Search

International audience; The importance of image compression is now essential during transmission or storage processes in various data applications, especially in medical and biometric systems. To perform the effectiveness of the compression process on images and evaluate degradation caused by this process, image quality assessment becomes an important tool in image services. We note that the objective criteria in image quality depend especially on the image type and image texture composition. The actual tendency is to find metrics making better qualification on errors in compressed images and correlate with the human visual system. This paper presents an investigation to examine and evaluate image compression degradation by the use of a new tendency concept of image quality assessment based on texture and edge analysis. To perform and practice this evaluation, we compress the medical and biometric images using second-generation wavelet compression algorithms and study the degradation of texture information in these images.

Color constancy is the capability to observe the true color of a scene from its image regardless of the scene's illuminant. It is a significant part of the digital image processing pipeline and is utilized when the true color of an object is required. Most existing color constancy methods assume a uniform illuminant across the whole scene of the image, which is not always the case. Hence, their performances are influenced by the presence of multiple light sources. This paper presents a color constancy adjustment technique that uses the texture of the image pixels to select pixels with sufficient color variation to be used for image color correction. The proposed technique applies a histogram-based algorithm to determine the appropriate number of segments to efficiently split the image into its key color variation areas. The K-means++ algorithm is then used to divide the input image into the pre-determined number of segments. The proposed algorithm identifies pixels with sufficient color variation in each segment using the entropies of the pixels, which represent the segment's texture. Then, the algorithm calculates the initial color constancy adjustment factors for each segment by applying an existing statistics-based color constancy algorithm on the selected pixels. Finally, the proposed method computes color adjustment factors per pixel within the image by fusing the initial color adjustment factors of all segments, which are regulated by the Euclidian distances of each pixel from the centers of gravity of the segments. The experimental results on benchmark single- and multiple-illuminant image datasets show that the images that are obtained using the proposed algorithm have significantly higher subjective and very competitive objective qualities compared to those that are obtained with the state-of-the-art techniques.

The rendering effect of known visual image texture is poor and the output image is not always clear. To solve this problem, this paper proposes a visual image rendering based on scene visual understanding algorithm. In this approach, the color segmentation of known visual scene is carried out according to a predefined threshold, and the segmented image is processed by morphology. For this purpose, the extraction rules are formulated to screen the candidate regions. The color image is fused and filtered in the neighborhood, the pixels of the image are extracted, and the 2D texture recognition is realized by multilevel fusion and visual feature reconstruction. Using compact sampling to extract more target features, feature points are matched, the coordinate system of known image information are integrated into a unified coordinate system, and design images are generated to complete art-aided design. Simulation results show that the proposed method is more accurate than the original method for extracting the information of known images, which helps to solve the problem of clearly visible output images and improves the overall design effect.

A static gesture recognition algorithm is proposed based on a recursive graph of the upper triangular image texture, motivated by the low accuracy and robustness of existing algorithms. Firstly, the fingertip localization method based on contour curvature is used to obtain the palm region and then the gesture contour model is established. Secondly, a recurrence plot of the gesture contour sequence is built, which is constructed using the central point and the starting point coordinates. Finally, the texture recognition algorithm is applied to calculate the normalized distance between the recurrence plots of the gesture. The experimental results show that the proposed algorithm can achieve higher recognition accuracy under varying complex backgrounds and illumination. At the same time, when the gesture is in rotation, translation, or scaling, the algorithm has high robustness with a small amount of computation and high efficiency.

A constant sound speed of 1540 m/s is usually used by ultrasound imaging systems for calculating delay curves in beamforming. A mismatch of this constant system sound speed and the real one in human tissue could result in significant defocusing and degrade the image resolution in the modern ultrasound imaging system. This paper has investigated characteristics and potential relationship of image texture parameters to image focusing quality due to unmatched speed of sound. Algorithms for sound speed optimization (SSO) system based on fuzzy process and image texture parameters are presented. The proposed method has been investigated and verified from phantom imaging including speckle, point targets and cyst images. Test results show that individual texture feature may help to determine appropriate sound speed used for beamforming; however, only the proposed fuzzy process based system can achieve the best sound speed detection with consistent and robust output.

