Chi-Man Pun

University of Macau, Macao, Macau, Macao

Are you Chi-Man Pun?

Claim your profile

Publications (103)69.33 Total impact

  • Guoheng Huang · Chi-Man Pun
  • Chi-Man Pun · Xiao-Chen Yuan · Xiu-Li Bi
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel copy–move forgery detection scheme using adaptive oversegmentation and feature point matching is proposed in this paper. The proposed scheme integrates both block-based and keypoint-based forgery detection methods. First, the proposed adaptive oversegmentation algorithm segments the host image into nonoverlapping and irregular blocks adaptively. Then, the feature points are extracted from each block as block features, and the block features are matched with one another to locate the labeled feature points; this procedure can approximately indicate the suspected forgery regions. To detect the forgery regions more accurately, we propose the forgery region extraction algorithm, which replaces the feature points with small superpixels as feature blocks and then merges the neighboring blocks that have similar local color features into the feature blocks to generate the merged regions. Finally, it applies the morphological operation to the merged regions to generate the detected forgery regions. The experimental results indicate that the proposed copy–move forgery detection scheme can achieve much better detection results even under various challenging conditions compared with the existing state-of-the-art copy–move forgery detection methods.
    IEEE Transactions on Information Forensics and Security 08/2015; 10(8):1-1. DOI:10.1109/TIFS.2015.2423261 · 2.41 Impact Factor
  • Ka-Cheng Choi · Chi-Man Pun
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a robust lossless digital watermarking scheme based on a generalized integer transform in spatial domain is proposed. In the proposed method, data bits are hidden into the cover media by a reversible generalized integer transform with bit plane manipulation. With the reversible transform, data can be hidden in the cover media, and the stego media can be restored to its original form after extraction of the hidden data. In embedding procedure, adaptive bit plane manipulation is applied to increase robustness of the algorithm while keeps good visual quality. To further increase the robustness of the algorithm, we repeatedly embed watermark bits and use majority voting to decode the hidden information in extraction procedure. Furthermore, a threshold is introduced in the algorithm, which helps in choosing regions that would result lower variance for embedding, as regions with lower variance is more robust against JPEG compression. The proposed scheme is quite different from the existing robust lossless data hiding algorithms which are histogram-based. The performance of the proposed scheme is evaluated and compared with state-of-the-arts techniques respect to robustness, data payload capacity and peak signal-to-noise ratio (PSNR). In the experiments, the proposed method can embed more than 10000 bits into 512 by 512 grayscale and medical images, and has around 30 dB in PSNR. In case of small watermark with 100 bits, marked images can have PSNR above 60 dB and with 0.1 bpp in JPEG robustness in the best cases. Conclusively, the robustness of the proposed method is quite good, and the results of hiding capacity and imperceptibility are also satisfactory.
    Multimedia Tools and Applications 04/2015; DOI:10.1007/s11042-015-2596-3 · 1.35 Impact Factor
  • Xiao-Chen Yuan · Chi-Man Pun · C. L. Philip Chen
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel digital audio watermarking scheme based on robust Mel-Frequency Cepstral coefficients feature detection and dual-tree complex wavelet transform is proposed in this paper, which is similar as patchwork based methods that several segments are extracted from the host audio clip for watermarking use. The robust Mel-Frequency Cepstral coefficients feature detection method is proposed to extract the feature segments which should be relocated when the host audio signal attacked by various distortions including both the common audio signal processing and the conventional geometric distortions. With the robust feature segments, the approximate shift invariant transform dual-tree complex wavelet transform based watermarking method is proposed to embed the watermark into the DT CWT real low-pass coefficients of each segment, using the spread spectrum techniques. The linear correlation is calculated to judge the existence of the watermark during the watermark detection. Experimental results show that the proposed digital audio watermarking scheme based on robust Mel-Frequency Cepstral coefficients feature detection and dual-tree complex wavelet transform can achieve high robustness against the common audio signal processing, such as low-pass filtering, MP3 compression, echo addition, volume change, and normalization; and geometric distortions, such as resample Time-Scale Modification (TSM), pitch invariant TSM, and tempo invariant pitch shifting. In addition, the proposed audio watermarking scheme is resilient to Stir-mark for Audio, and it performs much better comparing with the existing state-of-the art methods.
    Information Sciences 03/2015; 298. DOI:10.1016/j.ins.2014.11.040 · 4.04 Impact Factor
  • Guoheng Huang · Chi-Man Pun · Cong Lin · Yicong Zhou
    [Show abstract] [Hide abstract]
