Ching-Yu Yang

Robust real-time ship detection and tracking for visual surveillance of cage aquaculture

Abstract This paper presents a visual surveillance scheme for cage aquaculture that automatically detects and tracks ships (intruders). For ship detection and tracking, we propose a robust foreground detection and background updating to effectively reduce the influence of sea waves. Furthermore, we propose a fast 4-connected component labeling method to greatly reduce the computational cost associated with the conventional method. Wave ripples are removed from regions with ships. An improved full search algorithm based on adaptive template block matching with a wave ripple removal is presented to quickly, accurately, and reliably track overlapping ships whose scales change. Experimental results demonstrate that the proposed schemes have outstanding performance in ship detection and tracking. The proposed visual surveillance system for cage aquaculture triggers an alarm if intruders are detected. The security of cage aquaculture can be increased. The proposed visual surveillance can thus greatly help the popularization of cage aquaculture for ocean farming.

Effective image forgery detection of tampered foreground or background image based on image watermarking and alpha mattes

This paper proposes an effective image forgery detection scheme that identifies a tampered foreground or background image using image watermarking and alpha mattes. In the proposed method, component-hue-difference-based spectral matting is used to obtain the foreground and background images based on the obtained alpha matte. Next, image watermarking based on the discrete wavelet transform, discrete cosine transform, and singular value decomposition is used to embed two different watermarks into the foreground and background images, respectively. Finally, the difference between the obtained singular values is used to detect tampering of foreground or background image. Experimental results show that the proposed method performs well in terms of image forgery detection.

Authentication and protection for medical image

This paper proposes a method to authenticate and protect medical images, especially in the region of interest (ROI). The ROI of a medical image is an important area during diagnosis and must not be distorted during transmission and storage in the hospital information system. The rest of the ROI is used for embedding a watermark that contains the patients data and authentication information, and the authentication information is generated from the ROI by analyzing wavelet coefficients with singular value decomposition (SVD), before embedding the watermark into the discrete wavelet transform (DWT) sub-band. It is important that the ratio of ROI and non-ROI areas is consistent between different systems and doctors, and this ratio is analyzed in this paper. The ROI of watermarked medical image is fragile to any distortion, and patients data and authentication information can be easily extracted from non-ROI. The effectiveness of the new approach is demonstrated empirically.

High-Performance Digital Watermarking with L2-Norm Centroid for Colour Images

In this paper, we present a high-capacity watermarking scheme for color images by using the idea of L2-Norm centroid. Based on spatial domain, the proposed scheme can effectively embed a secret watermark in a host image. Simulations demonstrate that the marked images generated by the proposed watermarking scheme are tolerant of versatile attacks such as color reduction, compression, cropping, blurring, noise addition, and pixel-truncation. In addition, the payload provided by our method is larger than that provided by existing techniques.

Automatic and accurate image matting

This paper presents a modified spectral matting to obtain automatic and accurate image matting. Spectral matting is the state-of-the-art image matting and also a milestone in theoretic matting research. However, using spectral matting without user guides, the accuracy is usually low. The proposed modified spectral matting effectively raises the accuracy. In the proposed modified spectral matting, the palette-based component classification is proposed to obtain the reliable foreground and background components. In contrast to the spectral matting, based on these reliable foreground and background components, the accuracy of obtained alpha matte is greatly increased. Experimental results show that the proposed method has better performance than the spectral matting. Therefore, the proposed image matting is very suitable for image and video editing.

Robust high-capacity watermarking scheme based on Euclidean norms and quick coefficient alignment

This paper proposes simple but robust digital watermarking for color images based on Euclidean norms and quick coefficient alignment. For increasing the amount of hidden storage, we embedded two data bits in a host block at a time using a quick adjustment technique and four criteria that follow Euclidean norms of pixels. Simulations confirmed that a large number of secret bits can be embedded in host images without compromising image quality. In addition, our method is free from the underflow/overflow issue. The hidden storage provided by the proposed method is larger than that provided by existing color image watermarking techniques. The watermarked images generated by the proposed method are robust against various types of attacks such as cropping, Gaussian/uniform noise addition, inversion, JPEG, JPEG2000, and zigzagging.

High-capacity Robust Watermarking Approach for Protecting Ownership Right

In this work, we proposed a high-capacity robust watermarking scheme for color images. Based on integer wavelet domain (IWT), the proposed scheme utilized the idea of computing the offset of two square-root-values, a number of data bits can be embedded in a host image. Simulations indicated that our method did provide a large hiding-storage while the perceived quality is good. Further, the proposed method is tolerant of various attacks such as brightness, cropping, edge sharpening, blurring, ip horizontal, inversion, and rotation. Additionally, the payload for the proposed method is larger than that for existing techniques. abstract environment.

Analysis of Movement Effectiveness in Badminton Strokes with Accelerometers

The paper focuses on the relevance of three-axis accelerometers and the badminton swing movement coordination and stability. Some of the studies used recording devices or optical instrument to analyze the player’s actions, this method is limited by the venue, as well as photography dead, privacy issues, cost, complexity is high. In this paper, the method can effectively solve these problems. The methods uses less computing complexity, achieve effective analysis badminton swing action. After obtaining the three-axis acceleration value, use low pass filtering process for the noise. The characteristic values of different parts of the swing use neural networks to classify the action into error and correct operation provides different feedback for user. We analyzed the data of badminton clear. In the future, we will analysis other strokes in badminton.

High-Payload Digital Watermarking Using Radius-Weighted Mean Based on IWT Domain

Based on integer wavelet transform (IWT), the author uses the idea of radius-weighted mean (RWM) and present a high-capacity color image watermarking scheme. More specifically, the Euclidean distance of RWM and centroid is used as the embedding criterion, a watermark is hidden in the low-low (LL) subbnad of IWT domain. To further promote payload size, the criterion of Euclidean norm of RWM is employed in the low-high (LH) and high-low (HL) subbnads of IWT domain. Simulations confirm that the marked images generated by the proposed method are robust against manipulations such as JPEG, JPEG2000, color quantization, cropping, (edge) sharpening, noise additions, blurring, and inversion. In addition, the resultant perceived quality is good while our peak signal-to-noise ratio outperforms existing techniques.

Novel Detection of Image Forgery for Exchanged Foreground and Background Using Image Watermarking Based on Alpha Matte

This paper proposes an novel method to detect image forgery for exchanged foreground and background by using image watermarking based on alpha matte. in the proposed method, the DWT-DCT-SVD-based image watermarking is used and applied on the alpha mattes obtained using image matting algorithms. the difference of singular values is used to determine the exchanged foreground or exchanged background. Experimental results show that the proposed method can obtain accurate detection of image forgery for exchanged foreground or background. Therefore, the proposed method is a high-value tool of the image forgery detection.