This paper investigates the problem of glacier flow estimation using Synthetic Aperture Radar (SAR) image data. Our motivation is to exploit a weighted graph model constructed from characteristic points (i.e. keypoints) to measure the displacement vectors located at their positions. In fact, characteristic points are capable of capturing the image's radiometric and contextual information. Then, by encoding their interaction and inter-connection, a graph model is able to characterize both intensity and geometry information from the image content, which is relevant for texture tracking task. In this work, we employ a graph-based similarity measure to track the local texture information around each keypoint in order to figure out its correspondence from the other image and calculate the associated displacement. The proposed approach is tested and evaluated using high resolution TerraSAR-X images acquired from the Argentiere Glacier located in the French Alps. Our preliminary experimental results show the algorithm's capacity to provide a fast and reliable estimation of glacier flows, especially over highly textured and structured regions.

International audience; Texture feature is a measure method about relationship among the pixels in local area, reflecting the changes of image space gray levels. This paper presents a texture feature extraction method based on regional average binary gray level difference co-occurrence matrix, which combined the texture structural analysis method with statistical method. Firstly, we calculate the average binary gray level difference of eight-neighbors of a pixel to get the average binary gray level difference image which expresses the variation pattern of the regional gray levels. Secondly, the regional co-occurrence matrix is constructed by using these average binary gray level differences. Finally, we extract the second-order statistic parameters reflecting the image texture feature from the regional co-occurrence matrix. Theoretical analysis and experimental results show that the image texture feature extraction method has certain accuracy and validity

In the present paper, a methodological scheme, bringing together common Acoustic Seabed Classification (ASC) systems and a powerful data decomposition approach, called Independent Component Analysis (ICA), is demonstrated regarding its suitability for detecting small targets in Side Scan Sonar imagery. Traditional ASC systems extract numerous texture descriptors, leading to a large feature vector, the dimensionality of which is reduced by means of data decomposition techniques, usually Principal Component Analysis (PCA), prior to classification. However, in the target detection issue, data decomposition should point towards finding components that represent sub-ordinary image information (i.e., small targets) rather than a dominant one. ICA has long been proved to be suitable for separating targets from a background, and this study represents a novel exhibition of its applicability to Side Scan Sonar (SSS) images. The present study attempts to build a fully automated target detection approach that combines image based feature extraction, ICA, and unsupervised classification. The suitability of the proposed approach has been demonstrated using an SSS data-set containing more than 70 manmade targets, most of them metallic, validated through a marine magnetic survey or ground truthing inspection. The method exhibited very good performance as it was able to detect more than 77% of the targets and it produced less than seven false alarms per km2. Moreover, it was compared to cases where, in the exact same methodological scheme, no decomposition technique is used, or PCA is employed instead of ICA, achieving the highest detection rate, but, more importantly, producing more than six times less false alarms, thus proving that ICA successfully manages to maximize target to background separation.

The analysis of surface textures plays an important role in the geomorphometric analysis of high-resolution digital terrain models. Surface textures can be analyzed by means of geostatistical variogram-based indices. The use of variogram-based indices is promising because of their ability to consider the multiscale and anisotropic character of morphometric data. However, similar to other variance-type statistics, variogram-based indices are sensitive to the presence of hotspots and non-stationary data. Consequently, we present a multi-scale and directional image texture analysis operator (MAD or Median Absolute Differences) derived from a modification of a variogram estimator. MAD has been specifically developed to improve the robustness of variogram-based surface indices with a special focus on strongly non-stationary and often noisy spatial data representing solid earth surface morphology. Although the operator has been specifically developed for the analysis of high-resolution digital terrain models, it can be applied to the texture analysis of any type of image. Consequently MAD could be of interest in the broader context of remote sensing as well as for all disciplines for which image texture analysis is relevant. The theoretical presentation of the surface texture operator is accompanied by a working software prototype. The software prototype has been implemented in the Python scripting language for use in ArcGIS (ESRI) using its Spatial Analyst functions. The prototype architecture is concise and can be easily coded in different software environments, such as GIS mapping and image analysis software. The software prototype proposed has been developed to facilitate the development of ad hoc surface texture indices capable of adapting to the special needs of the study at hand. The MAD operator represents an improvement over variogram-based surface texture indices, offering a robust description of relevant aspects of surface texture, including surface roughness.

