Color Information Of Image Research Articles

Research on Fast Face Detection Algorithm in Complex Background

This paper presents a fast algorithm for face detection in complex background, in which image color information is used first, project upper part of the partition of face in the gray image to horizontal and vertical direction. Determine the eyes positions by the minimum value, and scope the human eye in the face of prior knowledge to judge and adjust the face region.

Graph-based segmentation for RGB-D data using 3-D geometry enhanced superpixels.

With the advances of depth sensing technologies, color image plus depth information (referred to as RGB-D data hereafter) is more and more popular for comprehensive description of 3-D scenes. This paper proposes a two-stage segmentation method for RGB-D data: 1) oversegmentation by 3-D geometry enhanced superpixels and 2) graph-based merging with label cost from superpixels. In the oversegmentation stage, 3-D geometrical information is reconstructed from the depth map. Then, a K-means-like clustering method is applied to the RGB-D data for oversegmentation using an 8-D distance metric constructed from both color and 3-D geometrical information. In the merging stage, treating each superpixel as a node, a graph-based model is set up to relabel the superpixels into semantically-coherent segments. In the graph-based model, RGB-D proximity, texture similarity, and boundary continuity are incorporated into the smoothness term to exploit the correlations of neighboring superpixels. To obtain a compact labeling, the label term is designed to penalize labels linking to similar superpixels that likely belong to the same object. Both the proposed 3-D geometry enhanced superpixel clustering method and the graph-based merging method from superpixels are evaluated by qualitative and quantitative results. By the fusion of color and depth information, the proposed method achieves superior segmentation performance over several state-of-the-art algorithms.

Color Image Segmentation Based on Secondary Watershed and GrowCut Algorithm

GrowCut algorithm is not only an interactive algorithm on the basis of cell automata, but also a multi-label algorithm based on seeds point. Aiming at the GrowCut algorithm usually asks users to partition foreground and background manually and mark a lot more initial seeds. This paper presents an automatic object segmentation method which combining secondary watershed and GrowCut algorithm, here in the following paper refers it to as SWGC algorithm. It firstly using the twice used watershed algorithm to partition the input image, the segmented regions are labeled using Mahalanobis distance, and merged according to the image color and space information, thereafter applying the GrowCut algorithm to perform globally optimized segmentation. The main contribution focuses on performing automatic segmentation which consist of obtain the foreground and background region and generate the seed template of GrowCut algorithm automatically. Thus not only leave out the constraints of user interaction operation, but also avoid the subjectivity and uncertainty. The proposed method reduces the runtime significantly as well as improves the segmentation accuracy and robustness of GrowCut algorithm. Experimental results show SWGC algorithm has superior performance compared to the other related methods.

Image Capturing and Segmentation Method for Characters Marked on Hot Billets

Real-time detecting information marked on billets is important for automatically manufacturing and management in steelworks. But due to the tough production environments in steel enterprises, capturing and identifying characters marked on hot billets have many challenges. This paper presents a real-time image capturing and segmenting method with machine vision for characters marked on hot billets, and characters area is located based on color information of images. Furthermore, considering the marked characters are often slant, we proposed a kind of characters skew correction method to adjust the alignment of characters, and then segment characters into singles for recognition. Finally, with the proposed method, we have conducted some experiments in Baosteel Company. The result shows that our method can achieve 97% segmentation rate if we select proper image acquisition device and preprocessing algorithm. Additionally, it provides a new way for steel enterprise real-time capturing and segmenting marked characters image.

Visualization of dyed NAPL concentration in transparent porous media using color space components