    ABSTRACT: A novel non-rigid object tracking based on interactive user-define marker and superpixel Gaussian kernel is proposed in this paper. In the initialization stage, instead of using the traditional bounding box to locate the targeted object, we have employed an interactive segmentation with user-defined marker to segment the object accurately in the first frame of the input video to avoid the background influence in the traditional bounding box. During the tracking stage, by using a Gaussian kernel as movement constraint, each superpixel is tracked independently to locate the object in the next frame. Experimental results show that the proposed method compared to state of the art methods can achieve better robustness and accuracy for various challenging video clips.
    Multimedia Tools and Applications 02/2015; DOI:10.1007/s11042-015-2516-6 · 1.35 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Because of the excellent properties of unpredictability, ergodicity and sensitivity to their parameters and initial values, chaotic maps are widely used in security applications. In this paper, we introduce a new two-dimensional Sine Logistic modulation map (2D-SLMM) which is derived from the Logistic and Sine maps. Compared with existing chaotic maps, it has the wider chaotic range, better ergodicity, hyperchaotic property and relatively low implementation cost. To investigate its applications, we propose a chaotic magic transform (CMT) to efficiently change the image pixel positions. Combining 2D-SLMM with CMT, we further introduce a new image encryption algorithm. Simulation results and security analysis demonstrate that the proposed algorithm is able to protect images with low time complexity and a high security level as well as to resist various attacks.
    Information Sciences 11/2014; 297. DOI:10.1016/j.ins.2014.11.018 · 4.04 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Chaotic maps are widely used in different applications. Motivated by the cascade structure in electronic circuits, this paper introduces a general chaotic framework called the cascade chaotic system (CCS). Using two 1-D chaotic maps as seed maps, CCS is able to generate a huge number of new chaotic maps. Examples and evaluations show the CCS's robustness. Compared with corresponding seed maps, newly generated chaotic maps are more unpredictable and have better chaotic performance, more parameters, and complex chaotic properties. To investigate applications of CCS, we introduce a pseudo-random number generator (PRNG) and a data encryption system using a chaotic map generated by CCS. Simulation and analysis demonstrate that the proposed PRNG has high quality of randomness and that the data encryption system is able to protect different types of data with a high-security level.
    Cybernetics, IEEE Transactions on 10/2014; 99(9). DOI:10.1109/TCYB.2014.2363168 · 3.47 Impact Factor
  • Xiao-Chen Yuan · Chi-Man Pun
    [Show abstract] [Hide abstract]
    ABSTRACT: A robust and geometric invariant digital image watermarking scheme based on robust feature detector and local Zernike transform is proposed in this paper. The robust feature extraction method is proposed based on the Scale Invariant Feature Transform (SIFT) algorithm, to extract circular regions/patches for watermarking use. Then a local Zernike moments-based watermarking scheme is raised, where the watermarked regions/patches can be obtained directly by inverse Zernike Transform. Each extracted circular patch is decomposed into a collection of binary patches and Zernike transform is applied to the appointed binary patches. Magnitudes of the local Zernike moments are calculated and modified to embed the watermarks. Experimental results show that the proposed watermarking scheme is very robust against geometric distortion such as rotation, scaling, cropping, and affine transformation; and common signal processing such as JPEG compression, median filtering, and low-pass Gaussian filtering.
    Multimedia Tools and Applications 09/2014; 72(1). DOI:10.1007/s11042-013-1405-0 · 1.35 Impact Factor
  • Source
    Haipeng Dai · Wei Feng · Liang Wan · Xuecheng Nie · Chi-Man Pun
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we focus on co-intrinsic decomposition, a new problem that performs intrinsic decomposition on a pair of images simultaneously, which share the same foreground with arbitrarily different illuminations and backgrounds. We specifically demand the common foreground across different images to share same reflectance values. For the purpose of efficiency and feasibility, we perform the co-intrinsic decomposition at superpixel-level and propose a uniform approach to automatically derive non-local reflectance relationships vi- a unsupervised L0 sparsity between superpixels from intra- and inter-images. We present a unicolor-light-based intrinsic model, from which we construct a non-local L0 sparse co-Retinex model that imposes feasible constraints on shad- ing, reflectance and environment light, respectively. The co- intrinsic decomposition is finally modeled as a quadratic minimization problem that leads to a fast closed form solution. Extensive experiments show plausible results of our approach in extracting common reflectance components from multiple images. We also validate the benefits of our results in boost- ing the accuracy of image co-saliency detection.
    IEEE International Conference on Multimedia and Expo; 07/2014
  • Source
    Shijie Zhang · Wei Feng · Jiawan Zhang · Chi-Man Pun
    [Show abstract] [Hide abstract]