The information of seismic damage of buildings in SAR images of different time phase, especially in SAR images after earthquake, is easily disturbed by other factors, which affects the accuracy of information discrimination. In order to identify and evaluate the distribution information of the seismic damage accurately and make full use of the abundant texture features in the SAR image. The conventional method of change detection based on texture features usually takes the pixel as the calculating unit. In this paper, a method of texture feature change detection of SAR images based on watershed segmentation algorithm is proposed. Based on the optimization of texture feature parameters, the feature parameters are segmented by the watershed segmentation algorithm, and the feature object image is obtained. This method introduces the idea of object oriented, and carries out the calculation of the difference map at the object level, Finally, the classification threshold value of different types of seismic damage types is selected, and the recognition of building damage is achieved. Taking the ALOS data before and after the earthquake in Yushu as an example to verify the effectiveness of the method, the overall accuracy of the building extraction is 88.9%, Compared with pixel-based methods, it is proved that the proposed method is effective.

International audience; The present study involves an investigation of a pointwise approach on the feature covariance matrix to extract textu-ral features for very high resolution (VHR) satellite images. Indeed, our proposition is to construct the covariance matrix of oriented gradients using a non-dense approach based on characteristic points extracted from the image. This novel non-dense covariance descriptor is capable of not only capturing both radiometric and local geometric information from the image, but also encoding their joint distribution and correlation, which are effectively relevant for texture characterization and discrimination. In order to demonstrate the efficiency of the proposed descriptor, a texture-based image segmentation stage is carried out. First efforts on VHR panchromatic images using the proposed algorithm provide very promising and competitive results compared to classical methods.

Liver biopsy is considered to be the gold standard for analyzing chronic hepatitis and fibrosis; however, it is an invasive and expensive approach, which is also difficult to standardize. Medical imaging techniques such as ultrasonography, computed tomography (CT), and magnetic resonance imaging are non-invasive and helpful methods to interpret liver texture, and may be good alternatives to needle biopsy. Recently, instead of visual inspection of these images, computer-aided image analysis based approaches have become more popular. In this study, a non-invasive, low-cost and relatively accurate method was developed to determine liver fibrosis stage by analyzing some texture features of liver CT images. In this approach, some suitable regions of interests were selected on CT images and a comprehensive set of texture features were obtained from these regions using different methods, such as Gray Level Co-occurrence matrix (GLCM), Laws' method, Discrete Wavelet Transform (DWT), and Gabor filters. Afterwards, sequential floating forward selection and exhaustive search methods were used in various combinations for the selection of most discriminating features. Finally, those selected texture features were classified using two methods, namely, Support Vector Machines (SVM) and k-nearest neighbors (k-NN). The mean classification accuracy in pairwise group comparisons was approximately 95% for both classification methods using only 5 features. Also, performance of our approach in classifying liver fibrosis stage of subjects in the test set into 7 possible stages was investigated. In this case, both SVM and k-NN methods have returned relatively low classification accuracies. Our pairwise group classification results showed that DWT, Gabor, GLCM, and Laws' texture features were more successful than the others; as such features extracted from these methods were used in the feature fusion process. Fusing features from these better performing families further improved the classification performance. The results show that our approach can be used as a decision support system in especially pairwise fibrosis stage comparisons. (C) 2014 Elsevier B.V. All rights reserved., Liver biopsy is considered to be the gold standard for analyzing chronic hepatitis and fibrosis; however, it is an invasive and expensive approach, which is also difficult to standardize. Medical imaging techniques such as ultrasonography, computed tomography (CT), and magnetic resonance imaging are non-invasive and helpful methods to interpret liver texture, and may be good alternatives to needle biopsy. Recently, instead of visual inspection of these images, computer-aided image analysis based approaches have become more popular. In this study, a non-invasive, low-cost and relatively accurate method was developed to determine liver fibrosis stage by analyzing some texture features of liver CT images. In this approach, some suitable regions of interests were selected on CT images and a comprehensive set of texture features were obtained from these regions using different methods, such as Gray Level Co-occurrence matrix (GLCM), Laws’ method, Discrete Wavelet Transform (DWT), and Gabor filters. Afterwards, sequential floating forward selection and exhaustive search methods were used in various combinations for the selection of most discriminating features. Finally, those selected texture features were classified using two methods, namely, Support Vector Machines (SVM) and k-nearest neighbors (k-NN). The mean classification accuracy in pairwise group comparisons was approximately 95% for both classification methods using only 5 features. Also, performance of our approach in classifying liver fibrosis stage of subjects in the test set into 7 possible stages was investigated. In this case, both SVM and k-NN methods have returned relatively low classification accuracies. Our pairwise group classification results showed that DWT, Gabor, GLCM, and Laws’ texture features were more successful than the others; as such features extracted from these methods were used in the feature fusion process. Fusing features from these better performing families further improved the classification performance. The results show that our approach can be used as a decision support system in especially pairwise fibrosis stage comparisons.

