Bilateral filter

About: Bilateral filter is a research topic. Over the lifetime, 3500 publications have been published within this topic receiving 75582 citations.

Advanced spatio-temporal filtering techniques for photogrammetric image sequence analysis in civil engineering material testing

Abstract: The paper shows advanced spatial, temporal and spatio-temporal filtering techniques which may be used to reduce noise effects in photogrammetric image sequence analysis tasks and tools. As a practical example, the techniques are validated in a photogrammetric spatio-temporal crack detection and analysis tool applied in load tests in civil engineering material testing. The load test technique is based on monocular image sequences of a test object under varying load conditions. The first image of a sequence is defined as a reference image under zero load, wherein interest points are determined and connected in a triangular irregular network structure. For each epoch, these triangles are compared to the reference image triangles to search for deformations. The result of the feature point tracking and triangle comparison process is a spatio-temporally resolved strain value field, wherein cracks can be detected, located and measured via local discrepancies. The strains can be visualized as a color-coded map. In order to improve the measuring system and to reduce noise, the strain values of each triangle must be treated in a filtering process. The paper shows the results of various filter techniques in the spatial and in the temporal domain as well as spatio-temporal filtering techniques applied to these data. The best results were obtained by a bilateral filter in the spatial domain and by a spatio-temporal EOF (empirical orthogonal function) filtering technique.

Reduction of block effects in spatially re-sampled image information for block-based image coding

Abstract: A method of processing block-based image information including up sample filtering pixels located along boundaries of image blocks using a first filter strength and up sample filtering at least a portion of the pixels that are not located along boundaries of the image blocks using a second filter strength. The method may alternatively include up sample filtering pixels located along boundaries of image blocks and image sub-blocks using the first filter strength. An up sample filter system which includes a first up sample filter which filters pixels located along boundaries of the image blocks using a first filter strength and a second up sample filter which filters pixels that are not located along boundaries of the image blocks using a second filter strength.

Image processing apparatus, image processing method, program, and recording medium

Abstract: PROBLEM TO BE SOLVED: To provide an image processing apparatus, an image processing method, a program, and a recording medium for reducing noise while storing an edge even if the edge exists in one of a plurality of images. SOLUTION: A bilateral filter 5 includes a coefficient arithmetic section 51 for calculating coefficients of a filter and a filter section 52. The coefficient arithmetic section 51 calculates the coefficients W of the filter on the basis of two images comprising a visible light image Visible imaged by a visible light imaging section 2 and an infrared ray image Infr imaged by an infrared ray imaging section 3. The filter section 52 uses the coefficients W to apply filtering processing to a filter object region of the visible light image Visible. COPYRIGHT: (C)2006,JPO&NCIPI

Saliency Guided Image Detail Enhancement

Abstract: The use of visual saliency for perceptual enhancement of images has drawn significant attention. In this paper, we explore the idea of selectively enhancing salient regions of an image. Moreover, we develop an algorithm based on adaptive bilateral filtering for this purpose. In most of the filtering based methods, detail enhancement is performed by decomposing the image into base and detail layers; the detail layer is amplified and added back to the base layer to obtain the enhanced image. The decomposition is performed using edge-preserving smoothing such as bilateral filtering. The present novelty is that we use the saliency map to locally guide the smoothing (and the enhancement) action of the bilateral filter. The effectiveness of our proposal is demonstrated using visual results. In particular, our method does not suffer from gradient reversals and halo artifacts, and does not amplify fine details in non-salient regions that often appear as noise grains in the enhanced image. Moreover, if we choose to perform the filtering channelwise, then our method can be efficiently implemented using an existing fast algorithm.

Automatic brain MR image denoising based on texture feature-based artificial neural networks.

Abstract: Noise is one of the main sources of quality deterioration not only for visual inspection but also in computerized processing in brain magnetic resonance (MR) image analysis such as tissue classification, segmentation and registration. Accordingly, noise removal in brain MR images is important for a wide variety of subsequent processing applications. However, most existing denoising algorithms require laborious tuning of parameters that are often sensitive to specific image features and textures. Automation of these parameters through artificial intelligence techniques will be highly beneficial. In the present study, an artificial neural network associated with image texture feature analysis is proposed to establish a predictable parameter model and automate the denoising procedure. In the proposed approach, a total of 83 image attributes were extracted based on four categories: 1) Basic image statistics. 2) Gray-level co-occurrence matrix (GLCM). 3) Gray-level run-length matrix (GLRLM) and 4) Tamura texture features. To obtain the ranking of discrimination in these texture features, a paired-samples t-test was applied to each individual image feature computed in every image. Subsequently, the sequential forward selection (SFS) method was used to select the best texture features according to the ranking of discrimination. The selected optimal features were further incorporated into a back propagation neural network to establish a predictable parameter model. A wide variety of MR images with various scenarios were adopted to evaluate the performance of the proposed framework. Experimental results indicated that this new automation system accurately predicted the bilateral filtering parameters and effectively removed the noise in a number of MR images. Comparing to the manually tuned filtering process, our approach not only produced better denoised results but also saved significant processing time.