Finding a correlation between image pixel information and non-aqueous phase liquid (NAPL) saturation is an important issue in bench-scale geo-environmental model studies that employ optical imaging techniques. Another concern is determining the best dye color and its optimum concentration as a tracer for use in mapping NAPL zones. Most bench scale flow studies employ monochromatic gray-scale imaging to analyze the concentration of mostly red dyed NAPL tracers in porous media. However, the use of grayscale utilizes a third of the available information in color images, which typically contain three color-space components. In this study, eight color spaces consisting of 24 color-space components were calibrated against dye concentration for three color-dyes. Additionally, multiple color space components were combined to increase the correlation between color-space data and dyed NAPL concentration. This work is performed to support imaging of NAPL migration in transparent synthetic soils representing the macroscopic behavior of natural soils. The transparent soil used in this study consists of fused quartz and a matched refractive index mineral-oil solution that represents the natural aquifer. The objective is to determine the best color dye concentration and ideal color space components for rendering dyed sucrose-saturated fused quartz that represents contamination of the natural aquifer by a dense NAPL (DNAPL). Calibration was achieved for six NAPL zone lengths using 3456 images (24 color space components×3 dyes×48 NAPL combinations) of contaminants within a defined criteria expressed as peak signal to noise ratio. The effect of data filtering was also considered and a convolution average filter is recommended for image conditioning. The technology presented in this paper is fast, accurate, non-intrusive and inexpensive method for quantifying contamination zones using transparent soil models.

Applying LCS To Affective Image Classification In Spatial-Frequency Domain

Abstract Recent studies have utilizes color, texture, and composition information of images to achieve affective image classification. However, the features related to spatial-frequency domain that were proven to be useful for traditional pattern recognition have not been tested in this field yet. Furthermore, the experiments conducted by previous studies are not internationally-comparable due to the experimental paradigm adopted. In addition, contributed by recent advances in methodology, that are, Hilbert-Huang Transform (HHT) (i.e. Empirical Mode Decomposition (EMD) and Hilbert Transform (HT)), the resolution of frequency analysis has been improved. Hence, the goal of this research is to achieve the affective image-classification task by adopting a standard experimental paradigm introduces by psychologists in order to produce international-comparable and reproducible results; and also to explore the affective hidden patterns of images in the spatial-frequency domain. To accomplish these goals, multiple human-subject experiments were conducted in laboratory. Extended Classifier Systems (XCSs) was used for model building because the XCS has been applied to a wide range of classification tasks and proved to be competitive in pattern recognition. To exploit the information in the spatial-frequency domain, the traditional EMD has been extended to a two-dimensional version. To summarize, the model built by using the XCS achieves Area Under Curve (AUC) = 0.91 and accuracy rate over 86%. The result of the XCS was compared with other traditional machine-learning algorithms (e.g., Radial-Basis Function Network (RBF Network)) that are normally used for classification tasks. Contributed by proper selection of features for model building, user-independent findings were obtained. For example, it is found that the horizontal visual stimulations contribute more to the emotion elicitation than the vertical visual stimulation. The effect of hue, saturation, and brightness; is also presented.

Dense terrain stereoreconstruction using modified SGM

A technique for creating 3D terrain models based on digital aerial images, using an algorithm of semi-global matching, is presented. A method of hierarchical application of the algorithm is demonstrated. A number of modifications and improvements at all stages of algorithm operation are proposed. Among them the following ones are distinguished: due account of the gradient and color information of images, the interpolation of the pixel matching metric for increasing the algorithm resolution and improving the stability to small distortions of the input data, filtering the matching cost and post-processing of disparity map by a bilateral filter. Results of algorithm application and the advantages of the modification are demonstrated by an example of processing of pairs of high-resolution aerial images.

