formulate the matching criterion using a weighting scheme and proposed a region clustering technique to determine the region correspondence between relevant images. With the proposed region clustering technique, we derive a representation in region level to characterize the target query. Experiments demonstrate that the proposed method combined with time-varying user model indeed achieves satisfactory results and our proposed region-based techniques further improve the retrieval accuracy.

Multiresolution mosaic

Mosaic techniques have been used to combine two or more signals into a new one with an invisible seam, and with as little distortion of each signal as possible. Multiresolution representation is an effective method for analyzing the information content of signals, and it also fits a wide spectrum of visual signal processing and visual communication applications. The wavelet transform is one kind of multiresolution representation, and has found a wide variety of application in many aspects, including signal analysis, image coding, image processing, computer vision and etc. Due to its characteristic of multiresolution signal decomposition, the wavelet transform is used in this paper to do the image mosaic by choosing the width of mosaic transition zone proportional to the frequency represented in the band. Both 1-D and 2-D signal mosaics are described, and some factors which affect the mosaics are discussed.

Online Selection of Tracking Features Using AdaBoost

This paper presents an online feature selection algorithm for video object tracking. Using the object and background pixels from the previous frame as training samples, we model the feature selection problem as finding a good subset of features to better classify object from background in current frame. This paper aims to improve existing methods by taking correlation between features into consideration. We propose to use AdaBoost algorithm to iteratively select one feature which best compensates the previously selected features. Using the selected features, we then construct a compound likelihood image, which shows the ability to discriminate better than the original frame, as the input for the tracking process. We also propose to use ellipse fitting to eliminate mislabeled pixels from our training process. In addition, we propose an online feature validity test to monitor the selected features and only re-select features when the previously selected features become out-of-date. Experimental results demonstrate that the proposed algorithm combined with mean-shift based tracking algorithm achieves very promising results.

Motion trajectory based video indexing and retrieval

This paper presents a technique to efficiently index and retrieve video clips in terms of motion-trajectory-based similarity. We describe the motion trajectory in three representations: the horizontal and vertical movements of the trajectory, and the motion trail that indicates shape of the trajectory. Each representation is approximated by a polynomial function. We index the polynomial coefficients and combine different spatio-temporal characteristics to provide flexible retrieval processes. A unified framework is also proposed to deal with various query types: query-by-example, query-by-sketch, and query-by-specification.