Search

In this paper, an approach of QR code detection using histograms of oriented gradients (HOG) and AdaBoost is proposed. There are two steps in our approach. In the first step, feature vectors are extracted using HOG with various cell sizes and overlapping or non-overlapping blocks. In the second step, the AdaBoost algorithms are trained by the input feature vectors from HOG and output targets. The QR code position is then detected via the predicted outputs from the AdaBoost algorithm. Experimental results show that the proposed method is an effective way to detect QR code position. Frankly speaking, the results reported here only provide preliminary study on QR code detection using HOG and AdaBoost.

Nowadays, touch panel is used as the interface of many portable consumer electronic products, such as smart phone, digital camera, GPS, and notebook. To ensure the quality of touch panel, it is necessary to inspect the serious defects during the production process. The manufacturing processes of the capacitive touch panel are complicated. The touch sensor is one of the most important components because it directly defines the function of touch panels. The quality of the touch sensor will greatly influence the overall quality and cost of the touch panel. Regular textures can be found on the touch sensor, and it would increase the workload of manual inspection. The automated machine vision can be applied to improve these problems if a good defect detection algorithm can be provided. This research develops an automated surface defect inspection system for capacitive touch sensor by using several image processing methods. First, Fourier transformation and a multi band-pass filter is applied to filter out regular texture. Second, based on Canny edge detection, binarization, and morphology method, the defects can be detected. 60 touch sensor images of size 640×320 are tested. The average accuracy is 96.67% and the processing time is 0.15 seconds for each image.

In this paper, a new approach is proposed for image super-resolution by combining morphological component analysis and least squares support vector machines. The proposed approach for image super-resolution consists of three steps. First, under morphological component analysis, the high resolution and low resolution images are individually decomposed into high and low frequency components, respectively. Second, the weights of two least squares support vector machines are trained by the low frequency components of the low/high resolution images and the high frequency component of low/high resolution images, respectively. Finally, the high resolution image is then reconstructed via sum of the predicted outputs from two least squares support vector machines. Experimental results show that the proposed super-resolution method performs better than the traditional bi-cubic interpolation method.

Nonparametric Wilcoxon regressors, which generalize the rank-based Wilcoxon approach for linear parametric regression problems to nonparametric neural networks, were recently developed aiming at improving robustness against outliers in nonlinear regression problems. It is natural to investigate if the Wilcoxon approach can also be generalized to nonparametric classification problems. Motivated by support vector classifiers (SVCs), we propose in this paper a novel family of classifiers, called kernel-based Wilcoxon classifiers (KWCs), for nonlinear classification problems. KWC has the same functional form as that of SVC, but with a totally different objective function. Simple weight updating rules based on gradient projection will be provided. Simulation results show that performances of KWCs and SVCs are about the same.

In traditional fractal image compression, the encoding procedure is time-consuming due to the full search mechanism. In order to speed-up the encoder, we adopt particle swarm optimization method performed under classification and Dihedral transformation to further decrease the amount of MSE computations. The classifier partitions all of the blocks in domain pool and range pool into three classes according to the third level wavelet coefficients. Each range block searches the most similar block only from the blocks of the same class. Furthermore, according to the property of Dihedral transformation, only four transformations for each domain block are considered so as to reduce the encoding time. Experimental results show that, the encoding time of the proposed method is faster than that of the full search method.

The well-known (two-parameter) sequential minimal optimization (2PSMO) algorithm for support vector classification is generalized to three-parameter sequential minimal optimization (3PSMO) algorithm in this paper. This new algorithm retains all the good properties of the former one. The main difference between these two algorithms is that the optimization is performed in each iteration of the 2PSMO algorithm on a line segment, whilst that of the 3PSMO algorithm on a region consisting of infinitely many line segments. Four public data sets are used to show the performance of both algorithms.

In this paper, an improved version of CFC algorithm is proposed. The main contribution is the reduction of a dimension in the search space. Moreover, the elements in the reduced search space are entries of control templates of uncoupled CNNs and the corresponding linearly separable Boolean functions are robust in the sense of maximal geometric margin. Illustrative examples demonstrate the efficiency of the proposed method.

A modified Rosenblatt's perceptron algorithm (1959) and Novikoff's theorem (1962) for binary classification problem is presented in this paper. For a linearly separable training set, the modified Rosenblatt's perceptron algorithm could get better convergence result. An example is provided to illustrate our main result.