International audience; This paper proposes a texture-based segmentation method for very high spatial resolution imagery. Indeed, our main objective is to perform a sparse image representation modeled by a graph and then to exploit the wavelet transform on graph for the final purpose of image segmentation. Here, a set of pixels of interest, called representative pixels, is first extracted from the image and considered as vertices for constructing a weighted graph. Once the wavelet transform on graph is generated, their coefficients serve as textural features and will be exploited for unsupervised segmentation. Experimental results show the effectiveness of the proposed method when applied for very high spatial resolution multi-spectral images in terms of good segmentation precision as well as low complexity requirement

Motivation: A key element in understanding the aging of Caenorhabditis elegans is objective quantification of the morphological differences between younger and older animals. Here we propose to use the image texture entropy as an objective measurement that reflects the structural deterioration of the C.elegans muscle tissues during aging. Results: The texture entropy and directionality of the muscle microscopy images were measured using 50 animals on Days 0, 2, 4, 6, 8, 10 and 12 of adulthood. Results show that the entropy of the C.elegans pharynx tissues increases as the animal ages, but a sharper increase was measured between Days 2 and 4, and between Days 8 and 10. These results are in agreement with gene expression findings, and support the contention that the process of C.elegans aging has several distinct stages. This can indicate that C.elegans aging is driven by developmental pathways, rather than stochastic accumulation of damage. Availability: The image data are freely available on the Internet at http://ome.grc.nia.nih.gov/iicbu2008/celegans, and the Haralick and Tamura texture analysis source code can be downloaded at http://ome.grc.nia.nih.gov/wnd-charm. Contact: shamirl@mail.nih.gov

In this work, a system for the classification of liver dynamic contest- enhanced CT images is presented. The system simultaneously analyzes the images with the same slice location, corresponding to three typical acquisition moments (without contrast, arterial- and portal phase of contrast propagation). At first, the texture features are extracted separately for each acquisition mo- ment. Afterwards, they are united in one “multiphase” vector, characterizing a triplet of textures. The work focuses on finding the most appropriate features that characterize a multi-image texture. At the beginning, the features which are unstable and dependent on ROI size are eliminated. Then, a small subset of remaining features is selected in order to guarantee the best possible classification accuracy. In total, 9 extraction methods were used, and 61 features were calculated for each of three acquisition moments. 1511 texture triplets, corresponding to 4 hepatic tissue classes were recognized (hepatocellular carcinoma, cholangiocarcinoma, cirrhotic, and normal). As a classifier, an adaptive boosting algorithm with a C4.5 tree was used. Experiments show that a small set of 12 features is able to ensure classification accuracy exceeding 90%, while all of the 183 features provide an accuracy rate of 88.94%.

International audience

We present a new efficient approach for characterizing image texture based on a recently published discrete, orthonormal space-frequency transform known as the DOST. We develop a frequency-domain implementation of the DOST in two dimensions for the case of dyadic frequency sampling. Then, we describe a rapid and efficient approach to obtain local spatial frequency information for an image and show that this information can be used to characterize the horizontal and vertical frequency patterns in synthetic images. Finally, we demonstrate that DOST components can be combined to obtain a rotationally invariant set of texture features that can accurately classify a series of texture patterns. The DOST provides the computational efficiency and multi-scale information of wavelet transforms, while providing texture features in terms of Fourier frequencies. It outperforms leading wavelet-based texture analysis methods.

