{"title":"Depth Estimation from Defocus Images Based on Oriented Heat-Flows","authors":"L. Hong, Jia Yu, Cheng Hong, Wei Sui","doi":"10.1109/ICMV.2009.32","DOIUrl":"https://doi.org/10.1109/ICMV.2009.32","url":null,"abstract":"The amount of blur on the defocus image depends on the depth information of the scene. So depth of the scene can be estimated by calculating the blur with the knowledge of the lens parameters. A novel depth estimation mode based on oriented heat-flows is proposed in this paper. In this model, the process of image defocusing is described using oriented heat-flows diffusion. The diffusion can be seen as the coupling of two weighted heat flows along orthonormal directions. The diffusion directions are defined by the local coherence geometry of image and the diffusion strength is the function of blur amount. Experimental results show that the model is quite effective and the emergence of artificial depth information in edge can be avoided by using this model.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"12 31","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131437591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Neural Based Approach for Fast Retrieval of Symbolic Images in Database","authors":"Mojtaba Sabet, Mohamad Firouzmand, S. Ayat","doi":"10.1109/ICMV.2009.57","DOIUrl":"https://doi.org/10.1109/ICMV.2009.57","url":null,"abstract":"The rapid growth of image databases results in new requirement for fast image indexing and retrieval. In this paper we use Correlation Matrix Memory (CMM) as data structure for fast image storage and retrieval. We use Triangular Spatial Relation (TSR) to represent spatial relations among image iconic objects. The proposed model is faster than other existing models in both partial and exact match retrieval (Ω(1)).","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131209031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Solitons Interaction and their Stability Based on Nonlinear Schrödinger Equation","authors":"A. Shahzad, M. Zafrullah","doi":"10.1109/ICMV.2009.38","DOIUrl":"https://doi.org/10.1109/ICMV.2009.38","url":null,"abstract":"Optical solitons are considered as natural bits for telecommunications as they have the tendency to maintain their shape over transoceanic distances because of interaction between nonlinearity and anomalous group velocity dispersion. However, depending upon the individual pulse width, inter-pulse spacing and loss in the fiber, co-propagating solitons do interact and share energy. It is therefore imperative to investigate the soliton pulse interaction before implementing them in a high speed optical communication system. Incorporating the mathematical model based on the Nonlinear Schrödinger (NLS) equation and using the split-step Fourier transform method; we have conducted various simulation experiments to investigate the interaction between adjacent pulses of equal amplitude, in-phase solitons copropagating in dispersion shifted fibers. The simulation results show that, solitons after traveling a certain distance get attracted and evolve as a giant pulse of double the amplitude of the individual pulse and if propagated further, simply get separated as if they have walked through each other. The simulation results reveal that, a careful choice of the pulse and fiber parameters can be helpful in avoiding the soliton interaction which limits the channel capacity","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123277937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Human Gait Recognition Based on Dynamic and Static Features Using Generalized Regression Neural Network","authors":"Luv Rustagi, Lokendra Kumar, G. Pillai","doi":"10.1109/ICMV.2009.70","DOIUrl":"https://doi.org/10.1109/ICMV.2009.70","url":null,"abstract":"Biometric Recognition using the behavioral modality of gait is an emerging research area. This paper describes a method for human gait recognition using Generalized Regression Neural Networks. The feature space is composed of a combination of dynamic (time-varying) gait signals and static body-shape parameters, extracted from binary silhouettes obtained after background subtraction from human gait sequences. The inputs to the neural network are obtained by performing Discrete Cosine Transform (DCT) on the feature space, followed by selection of transformed coefficients to construct compact vectors.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130307090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Content-Based Medical Image Retrieval Using the Generic Fourier Descriptor with Brightness","authors":"Ashok Vijay, M. Bhattacharya","doi":"10.1109/ICMV.2009.42","DOIUrl":"https://doi.org/10.1109/ICMV.2009.42","url":null,"abstract":"Content based medical image retrieval (CBMIR) is been highly active research area from past few years . We describes a efficient approach and algorithm that capable of extracting the key information from the medical images based on there shape. We use the Generic Fourier Descriptor (GFD) with Brightness as additional parameter to have good retrieval accuracy. Image is represented in polar form and 2-D Fourier transform is applied on them to get GFD. The acquired descriptor is application independent and robust. Experimental results show the GFD with brightness have better performance over the other contour-based descriptor","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126222026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Application of Digital Imaging Technique in Electrical Charge Tomography System for Image Reconstruction Validation","authors":"M. Isa, M. F. Rahmat","doi":"10.1109/ICMV.2009.35","DOIUrl":"https://doi.org/10.1109/ICMV.2009.35","url":null,"abstract":"Image reconstruction in electrical charge tomography is vital and has not been widely studied. There are three methods introduced before namely linear back projection, filter back projection and least square methods. These normally face with ill-posed problem and its solution is unstable and inaccuracy. In this paper, the new image reconstruction method has been introduced to reconstruct the image cross-section of material in gravity mode conveyor pipeline. Numerical analysis result indicated that this algorithm is efficient to overcome the numerical instability. Instead of image reconstruction process, validation the accuracy of the image is very important. It would be parts of verify process to the new image reconstruction method. In this system, digital imaging technique is used to interrogate the flow in pipeline around sensing area using CCD camera. The result between image reconstruction by new method and image captured by CCD camera will be compared.