RGB-Depth 카메라 기반의 실내 연기검출

본 논문에서 RGB-Depth 카메라를 이용하여 실내에서의 연기를 검출하는 알고리즘을 제안한다. RGB-Depth 카메라는 RGB 색영상과 깊이 정보를 제공한다. 키넥트(Kinect)는 특정한 패턴의 적외선을 출력하고 이를 적외선 카메라로 수집하고 분석하여 깊이 정보를 획득한다. 특정한 패턴을 구성하는 점들 각각에 대하여 거리를 측정하고 객체면의 깊이를 추정한다. 따라서, 이웃하는 점들의 깊이 변화가 많은 객체인 경우에는 객체면의 깊이를 결정하지 못한다. 연기의 농도가 일정 주파수로 변화하고, 적외선 영상의 이웃하는 화소간의 변화가 많기 때문에 키넥트가 깊이를 결정하지 못한다. 본 논문에서는 연기에 대한 키넥트의 특성을 이용하여 연기를 검출한다. 키넥트가 깊이를 결정하지 못한 영역을 후보영역으로 설정하고, 색영상의 밝기가 임계값보다 큰 경우 연기영역으로 결정한다. 본 논문에서는 시뮬레이션을 통하여 실내에서의 연기 검출에 RGB-Depth 카메라가 효과적임을 확인할 수 있다. In this paper, an algorithm using RGB-depth camera is proposed to detect smoke in interrior. RGB-depth camera, the Kinect provides RGB color image and depth information. The Kinect sensor consists of an infra-red laser emitter, infra-red camera and an RGB camera. A specific pattern of speckles radiated from the laser source is projected onto the scene. This pattern is captured by the infra-red camera and is analyzed to get depth information. The distance of each speckle of the specific pattern is measured and the depth of object is estimated. As the depth of object is highly changed, the depth of object plain can not be determined by the Kinect. The depth of smoke can not be determined too because the density of smoke is changed with constant frequency and intensity of infra-red image is varied between each pixels. In this paper, a smoke detection algorithm using characteristics of the Kinect is proposed. The region that the depth information is not determined sets the candidate region of smoke. If the intensity of the candidate region of color image is larger than a threshold, the region is confirmed as smoke region. As results of simulations, it is shown that the proposed method is effective to detect smoke in interior.

A homography transform based higher-order MRF model for stereo matching

Stereo matching is one of the most important and fundamental topics in computer vision. It is usually solved by minimizing an energy function, which includes a data term and a smoothness term. The data term consists of the matching cost, and the smoothness term encodes the prior assumption that the surfaces are piecewise smooth. In contrast to the traditional methods, in which the smoothness term is modeled by the pairwise interactions, the smoothness term is modeled with a higher-order model in this paper. With the prior assumption that a tiny piece of a smooth surface is approximately planar, a higher-order potential function based on the homography transformations is presented. Then the energy function defined on a factor graph is proposed, in which the coefficients of the factors depend on the color information of the input images so that the discontinuous edges are preserved. The belief propagation (BP) algorithm is adopted to minimize the energy function, and the experimental results tested on the Middlebury data set show the potential of the proposed method.

Color Edge Detection by Using the Centerline Extraction Method

In order to obtain more complete and continuous edge information of the image, the image enhancement methods and Hessian matrix are used in the process of edge detection. Based on the gradient information of color images, the pseudo-color edges can be got by using the multi-channel edge detection. Then, enhance the edge information and remove the correlation to obtain complete edge information. The Hessian matrix is used in the last place to remove edges with redundant background texture and coarse edges so that the edge information will be more continuous and smooth. Two experiments are conducted to verify the effectiveness of the proposed method. The software is developed by using MATLAB. Experiments have confirmed that the result of proposed detection is more continuous and clearer and more details are contained. Furthermore, a good balance between the integrity and accuracy of edge detection is achieved as well.

Information System in Image Classification Based on SVM and Color Clustering Analysis

Effective use of the color feature of Content Based Image Retrieval (CBIR) and Image classification is an important basic research, but there are some shortcomings in the color histogram representation method, such as high dimension, pixels spatial information is ignored and so on. Although color feature data can reduce the dimension by quantification, but some useful image color information will be discard. In this paper, the image color information processing in space constrained fuzzy clustering to obtain a lower dimensional color feature data of the image characteristics of domain colors description, and use multi-class support vector machine to classify color images. Experimental results show that the proposed method can better describe image color information than color histogram; image domain color description combined with support vector machine model can achieve the automatic classification of images effectively.

Nowcasting of Spatial Average Irradiance in Several km Radius Area using All-sky Image

Because of the unstable power output characteristics of a photovoltaic power generation system (PVS), the on-line monitoring or nowcasting of the aggregated PVS power output is important for the stable operation of electric power system. In this paper, we propose a nowcasting method of the spatial average irradiance in the area of several km radius using the all-sky image and the observed irradiance both at single point. First, the proposed method classifies the sky condition based on the color information of the all-sky image. If the sky is classified as the uniform condition (very fine or very cloudy), the spatial average irradiance is estimated as the same with the single point observed irradiance. If not, the spatial average irradiance is estimated by using a neural network (NN) model utilizing the color information as the inputs. As a result of a demonstrative study for several months, the Root Mean Square Error (RMSE) of the NN model-based estimation for the periods of the non-uniform sky condition is 103.8W/m2 (15.2%). Because the performance of the sky condition classification is high, RMSE for the periods of the uniform sky condition is 41.8W/m2 (8.7%), resulting in RMSE of 77.4W/m2 (13.5%) for the entire periods.

