The embedded hidden Markov model (HMM) is a statistical model that can be used in many pattern recognition and computer vision applications. This model inherits the partial size invariance of the standard HMM, and, du...
详细信息
ISBN:
(纸本)0780362977
The embedded hidden Markov model (HMM) is a statistical model that can be used in many pattern recognition and computer vision applications. This model inherits the partial size invariance of the standard HMM, and, due to its pseudo two-dimensional structure, is able to model two-dimensional data such as images, better than the standard HMM. We describe the maximum likelihood training for the continuous mixture embedded HMM and present the performance of this model for face detection and recognition. The experimental results are compared with other approaches to face detection and recognition.
An iterative technique for detecting linear features in 2D images based on the Radon transform is developed. The algorithm is suitable for processing ground penetrating radar (GPR) and seismic images to find undergrou...
详细信息
An iterative technique for detecting linear features in 2D images based on the Radon transform is developed. The algorithm is suitable for processing ground penetrating radar (GPR) and seismic images to find underground pipes and tunnels. Detection is performed in the Radon transform space. The length and width of the linear object area are estimated and the corresponding portion of the image is removed at each iteration. The algorithm has the advantage of detecting very weak linear objects, which are barely detected by existing detection algorithms, in Radon transform space. The proposed algorithm is tested on both simulated and experimental data measured from a laboratory scale model area. Results show successful detection of strong and weak linear objects
The increasing amount of music being stored in digital formats calls for increasingly more creative methods for music information retrieval. One subset of music retrieval methods relies on storing a melody in a pitch ...
详细信息
The increasing amount of music being stored in digital formats calls for increasingly more creative methods for music information retrieval. One subset of music retrieval methods relies on storing a melody in a pitch contour representation. Most often, this contour information is generated either from symbolic format (MIDI) or from raw audio after a pitch transcription step. We propose a method of extracting pitch contour information from musical audio without an intermediate transcription step by combining a musically-tuned constant Q transform with crosscorrelation. When tested on a database of 520 monophonic music recordings, our method generates pitch contours from raw audio data with up to 98% accuracy.
Faculty members from Georgia Tech's school of electrical and computerengineering (ECE) have worked jointly with engineers from National Instruments to develop a new freshman course. This course, entitled 'Int...
详细信息
ISBN:
(纸本)9781424436767
Faculty members from Georgia Tech's school of electrical and computerengineering (ECE) have worked jointly with engineers from National Instruments to develop a new freshman course. This course, entitled 'Introduction to ECE Design,' is constructed around the LEGO Mindstorms NXT robotics kit. This course addresses the diverse objectives of providing students with a systems-level design experience at the *** of their academic programs and introducing them to a broad range of ECE disciplines. A primary goal is to enable students to make better-informed decisions when choosing whether or not to major in electricalengineering or computerengineering.
In this paper, we consider the problem of detecting and locating buried land mines and subsurface objects by using seismic waves. We demonstrate an adaptive seismic system that maneuvers an array of receivers, accordi...
详细信息
In this paper, we consider the problem of detecting and locating buried land mines and subsurface objects by using seismic waves. We demonstrate an adaptive seismic system that maneuvers an array of receivers, according to an optimal positioning algorithm based on the theory of optimal experiments, to minimize the number of distinct measurements to localize the mine. The adaptive localization algorithm is tested using numerical model data as well as laboratory measurements performed in a facility at Georgia Tech. It is envisioned that the future systems should be able to incorporate this new method into portable mobile mine-location systems
The paper describes a low rate feedback algorithm for conveying partial channel state information - specifically, the dominant row subspace of the channel matrix - from the receiver to the transmitter in a continuousl...
详细信息
The paper describes a low rate feedback algorithm for conveying partial channel state information - specifically, the dominant row subspace of the channel matrix - from the receiver to the transmitter in a continuously time-varying multiple-antenna environment. Since subspaces are points on a complex Grassmann manifold, variations in subspaces are treated as a piecewise geodesic process on the manifold. The receiver feeds back one bit to indicate the preferred sign of a random velocity matrix of the geodesic. Numerical results show that the performance of the proposed algorithm is better than the Grassmannian subspace packing approach at low-to-medium Doppler frequency and always better than the previously proposed gradient sign feedback scheme.
In this paper, a speech signal estimation framework involving Kalman filters for use as a front-end to the Aurora-2 speech recognition task is presented. Kalman-filter based speech estimation algorithms assume autoreg...
详细信息
In this paper, a speech signal estimation framework involving Kalman filters for use as a front-end to the Aurora-2 speech recognition task is presented. Kalman-filter based speech estimation algorithms assume autoregressive (AR) models for the speech and the noise signals. In this paper, the parameters of the AR models are estimated using a expectation-maximization approach. The key to the success of the proposed algorithm is the constraint on the AR model parameters corresponding to the speech signal to belong to a codebook trained on AR parameters obtained from clean speech signals. Aurora-2 noise-robust speech recognition experiments are performed to demonstrate the success of the codebook-constrained Kalman filter in improving speech recognition accuracy in noisy environments. Results with both clean and multi-conditional training are provided to show the improvements in the recognition accuracy compared to the base-line system where no pre-processing is employed
This paper presents a new hardware efficient distributed arithmetic (DA) architecture for high order (> 1024) digital filters. The new architecture is termed reusable distributed arithmetic (RDA). The proposed arch...
详细信息
This paper presents a new hardware efficient distributed arithmetic (DA) architecture for high order (> 1024) digital filters. The new architecture is termed reusable distributed arithmetic (RDA). The proposed architecture has a linear dependence of memory size on filter length versus the exponential dependence found in lookup table (LUT)-based designs by removing the LUT and generating the required combinations online. In addition, the proposed RDA architecture reuses the computation blocks much like the way multipliers are reused in multiplier-based architectures to reduce hardware complexity. The proposed RDA design is compared against a multiplier-based (MM) design to illustrate the area dependency of both designs on filter length. FPGA synthesis results confirm that the RDA design is capable of much higher order filters (2048 tap) than the MM design (512 tap) while at the same time having similar equivalent gate counts and throughput.
The work presented in this paper describes a hidden Markov model (HMM)-based framework for face recognition and face detection. The observation vectors used to characterize the states of the HMM are obtained using the...
详细信息
The work presented in this paper describes a hidden Markov model (HMM)-based framework for face recognition and face detection. The observation vectors used to characterize the states of the HMM are obtained using the coefficients of the Karhunen-Loeve transform (KLT). The face recognition method presented reduces significantly the computational complexity of previous HMM-based face recognition systems, while slightly improving the recognition rate. Consistent with the HMM model of the face, this paper introduces a novel HMM-based face detection approach using the same feature extraction techniques used for face recognition.
We propose a blind multiuser detector based on Monte Carlo Markov chain (MCMC) techniques. The detector exploits mutually orthogonal complementary sequences to distinguish between transmitting users and space-time cod...
详细信息
We propose a blind multiuser detector based on Monte Carlo Markov chain (MCMC) techniques. The detector exploits mutually orthogonal complementary sequences to distinguish between transmitting users and space-time codes to take advantage of the available spatial diversity. We propose a partitioning scheme for the symbol draws in the MCMC algorithm that reduces the complexity without any degradation in performance. The detector's performance is simulated in an iterative receiver that utilizes an outer coder. The simulations display some loss in coding gain because of the blind nature of the system; however, diversity gain is preserved.
暂无评论