Applied Mechanics and Materials Vols. 475-476

Abstract: A new detecting method for apples’ early defects which was based on the image fusion of infrared and visible images was introduced in order to distinguish and separate the fruits with mechanical damage. Using apple as the research object, the basic detecting process was expounded, and the process of image registration was introduced emphatically. An improved algorithm of image fusion, which was based on wavelet transform, was proposed. Then the experimental result was provided as well as the objective evaluation for it.

Abstract: This paper proposed a method to acquire high quality profile image based on a serious of special parameters selection and setting.And to deal with the un-matching between the speed of image grabbing and image processing,we use a special method to grab and process image in parallel based on Halcon platform. The experimental results obtained the high quality light stripe image that could increase the efficiency of measurement and simplify the image process algorithm.

Abstract: Wall rock alteration is an important indication of mineralization. On the basis of analyzing spectrum characteristic of Landsat Thematic Mapper (TM) image data, the rock ore spectrum characteristic and the theory of extracting information from remote sensing,this paper utilized Principal Component Analysis (PCA) to analyses and mapping efficiency of alteration information extracting. Study area is located in the North West periphery of Junggar Basin, China. PCA was carried out on six bands of Landsat TM data and the relevant principal components were chosen to obtain images that show alternation minerals. The results showed that PCA technique can be used as a very reliable method for enhancing the areas with alteration as a fast, effective and cheap tool for exploration of mineralization information in the northwestern Junggar basin.

Abstract: Image feature extraction and classification is increasingly important in all sectors of the images system management. Aiming at the problems that applying Hu invariant moments to extract image feature computes large and too dimensions, this paper presented Harris corner invariant moments algorithm. This algorithm only calculates corner coordinates, so can reduce the corner matching dimensions. Combined with the SVM (Support Vector Machine) classification method, we conducted a classification for a large number of images, and the result shows that using this algorithm to extract invariant moments and classifying can achieve better classification accuracy.

Abstract: Using the analysis method and the function of constructing the Smarandachely adjacent vertex distinguishing E-total coloring function, the Smarandachely adjacent vertex distinguishing E-total coloring of join graphs are mainly discussed, and the Smarandachely adjacent vertex distinguishing E-total chromatic number of join graph are obtained. The Smarandachely adjacent vertex distinguishing E-total coloring conjecture is further validated.

Abstract: Single pixel camera is a new imaging device that develops from the ghost imaging and compressive sensing theory. For high resolution remote sensing imaging with large amount of data, the process of measurement and reconstruction is time-consuming, which limits its application to remote sensing area. Based on the analysis of the configuration of the single pixel camera, an efficient imaging strategy through combining different numbers of micro mirrors was proposed. Simulation experiment was carried out for the scene consisting of a ship in the ocean. Three types of images, in low, middle and high resolution, are constructed respectively by the control of DMD working area and the strategy to combining DMD mirrors. The reconstructed images reached the application requirements at very low measurement and reconstruction time cost. The effectiveness and practicality of this strategy could be applied to other compressive sensing imaging devices.

Abstract: Deliberate imitation which is the reproduction of another speakers voice and speech behavior can pose a threat to the security of the voice authentication system. Therefore effective characteristic parameters are the key to the anti-deliberate imitation. The study chose speech database of anti-deliberate imitation and investigated some common feature parameters separating capacity and descriptive power against voice deliberate imitation. The study compared the ranking of subjective evaluation and feature parameters Euclidean distance of imitators. The comparison results indicate that Mel frequency cepstrum coefficient (MFCC) combined with its differential cepstrum parameters (WMFCC) have the best performance for anti-deliberate imitation. And the results were validated by the experiment based on VQ speaker verification system.

Abstract: By substituting an anisotropic diffusion operator for the isotropic Laplace operator in the directed diffusion equation, an improvd directed diffusion equation model is proposed. To overcome the staircasing effects and simultaneously avoid edge blurring, this paper proposed an adaptive fourth order partial differential equation from the Webers Total Variation for Image Restoration. This functional is not only to use Laplace operator but also to add the human psychology system, this paper show numerical evidence of the power of resolution of the model with respect to other known models as the Perona-Malik model. Compared results disctincly demonstrate the superiority of our proposed scheme , in terms of removing noise while sharply maintaining the edge features.

Abstract: ICP method is a powerful tool widely used in 3D point registration and pose estimation application. But there lacks an deterministic relation between the 3D point dataset and the model. Here we present some Monte Carlo simulation results for pose estimation error of one degree and the system requirement for lidar 3D point measurement techniques.

Abstract: For many applications requiring automatic positioning docking, we often use machine vision to guide automatic docking location. The key technology of automatic positioning system based on machine vision is edge detection technology of docking interface; the algorithm is the key factor to decide the success or failure of the system. In this paper, the elliptic edge detection as an example, introduces the application and experiment using Sobel edge detection algorithm in positioning aspect. The experimental results show that the method has high precision for oval edge detection, can assist machine to carry out automatic docking location, and has shorter time of image processing, it is beneficial to improve the processing speed of docking.