Proposed is a fast detection algorithm for urban road traffic congestion based on image processing technology. Firstly, to speed up the processing and to freely select the interesting area, the human-computer interaction vehicle area detection was put forward. Then, by using the difference of texture features between congestion image and unobstructed image, vehicle density estimation based on texture analysis is proposed. Through image grayscale relegation, gray level co-occurrence matrix calculation and feature extraction, the energy and entropy features that could reflect vehicle density were obtained from vehicle area. After features training, the decision threshold could be obtained and traffic congestion was carried out. Experimental results showed that the accuracy of the algorithm was as high as 99%, and the processing speed could satisfy the real-time requirement in engineering.

This work is oriented toward video tracking of vehicles in a typical traffic environment, based on particle filters. The proposed tracking algorithm is based on simultaneous usage of three different image features - color, edge orientation, and texture. All three features are related to the contents of a rectangular window that includes both the vehicle that is tracked and local background and they are represented in the form of appropriate histograms. Based on individual estimates produced by every single feature, the resultant estimate is made by their weighted averaged. Weighting factors are adaptively changing depending on the quality of a particular feature, estimated by calculations of average similarities between the reference window and the set of windows on particles' positions. The tracking accuracies of single-feature and three-features-based filters have been verified using the set of traffic sequences illustrating the presence of typical disturbances (shadows, partial and full occlusions, maneuvering etc.).

BACKGROUND AND PURPOSE: Iterative reconstruction has promise in lowering the radiation dose without compromising image quality, but its full potential has not yet been realized. While phantom studies cannot fully approximate the subjective effects on image quality, live animal models afford this assessment. We characterize dose reduction in head CT by applying advanced modeled iterative reconstruction (ADMIRE) in a live ovine model while evaluating preservation of gray-white matter detectability and image texture compared with filtered back-projection. MATERIALS AND METHODS: A live sheep was scanned on a Force CT scanner (Siemens) at 12 dose levels (82–982 effective mAs). Images were reconstructed with filtered back-projection and ADMIRE (strengths, 1–5). A total of 72 combinations (12 doses × 6 reconstructions) were evaluated qualitatively for resemblance to the reference image (highest dose with filtered back-projection) using 2 metrics: detectability of gray-white matter differentiation and noise-versus-smoothness in image texture. Quantitative analysis for noise, SNR, and contrast-to-noise was also performed across all dose-strength combinations. RESULTS: Both qualitative and quantitative results confirm that gray-white matter differentiation suffers at a lower dose but recovers when complemented by higher iterative reconstruction strength, and image texture acquires excessive smoothness with a higher iterative reconstruction strength but recovers when complemented by dose reduction. Image quality equivalent to the reference image is achieved by a 58% dose reduction with ADMIRE-5. CONCLUSIONS: An approximately 60% dose reduction may be possible while preserving diagnostic quality with the appropriate dose-strength combination. This in vivo study can serve as a useful guide for translating the full implementation of iterative reconstruction in clinical practice.

In this paper, for evaluating the 3-D roughness of the additive manufacturing surfaces, we constructed a 3-D reconstruction system of structured light scanner. By calibrating the system, the center line of structured light is extracted online to reconstruct the profile of additive manufacturing and realize data registration. A dynamic texture coarseness algorithm is proposed, which combines 3-D data with 2-D Gaussian filtering and texture coarseness characteristics to transform 3-D roughness into visual image texture coarseness. The algorithm is applied to evaluate 3-D weld roughness with low delay. The validity of the algorithm is verified by roughness comparison specimens and the actual material adding experiment. The result of roughness is reliable and conforms to the evaluation standard of weld quality. At the same time, the position of structured light is optimized in the process of on-line detection, which reduces the complexity of extracting contour centerline and ensures the low delay characteristic of roughness calculation.

