Flower image retrieval is a very important step for computer-aided plant species recognition. In this paper, we propose an efficient segmentation method based on color clustering and domain knowledge to extract flower...Flower image retrieval is a very important step for computer-aided plant species recognition. In this paper, we propose an efficient segmentation method based on color clustering and domain knowledge to extract flower regions from flower images. For flower retrieval, we use the color histogram of a flower region to characterize the color features of flower and two shape-based features sets, Centroid-Contour Distance (CCD) and Angle Code Histogram (ACH), to characterize the shape features of a flower contour. Experimental results showed that our flower region extraction method based on color clustering and domain knowledge can produce accurate flower regions. Flower retrieval results on a database of 885 flower images collected from 14 plant species showed that our Region-of-Interest (ROI) based retrieval approach using both color and shape features can perform better than a method based on the global color histogram proposed by Swain and Ballard (1991) and a method based on domain knowledge-driven segmentation and color names proposed by Das et al.(1999).展开更多
Real-time streaming media over the Internet is an important component of multimedia applications. For the sake of quality of service (QoS), they make rigid demands on bandwidth, delay and packet loss. However, the cur...Real-time streaming media over the Internet is an important component of multimedia applications. For the sake of quality of service (QoS), they make rigid demands on bandwidth, delay and packet loss. However, the current Internet does not offer any QoS guarantees to real-time streaming media over it. How to maximize the transmission quality of real-time streaming applications in a best-effort network while friendly sharing bandwidth with non-real time applications like TCP has become an important issue. But now, many real-time streaming applications based on UDP rarely perform congestion control in a TCP-friendly manner, and they do not share the available bandwidth fairly with applications built on TCP. The Internet communication strongly fears that the current evolution could lead to congestion collapse and starvation of TCP traffic. For this reason, TCP-friendly protocols are being developed to behave fairly with respect to coexistent TCP flows. In this paper we present a new window-based congestion control method—fast fair binomial congestion control (FFBCC) for real-time applications. It provides a good performance of bandwidth distribution and TCP-friendliness for real-time streaming transmission while competing bandwidth with TCP flows.展开更多
Two problems are proposed. The first one is the noise decontamination of chaotic carriers using a deterministic approach to reconstruct pseudo trajectories, the second is the design of communications schemes with chao...Two problems are proposed. The first one is the noise decontamination of chaotic carriers using a deterministic approach to reconstruct pseudo trajectories, the second is the design of communications schemes with chaotic carriers. After presenting our deterministic noise decontamination algorithm, conventional chaos shift keying (CSK) communication system is applied. The difference of Euclidean distance between noisy trajectory and decontaminated trajectory in phase space could be utilized to non-coherently detect the sent symbol simply and effectively. It is shown that this detection method can achieve the bit error rate performance comparable to other non-coherent systems.展开更多
Many common multimedia signal processing, including cropping, filtering, and perceptual coding, make watermark signal fading-like modification. A scheme that applies transmit diversity technique to improve robustness ...Many common multimedia signal processing, including cropping, filtering, and perceptual coding, make watermark signal fading-like modification. A scheme that applies transmit diversity technique to improve robustness of digital watermarking is presented. First, the scheme decomposes the original image using wavelet pyramid algorithm and chooses the middle-frequency band for transmission channel that the watermark will be embedded into. Then the watermark is pseudo-randomly permuted. The scheme makes use of space-time coding and differential detection technique to embed and extract watermark. The extracting process has access to neither the original image nor channel state information. Experimental results demonstrate that the scheme improves the performance of robust watermarking.展开更多
A single-channel speech enhancement method of noisy speech signals at very low signal-to-noise ratios is presented, which is based on masking properties of the human auditory system and power spectral density estimati...A single-channel speech enhancement method of noisy speech signals at very low signal-to-noise ratios is presented, which is based on masking properties of the human auditory system and power spectral density estimation of non stationary noise. It allows for an automatic adaptation in time and frequency of the parametric enhancement system, and finds the best tradeoff among the amount of noise reduction, the speech distortion, and the level of musical residual noise based on a criterion correlated with perception and SNR. This leads to a significant reduction of the unnatural structure of the residual noise. The results with several noise types show that the enhanced speech is more pleasant to a human listener.展开更多