    ABSTRACT: As the increasing popularity of superpixel-based applications, measuring superpixel-level similarity becomes an important and commonly required problem. In this paper, we propose a general bag of squares (BoS) model for such particular purpose. Compared to existing methods, our approach provides a full scheme to both invariantly represent superpixels and accurately measure their pairwise similarities. In order to handle the split-and-merge variety of superpixels of same objects in different scenes, our model is based on superpixel pyramid. As a result, the BoS model of a superpixel is built upon a group of subregions consisting of the superpixel itself and its children subregions in the pyramid. For each subregion, we extract a proper number of maximum squares via distance transform, and then use a fast self-validated approach to clustering them into a small number of dominant squares, which together with a rotation and scale invariant square descriptor, jointly compose the BoS model for the particular superpixel. Finally, we measure the similarity between a pair of superpixels by the closeness of their BoS models. Experiments on interactive object segmentation and co-saliency detection show that the proposed BoS model can reliably capture the delicate differences among superpixels, thus always producing better segmentation results, especially for segmenting highly variant objects in clutter scenes.
    IEEE International Conference on Multimedia and Expo; 07/2014
  • Source
    Xuecheng Nie · Wei Feng · Liang Wan · Haipeng Dai · Chi-Man Pun
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a hierarchical approach based on non-local $l_0$ sparsity for intrinsic image decomposition. Different from the previous studies which use heuristic ways to make the ill-posed problem well-defined, our approach can effectively construct sparse and non-local pairwise correlations in an unsupervised manner. Moreover, our approach is less dependent on chromaticity feature. Homogenous pairwise smoothness prior and scalability prior is added in our model to improve the decomposition accuracy. We formulate the decomposition problem as the minimization of a quadratic function, which can be solved in closed form with the standard conjugate gradient algorithm. Experimental results show that our approach can successfully extract the shading component and reflectance component from a single image, and outperform state-of-the-art techniques on the benchmark MIT dataset both in accuracy and perception. Besides, our approach can achieve comparable results with user-assisted approach on natural scenes.
    IEEE International Conference on Multimedia & Expo; 07/2014
  • Ning-Yu An · Chi-Man Pun
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a new hybrid color image segmentation approach, which attempts two different transforms for texture representation and extraction. The 2-D discrete wavelet transform that can express the variance in frequency and direction of textures, and the contourlet transform that represents boundaries even more accurately are applied in our algorithm. The whole segmentation algorithm contains three stages. First, an adaptive color quantization scheme is utilized to obtain a coarse image representation. Then, the tiny regions are combined based on color information. Third, the proposed energy transform function is used as a criterion for image segmentation. The motivation of the proposed method is to obtain the complete and significant objects in the image. Ultimately, according to our experiments on the Berkeley segmentation database, our techniques have more reasonable and robust results than other two widely adopted image segmentation algorithms, and our method with contourlet transform has better performance than wavelet transform.
    Signal Image and Video Processing 07/2014; 8(5). DOI:10.1007/s11760-012-0340-2 · 1.43 Impact Factor
  • Source
    Hong-Min Zhu · Chi-Man Pun
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose an adaptive and robust superpixel based hand gesture tracking system, in which hand gestures drawn in free air are recognized from their motion trajectories. First we employed the motion detection of superpixels and unsupervised image segmentation to detect the moving target hand using the first few frames of the input video sequence. Then the hand appearance model is constructed from its surrounding superpixels. By incorporating the failure recovery and template matching in the tracking process, the target hand is tracked by an adaptive superpixel based tracking algorithm, where the problem of hand deformation, view-dependent appearance invariance, fast motion, and background confusion can be well handled to extract the correct hand motion trajectory. Finally, the hand gesture is recognized by the extracted motion trajectory with a trained SVM classifier. Experimental results show that our proposed system can achieve better performance compared to the existing state-of-the-art methods with the recognition accuracy 99.17% for easy set and 98.57 for hard set.
    05/2014; 2014:1-12. DOI:10.1155/2014/849069
  • Source
    Bo Liu · Chi-Man Pun · Xiao-Chen Yuan
    [Show abstract] [Hide abstract]
    ABSTRACT: Wide availability of image processing software makes counterfeiting become an easy and low-cost way to distort or conceal facts. Driven by great needs for valid forensic technique, many methods have been proposed to expose such forgeries. In this paper, we proposed an integrated algorithm which was able to detect two commonly used fraud practices: copy-move and splicing forgery in digital picture. To achieve this target, a special descriptor for each block was created combining the feature from JPEG block artificial grid with that from noise estimation. And forehand image quality assessment procedure reconciled these different features by setting proper weights. Experimental results showed that, compared to existing algorithms, our proposed method is effective on detecting both copy-move and splicing forgery regardless of JPEG compression ratio of the input image.
