Wangmeng Zuo

An assembled matrix distance metric for 2DPCA-based image recognition

Two-dimensional principal component analysis (2DPCA) is a novel image representation approach recently developed for image recognition. One characteristic of 2DPCA is that it can extract feature matrix using a straightforward image projection technique. In this paper, we propose an assembled matrix distance metric (AMD) to measure the distance between two feature matrices. To test the efficiency of the proposed distance measure, we use two image databases, the ORL face database and the PolyU palmprint database. The results of our experiments show that the assembled matrix distance metric is very effective in 2DPCA-based image recognition.

An additive convolution model for fast restoration of nonuniform blurred images

Nonuniform blurring would be introduced during imaging by many inevitable factors, such as defocus, camera shake, or motion. Fast restoration of nonuniform blurred images, however, remains a challenging problem. The sparse blur matrix-based approach models nonuniform blurring as the multiplication of a high-dimensional sparse blur matrix and an image vector, and suffers from the high computational and memory complexity problems. To tackle these, we propose an additive convolution model (ACM) which models nonuniform blurring as the space variant weighted sum of the convolution images of a set of basis filters. We further propose a principal component analysis-based method to learn the basis filters and weight matrices. Finally, we incorporate ACM with the total variation-based restoration model, and adopt the generalized accelerated proximal gradient algorithm for the restoration of nonuniform blurred images. Numerical results show that the proposed method is effective for the restoration of nonuniform blurred images caused by defocus or camera shake, and is superior to the sparse matrix-based approach in terms of computational and memory complexity.

Optimized Preprocessing Framework for Wrist Pulse Analysis

Since wrist pulse signals collected by the sensors are often corrupted by artifacts in real situations, many approaches on the wrist pulse preprocessing including pulse denoising and baseline drift removal are introduced for more accurate wrist pulse analysis. However, these scattered methods are incomplete with some limitations when used to preprocess our special pulse data for the clinical applications. This chapter presents a robust signal preprocessing framework for wrist pulse analysis. The cascade filter based on frequency-dependent analysis (FDA) is first introduced to remove the high-frequency noises and to select the significant intervals. Then the curve fitting method is developed to adjust the direction and the baseline drift with minimum signal distortion. Last, the period segmentation and normalization is applied for the feature extraction. The effectiveness of the proposed framework is validated through experiments on actual pulse records with biochemical markers. Both quantitative and qualitative results are given. The results show that the proposed pulse preprocessing framework is effective in extracting more accurate pulse features and practical for wrist pulse analysis.

Computational Pulse Signal Analysis

Quantifying pulse diagnosis is to acquire and record pulse waveforms by a set of sensor firstly and then analyze these pulse waveforms. However, respiration and artifact motion during pulse waveform acquisition can introduce baseline drift. It is necessary, therefore, to remove the pulse waveform’s baseline drift in order to perform accurate pulse waveform analysis. This chapter presents a wavelet-based cascaded adaptive filter (CAF) to remove the baseline drift of pulse waveform. To evaluate the level of baseline drift, we introduce a criterion: energy ratio (ER) of pulse waveform to its baseline drift. If the ER is more than a given threshold, the baseline drift can be removed only by cubic spline estimation; otherwise it must be filtered by, in sequence, discrete Meyer wavelet filter and the cubic spline estimation. Compared with traditional methods such as cubic spline estimation, morphology filter, and linear-phase finite impulse response (FIR) least-squares-error digital filter, the experimental results on 50 simulated and 500 real pulse signals demonstrate the power of CAF filter both in removing baseline drift and in preserving the diagnostic information of pulse waveforms. This CAF also can be used to remove the baseline drift of other physiological signals, such as ECG and so on.

Pulse Signal Acquisition Using Multi-sensors

In this chapter, we integrate a pressure sensor with a photoelectric sensor to make a fusion sensor which can acquire the pulse from different approaches. We designed the multichannel sensor arrays structure and introduced the pulse analysis algorithm and classification methods. Experiments on disease classification are carried out to test the system performance with multichannel and different sensor arrays. The results show that the novel system is not only able to distinguish between healthy pulse samples and subjects suffering from diabetes but also good at obtaining more information than the conventional pulse system with single channel or simplex-type sensor.