The shortcoming of the coherence of digital holographic light sources leads to the generation of holographic reconstruction speckle noise, which seriously affects the quality of holographic reconstruction. Although many advanced algorithms for reducing speckle noise in digital holography (DH) have achieved good results, in the process of processing image speckle noise, the details of the image are blurred, and the information relating to the image texture is lost. Therefore, we propose a new algorithm, which combines automatic GrabCut and guided filtering to solve the problem of blurred image details in filtering reconstruction. The new algorithm is applied to the problem of holographic speckle removal for the first time. In this paper, the new algorithm not only achieves quasi-noise-free (approximate the noise-free state) DH reconstruction but also realizes the retention of details in the image. The quality of the resulting holographic reconstruction is comparable to that achieved by incoherent technology, which exceeds the current level of DH and produces a good visual effect.

The guided filter has been acknowledged as an exceptional edge-preserving filter whose output is a locally linear transform of the guidance image. However, the traditional guided filter heavily relies on the guidance image and fails to achieve the desired result when performing image denoising without a clear guidance image. In this study, to address this limitation, the authors propose a simple yet effective guided filter variant for the single image noise removing. They further show that the proposed denoising strategy can be easily realised by using the iterative framework. Moreover, the weak textured patches based image noise estimation is utilised to generate a clear intermediate image which makes the proposed method highly adaptable to the local noise level. Experimental results demonstrate that their proposed algorithm can compete with the state-of-the-art local denoising methods in edge-preserving.

Retinal photomontages, which are constructed by aligning and integrating multiple fundus images, are useful in diagnosing retinal diseases affecting peripheral retina. We present a novel framework for constructing retinal photomontages that fully leverage recent deep learning methods. Deep learning based object detection is used to define the order of image registration and blending. Deep learning based vessel segmentation is used to enhance image texture to improve registration performance within a two step image registration framework comprising rigid and non-rigid registration. Experimental evaluation demonstrates the robustness of our montage construction method with an increased amount of successfully integrated images as well as reduction of image artifacts.

The learning-based super-resolution reconstruction method inputs a low-resolution image into a network, and learns a non-linear mapping relationship between low-resolution and high-resolution through the network. In this study, the multi-scale super-resolution reconstruction network is used to fuse the effective features of different scale images, and the non-linear mapping between low resolution and high resolution is studied from coarse to fine to realise the end-to-end super-resolution reconstruction task. The loss of some features of the low-resolution image will negatively affect the quality of the reconstructed image. To solve the problem of incomplete image features in low-resolution, this study adopts the multi-scale super-resolution reconstruction method based on guided image filtering. The high-resolution image reconstructed by the multi-scale super-resolution network and the real high-resolution image are merged by the guide image filter to generate a new image, and the newly generated image is used for secondary training of the multi-scale super-resolution reconstruction network. The newly generated image effectively compensates for the details and texture information lost in the low-resolution image, thereby improving the effect of the super-resolution reconstructed image.Compared with the existing super-resolution reconstruction scheme, the accuracy and speed of super-resolution reconstruction are improved.

Infrared and visible image fusion technology provides many benefits for human vision and computer image processing tasks, including enriched useful information and enhanced surveillance capabilities. However, existing fusion algorithms have faced a great challenge to effectively integrate visual features from complex source images. In this paper, we design a novel infrared and visible image fusion algorithm based on visual attention technology, in which a special visual attention system and a feature fusion strategy based on the saliency maps are proposed. Special visual attention system first utilizes the co-occurrence matrix to calculate the image texture complication, which can select a particular modality to compute a saliency map. Moreover, we improved the iterative operator of the original visual attention model (VAM), a fair competition mechanism is designed to ensure that the visual feature in detail regions can be extracted accurately. For the feature fusion strategy, we use the obtained saliency map to combine the visual attention features, and appropriately enhance the tiny features to ensure that the weak targets can be observed. Different from the general fusion algorithm, the proposed algorithm not only preserve the interesting region but also contain rich tiny details, which can improve the visual ability of human and computer. Moreover, experimental results in complicated ambient conditions show that the proposed algorithm in this paper outperforms state-of-the-art algorithms in both qualitative and quantitative evaluations, and this study can extend to the field of other-type image fusion.