    03/2014; 2014:230425. DOI:10.1155/2014/230425
  • Miao Cheng · Chi-Man Pun · Yuan Yan Tang
    [Show abstract] [Hide abstract]
    ABSTRACT: Nonnegative learning aims to learn the part-based representation of nonnegative data and receives much attention in recent years. Nonnegative matrix factorization has been popular to make nonnegative learning applicable, which can also be explained as an optimization problem with bound constraints. In order to exploit the informative components hidden in nonnegative patterns, a novel nonnegative learning method, termed nonnegative class-specific entropy component analysis, is developed in this work. Distinguish from the existing methods, the proposed method aims to conduct the general objective functions, and the conjugate gradient technique is applied to enhance the iterative optimization. In view of the development, a general nonnegative learning framework is presented to deal with the nonnegative optimization problem with general objective costs. Owing to the general objective costs and the nonnegative bound constraints, the diseased nonnegative learning problem usually occurs. To address this limitation, a modified line search criterion is proposed, which prevents the null trap with insured conditions while keeping the feasible step descendent. In addition, the numerical stopping rule is employed to achieve optimized efficiency, instead of the popular gradient-based one. Experiments on face recognition with varieties of conditions reveal that the proposed method possesses better performance over other methods.
    Formal Pattern Analysis & Applications 02/2014; 17(1). DOI:10.1007/s10044-011-0258-2 · 0.65 Impact Factor
  • Cong Lin · Chi-Man Pun
    02/2014; 4(1):68-72. DOI:10.7763/IJMLC.2014.V4.388
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper introduces a novel parameter-control framework to produce many new one-dimensional (1D) chaotic maps. It has a simple structure and consists of two 1D chaotic maps, in which one is used as a seed map while the other acts as a control map that controls the parameter of the seed map. Examples and analysis results show that these newly generated chaotic maps have more complex structures and better chaos performance than their corresponding seed and control maps.
    Proceedings of SPIE - The International Society for Optical Engineering 01/2014; 9030. DOI:10.1117/12.2049055 · 0.20 Impact Factor
  • Shuang Yi · Yicong Zhou · Chi-Man Pun · C. L. Philip Chen
    [Show abstract] [Hide abstract]
    ABSTRACT: Existing collage steganographic methods suffer from low payload of embedding messages. To improve the payload while providing a high level of security protection to messages, this paper introduces a new collage steganographic algorithm using cartoon design. It embeds messages into the least significant bits (LSBs) of color cartoon objects, applies different permutations to each object, and adds objects to a cartoon cover image to obtain the stego image. Computer simulations and comparisons demonstrate that the proposed algorithm shows significantly higher capacity of embedding messages compared with existing collage steganographic methods.
    Proceedings of SPIE - The International Society for Optical Engineering 01/2014; 9030. DOI:10.1117/12.2049056 · 0.20 Impact Factor
  • Source
    Dawei Liu · Moon-Chuen Lee · Chi-Man Pun · Hongli Liu
  • Chi-Man Pun · Xiao-Chen Yuan
    [Show abstract] [Hide abstract]
    ABSTRACT: A geometrically invariant digital image watermarking scheme based on histogram modification is proposed in this paper. The feature extraction method called Adaptive Harris Detector with Simulated Attacks is proposed and employed, which adjusts and ranks the response threshold value of the traditional Harris Corner Detector, and trains the input image with several simulated attacks, to extract the most reliable feature points for watermark data bits embedding and extraction. The watermark embedding regions are then found as square patches centering at the selected geometric invariant feature points. In each region, the intensity-level histogram is modified by moving some pixels to form a specific pattern according to the corresponding watermark bit. For watermark extraction, the proposed Adaptive Harris Detector with Simulated Attacks is proposed to restore the watermarked image to its original position if any geometric attack exists, and to retrieve the watermarked regions. According to the pattern of intensity-level histogram distribution in these regions, a sequence of watermark bits is then extracted. Experimental results show that the proposed scheme is robust against both the geometric attacks and common signal processing, such as rotation, scaling, cropping, JPEG compression, median filtering, low-pass Gaussian filtering and also noise pollution.
    Multimedia Tools and Applications 01/2014; 74(18). DOI:10.1007/s11042-014-2025-z · 1.35 Impact Factor

Publication Stats

431 Citations
69.33 Total Impact Points


  • 2002–2015
    • University of Macau
      • • Department of Computer Science and Information Science
      • • Faculty of Science and Technology
      Macao, Macau, Macao
  • 2013
    • City University of Macau
      Macao, Macau, Macao
  • 2000
    • The Chinese University of Hong Kong
      • Department of Computer Science and Engineering
      Hong Kong, Hong Kong