基金Project (Nos. 60302012 60202002) supported by the NationaNatural Science Foundation of China and the Research GrantCouncil of the Hong Kong Special Administrative Region (NoPolyU 5119.01E) China
文摘Flower image retrieval is a very important step for computer-aided plant species recognition. In this paper, we propose an efficient segmentation method based on color clustering and domain knowledge to extract flower regions from flower images. For flower retrieval, we use the color histogram of a flower region to characterize the color features of flower and two shape-based features sets, Centroid-Contour Distance (CCD) and Angle Code Histogram (ACH), to characterize the shape features of a flower contour. Experimental results showed that our flower region extraction method based on color clustering and domain knowledge can produce accurate flower regions. Flower retrieval results on a database of 885 flower images collected from 14 plant species showed that our Region-of-Interest (ROI) based retrieval approach using both color and shape features can perform better than a method based on the global color histogram proposed by Swain and Ballard (1991) and a method based on domain knowledge-driven segmentation and color names proposed by Das et al.(1999).
文摘Real-time streaming media over the Internet is an important component of multimedia applications. For the sake of quality of service (QoS), they make rigid demands on bandwidth, delay and packet loss. However, the current Internet does not offer any QoS guarantees to real-time streaming media over it. How to maximize the transmission quality of real-time streaming applications in a best-effort network while friendly sharing bandwidth with non-real time applications like TCP has become an important issue. But now, many real-time streaming applications based on UDP rarely perform congestion control in a TCP-friendly manner, and they do not share the available bandwidth fairly with applications built on TCP. The Internet communication strongly fears that the current evolution could lead to congestion collapse and starvation of TCP traffic. For this reason, TCP-friendly protocols are being developed to behave fairly with respect to coexistent TCP flows. In this paper we present a new window-based congestion control method—fast fair binomial congestion control (FFBCC) for real-time applications. It provides a good performance of bandwidth distribution and TCP-friendliness for real-time streaming transmission while competing bandwidth with TCP flows.
文摘Two problems are proposed. The first one is the noise decontamination of chaotic carriers using a deterministic approach to reconstruct pseudo trajectories, the second is the design of communications schemes with chaotic carriers. After presenting our deterministic noise decontamination algorithm, conventional chaos shift keying (CSK) communication system is applied. The difference of Euclidean distance between noisy trajectory and decontaminated trajectory in phase space could be utilized to non-coherently detect the sent symbol simply and effectively. It is shown that this detection method can achieve the bit error rate performance comparable to other non-coherent systems.
基金This project was supported by the National Natural Science Foundation of China(60072041).
文摘Many common multimedia signal processing, including cropping, filtering, and perceptual coding, make watermark signal fading-like modification. A scheme that applies transmit diversity technique to improve robustness of digital watermarking is presented. First, the scheme decomposes the original image using wavelet pyramid algorithm and chooses the middle-frequency band for transmission channel that the watermark will be embedded into. Then the watermark is pseudo-randomly permuted. The scheme makes use of space-time coding and differential detection technique to embed and extract watermark. The extracting process has access to neither the original image nor channel state information. Experimental results demonstrate that the scheme improves the performance of robust watermarking.
文摘A single-channel speech enhancement method of noisy speech signals at very low signal-to-noise ratios is presented, which is based on masking properties of the human auditory system and power spectral density estimation of non stationary noise. It allows for an automatic adaptation in time and frequency of the parametric enhancement system, and finds the best tradeoff among the amount of noise reduction, the speech distortion, and the level of musical residual noise based on a criterion correlated with perception and SNR. This leads to a significant reduction of the unnatural structure of the residual noise. The results with several noise types show that the enhanced speech is more pleasant to a human listener.