Over the last 20 years road pavement imaging has become a routine output from annual pavement assessment survey regimes across the world. Hitherto the traditional use of road pavement images in road condition assessment has been crack detection, rather than direct analysis of image features such as aggregate loss, changes in surface texture or deterioration of road markings. Any attempt to assess pavement condition change from features in a sequence of such images captured months or years apart requires image registration. A method for registering road pavement images is presented that makes use of an affine transformation based on pseudo-features within images. An affine transformation is considered suitable for registering road pavement images because of the linear way in which pavements are surveyed. Pseudo feature points are found using a modified corner detector, and then matching points between reference and template images established via a correlation analysis of pavement image texture. With 4 such points it is possible to establish an affine transformation between the images. The method is tested on pavement images captured on three UK sites between winter 2014/15 and 2015/16. The method successfully registered 98% of images captured on sites typical of the UK's strategic road network, and 65% of images captured on a site typical of the UK's minor road network. Keywords: Pavement engineering, Pavement texture, Image registration, Pseudo feature point

Computer vision is an area of the computer science which aims to make computers to have some functions owned by human vision system. During the research on computer vision, we often think about "how human see". Obviously, when a human observer views a scene, the observer sees not the whole complex scene, but rather a collection of objects. A common experience of segmentation is the way that an image can resolve itself into a figure, typically the significant, important object, and a ground, the background on which the figure lies. The capability of human beings to segment the complex scene into separated objects is so efficient that we regard it as a mystery. At meantime, it appeals the researchers of computer vision who want to let computer have the same capability. So the task, Image Segmentation, is presented. The chapter describes new achievements in the area of multimodal range and intensity image unsupervised segmentation. This chapter is organized as follows. Range sensors are described in section 2 followed by the current state of art survey in section 3. Sections 4 to 6 describe our fast range image segmentation method for scenes comprising general faced objects. This range segmentation method is based on a recursive adaptive probabilistic detection of step discontinuities (sections 4 and 5) which are present at object face borders in mutually registered range and intensity data. Detected face outlines guides the subsequent region growing step in section 6 where the neighbouring face curves are grouped together. Region growing based on curve segments instead of pixels like in the classical approaches considerably speed up the algorithm. The exploitation of multimodal data significantly improves the segmentation quality. The evaluation methodology a range segmentation benchmarks are described in section 7. Following sections show our experimental results of the proposed model (section 8), discuss its properties and conclude (section 9) the chapter.

Segmentation is the partitioning of an image into multiple regions (sets of pixels) according to a given criterion. The goal of segmentation is typically to locate objects of interest within the image. A wide variety of methods and algorithms are available to deal with the problem of the segmentation of images (Fu and Mui, 1981; Haralick and Shapiro, 1985; Pal and Pal, 1993). These methods can be broadly classified into four categories (Zhu and Yuille, 1996): • Edge-based techniques. • Region-based techniques. • Deformable models. • Global optimization approaches. The edge-based techniques are based on information about the boundaries of the image. Therefore, they try to locate the points in which abrupt changes occur in the levels of some property of the image, typically brightness (Canny, 1986; Rosenfeld and Kak, 1982). On the other hand, those methods that use spatial information of the image (e.g. color or texture) to produce the segmented image fit into the region-based techniques (Chen et al., 1992; Sahoo et al., 1988). These methods depend on the consistency of some relevant property in the different regions of the image. The deformable models are based on curves or surfaces defined within an image that moves due to the influence of certain forces. They can be classified into various groups, principally snakes, deformable templates and active contours (Blake and Isard, 1998; Kass et al., 1988). All of these techniques avoid the use of a global criterion when segmenting the image, which is contrary to the global optimization approaches (Geman and Geman, 1984; Kanungo et al., 1994). In this work a unified framework for image segmentation is proposed. The technique consists of two stages: a parallel seeded region growing algorithm (PSRG) and a region merging heuristic (RM). In Figure 1 the functional scheme of the proposed algorithm is shown. In the first step, different segmentations, performed in parallel, of the same input image are obtained. Each of these segmentations, which from now on will be called partial segmentations, are also generated in parallel using different number of processors. This way, the region growing algorithm uses a two level parallelism. Next, a region merging heuristic is applied to the oversegmented image created as result of combining the different initial