Abstract. Automatic pulmonary nodule detection in computed tomography (CT) images has been a challenging problem in computer aided diagnosis (CAD). Most recent recognition methods based on support vector machines (SVMs) have shown difficulty in achieving balanced sensitivity and accuracy. To improve overall performance of SVM based pulmonary nodule detection, a mixed kernel SVM method is proposed for recognizing pulmonary nodules in CT images by combining both Gaussian and polynomial kernel functions. The proposed mixed kernel SVM, together with a grid search for parameters optimization, can be tuned to seek a balance between sensitivity and accuracy so as to meet the CADs need, and eventually to improve learning and generalization ability of the SVM at the same time. In our experiments, thirteen features were extracted from the candidate regions of interest (ROIs) preprocessed from a set of real CT samples, and the mixed kernel SVM was trained to recognize the nodules in the ROIs. The results show that the proposed method takes into account both the sensitivity and accuracy compared to single kernel SVMs. The sensitivity and accuracy of the proposed method achieve 92.59% and 92% respectively.

Pulmonary nodule recognition is the core module of lung CAD. The Support Vector Machine (SVM) algorithm has been widely used in pulmonary nodule recognition, and the algorithm of Multiple Kernel Learning Support Vector Machine (MKL-SVM) has achieved good results therein. Based on grid search, however, the MKL-SVM algorithm needs long optimization time in course of parameter optimization; also its identification accuracy depends on the fineness of grid. In the paper, swarm intelligence is introduced and the Particle Swarm Optimization (PSO) is combined with MKL-SVM algorithm to be MKL-SVM-PSO algorithm so as to realize global optimization of parameters rapidly. In order to obtain the global optimal solution, different inertia weights such as constant inertia weight, linear inertia weight, and nonlinear inertia weight are applied to pulmonary nodules recognition. The experimental results show that the model training time of the proposed MKL-SVM-PSO algorithm is only 1/7 of the training time of the MKL-SVM grid search algorithm, achieving better recognition effect. Moreover, Euclidean norm of normalized error vector is proposed to measure the proximity between the average fitness curve and the optimal fitness curve after convergence. Through statistical analysis of the average of 20 times operation results with different inertial weights, it can be seen that the dynamic inertial weight is superior to the constant inertia weight in the MKL-SVM-PSO algorithm. In the dynamic inertial weight algorithm, the parameter optimization time of nonlinear inertia weight is shorter; the average fitness value after convergence is much closer to the optimal fitness value, which is better than the linear inertial weight. Besides, a better nonlinear inertial weight is verified.

The measurement of safe driving distance based on stereo vision is proposed. The model of camera imaging is established using traditional camera calibration method firstly. Secondly, the projection matrix is deduced according to camera's internal and external parameter and used to calibrate the camera. The method of camera calibration based on two-dimensional target plane is adopted. Then the distortion parameters are calculated when the nonlinear geometric model of camera imaging is built. Moreover, the camera's internal and external parameters are optimized on the basis of the projection error' least squares criterion so that the un-distortion image can be obtained. The matching is done between the left image and the right image corresponding to angular point. The parallax error and the distance between the target vehicle and the camera can be calculated. The experimental results show that the measurement scheme is an effective one in a security vehicles spacing survey. The proposed system is convenient for driver to control in time and precisely. It is able to increase the security in intelligent transportation vehicles.

In order to improve the practical application property of the two-dimensional barcode Quick Response (QR) code, we investigate the coding and decoding process of the QR code image. Run-length coding is applied to binary QR code image so as to accelerate the identification of QR code image. The QR code is transformed into many runs of data in alternate pixels of black and white. The related runs of data among adjacent rows are formed a unit module. After the whole image has been scanned, all of such modules in binary QR code image can be generated accordingly. With a noisy QR image captured by an industrial camera as an example, the experiments of image binarization, image seeking and localization adjustment are accomplished in sequence. Also the error correction algorithm is discussed in detail. A decoding system of QR code is designed and the online detection experiments are carried out. The satisfied results are achieved.

No abstract