Papers by Keyword: Texture Extraction

Abstract: As known, there always exist severely degradation problems in digital radiography. How we can extract necessary textures from degraded radiographic images is the post-processing key. Local binary pattern (LBP) is a well-known method, which is widely used in fast image texture extraction. However, for noisy images, LBP can’t work well due to its sensitivity to details. On the other hand, as one of the important shock filters developed in recent years, complex shock filter possesses excellent capabilities in textural image processing. Here, by combining complex shock filter with LBP, a novel fast and efficient method, C-LBP is presented for texture extraction of degraded radiographic images. Experimental results show that comparing with traditional LBP, C-LBP not only distinguishes between noise and details in radiographic images, but also extracts image textures efficiently and rapidly, which plays an important role in developing nondestructive detection technique by low-dose ray radiography.

Abstract: Due to the wide diffusion of 3D maps, supporting tool for constructing the 3D maps are required. Individual information necessary for constructing the 3D maps is gathered by some measurement instruments. For example, 3D information and wall textures are acquired by triangulation (or GPS measurement) and optical devices, respectively. Building polygons in a 3D map can be constructed easily by combining the 3D (height) information and a 2D map. It is, however, difficult to obtain an appropriate texture for an arbitrary building polygon by combining those measurements information. In general, the texture mapping with the acquired image is performed manually. However, it takes huge costs to perform in a wide area. Therefore, the demand of the automation is extremely high. In this study, we aim to automatize the texture mapping by image information from the in-vehicle camera. An in-vehicle camera has the advantage that it is possible to take a picture of the building wall while driving over the broad area. But, the vibration and the traffic have influences on the photography environment. As a result, it is difficult to specify the building area in the image. In the proposed method, tracks of the camera are calculated from the acquired continuous image, the building area that corresponds to the polygon on the map is specified. In this paper, we described our observation about the result of a miniature model.

Abstract: For linear textures, widely exist on 3D engineering surfaces, a method for characterization based on the spectrum analysis is proposed. Through an angular spectrum analysis of the power spectrum of 3D surface signals, the directional characteristic parameters of the linear texture distribution on the surface are extracted. By using the directional parameters, the engineering surface can be roughly identified. A texture detector based on the directional Gabor wavelet transformation is used to detect the texture signals. The linear texture features of different directions and scales on a complex engineering surface can be decomposed. A weighting multi-scale correlative analyzing method is presented. The correlation analysis results of the texture features of different scales are weighted according to the significance and summed to obtain the final correlation results. Through Laplacian differential operation of the correlative output, a sharper correlative peak is obtained. This method has been successfully used to extract and identify bullet marks.