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131893207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hadi Rezaei, M. Shakeri, S. Azadi, Keyvan Jaferzade
{"title":"Multimodality Image Registration Utilizing Ant Colony Algorithm","authors":"Hadi Rezaei, M. Shakeri, S. Azadi, Keyvan Jaferzade","doi":"10.1109/ICMV.2009.21","DOIUrl":"https://doi.org/10.1109/ICMV.2009.21","url":null,"abstract":"Image Registration is the determination of a geometrical transformation that aligns points in one image of an object with corresponding points in another image. To find the best transformation function we should optimize the similarity measure. The optimization methods are generally divided into two general classes of Global and Local methods. The problem with local methods is that they trap in local optima. So, in this paper we use Ant Colony Algorithm as a global optimization method which is based on real ant behavior. The results of our experiments show the effectiveness and better accuracy for this method rather than local methods.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131395276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mina Behravan, R. Boostani, F. Tajeripour, Z. Azimifar
{"title":"A Hybrid Scheme for Online Detection and Classification of Textural Fabric Defects","authors":"Mina Behravan, R. Boostani, F. Tajeripour, Z. Azimifar","doi":"10.1109/ICMV.2009.53","DOIUrl":"https://doi.org/10.1109/ICMV.2009.53","url":null,"abstract":"Online automatic fabric defect detection and classification of the localized defect types are two vital stages in production line of textile manufactures. Here a hybrid approach is proposed for online detection of defects through serial fabric images and then classifying the localized defect types. First, defects are detected and localized by using a modified local binary pattern (LBP) operator and second, to characterize the defective regions, textons are utilized. Different classes of fabric defects locally cause different types of texture and therefore the classification of defects can be formulated as a texture classification problem. In the state-of-the-art texture analysis approaches a texture is characterized through textons describing local properties of textures. For the first time, in this paper the approach is used for classification of fabric defects. The employed dataset in this study is provided by fabric laboratory of University of Hong Kong. Images in the dot-patterned fabric database contain six types of well-known defects. Experimental results have yielded excellent results such that classification accuracy of detected defect types is determined 100%. The low computational complexity and high robustness of the proposed scheme confirm the usefulness of this approach for online fabric inspection.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"316 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115444860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dual Watermarking in Video Using Discrete Wavelet Transform","authors":"S. Gandhe, Ujwala Potdar, K. Talele","doi":"10.1109/ICMV.2009.22","DOIUrl":"https://doi.org/10.1109/ICMV.2009.22","url":null,"abstract":"The proposed system in this paper gives the invisible watermarking which is performed by using Discrete Wavelet Transform. To get the invisible watermarking the alternate pixel value of the host video is replaced by the pixel value of watermark video/image. This type of watermarking provides a means of forensic analysis for combating media piracy. Video watermarking provides robustness to geometric attack such as rotation, cropping, contract altercation, time editing without compromising the security of the watermark.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123638475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ming Li, Limin Wang, Yang Liu, Ying Liu, Qian Sun, Xuming Han
{"title":"An Improved OIF Elman Neural Network Model with Direction Profit Factor and Its Applications","authors":"Ming Li, Limin Wang, Yang Liu, Ying Liu, Qian Sun, Xuming Han","doi":"10.1109/ICMV.2009.39","DOIUrl":"https://doi.org/10.1109/ICMV.2009.39","url":null,"abstract":"Output-input feedback (OIF) Elman neural network is a dynamic feedback network. An improved model is proposed based on the OIF Elman neural network by introducing direction profit factor in this paper. Moreover, the proposed model is applied to forecast the composite index of stock. In addition, some comparisons are also made when the stock exchange is performed using prediction results from OIF Elman neural network. Simulation results show that the proposed model is feasible and effective in the finance field. It shows that the proposed model can not only improve the forecasting precision evidently and possess the characteristic of quick convergence but also provide a good reference tool for investors to obtain more profits.","PeriodicalId":315778,"journal":{"name":"2009 Second International Conference on Machine Vision","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127176071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}