Contour-Based Image Registration using Bipartite Graph Matching with Munkres Algorithm

Image registration is a vital research topic in image processing. In this pap er, we present a novel method to register color image and depth information captured by Kinect for Xbox 360. A contour-based approach is employed to find the correspondence points and estimate the transformation parameters model between color image and depth image. In our paper, the boundary contours are detected by Canny edge detector and located to sub-pixel level by a B-spline model. The shape descriptors of contours are computed by shape context. The correspondence points on both similar contours will have similar shape descriptors, which enables us to solve a bipartite graph matching with Munkres algorithm. Based on the correspondence points, the transform model that best aligns the two images can be estimated via RANSAC method. Experiments on a series of natural images are used for compare with some existing approaches and demonstrate the effectiveness of our method.

A highly accurate dense approach for homography estimation using modified differential evolution

The homography corresponds to a 3×3 matrix which transfers image points between two images of a planar scene or two images captured by cameras under purely rotational motion. Homography estimation is crucial to many computer vision tasks involving multi-view geometry. Unlike most existing algorithms using sparse information extracted from images, this paper proposes a dense homography estimation method taking into account both the color and gradient information of the whole image. In particular, homography estimation is recast as a two-objective optimization problem, which is solved within a global optimization procedure guided by sparse control points (SCPs) based on modified differential evolution (DE). In order to improve the computational efficiency, two strategies namely pre-evaluation and coarse-to-fine (C2F) search are integrated into the proposed framework. The experimental results on synthetically rendered images and real images demonstrate that the new method can consistently improve the accuracy of homography estimation compared with two most successful feature based algorithms, and the incorporated acceleration strategies are able to speed up the minimization procedure by about 15 times. The applicability of our proposed method is further demonstrated in two real-world applications, namely occlusion removal and image mosaicing.

Application of Different HSI Color Models to Detect Fire-Damaged Mortar

To obtain a better understanding of the effect of vehicle fires on rigid pavement, a nondestructive test method utilizing an ordinary digital camera to capture images of mortar at five elevated temperatures was undertaken. These images were then analyzed by “image color-intensity analyzer” software. In image analysis, the RGB color model was the basic system used to represent the color information of images. HSI is a derived-color model that is transformed from an RGB model by formulae. In order to understand more about surface color changes and temperatures after a vehicle fire, various transformation formulae used in different research areas were applied in this study. They were then evaluated to obtain the optimum HSI model for further studies of fire-damaged mortar through the use of image analysis.

Discovery of automotive design paradigm using relevance feedback

According to the development of convergence technology and diversification of lifestyle, the importance of automotive design about sensibility products is rapidly increasing. According to the technical development, product performance and reliability of more than certain standards are recognized as basal conditions of market entry. And design and usability of products and subjective satisfaction are being magnified as the success factors of products. As functional performance including maximum speed, horsepower, and mileage reaches the satisfactory level in the automobile industry, consumers think the emotional aspects of the exterior and interior decor of automobiles as important. An analysis of customers' sensibility and preferences is an important business strategy in the automobile industry that is increasingly becoming more customer oriented. In this paper, we proposed the discovery of automotive design paradigm using the relevance feedback. The proposed method applies a method that supports automotive design using the image-based collaborative filtering utilizing sensibility as a starting point in the development process. Although a collaborative filtering process can well predict the users' interests and preferences, it cannot efficiently analyze design information while considering the contents of specific contents. The process extracts features from the image data that the users are interested to mitigate a problem, which is regarded as an undulated analysis, and then recommends an automotive design by combining the image filtering and collaborative filtering that use the static relationship between the users' preference and the image color information. The proposed automotive design paradigm prediction system provides a recommendation by the image-based collaborative filtering. Paradigm recommendation according to sensibility and tendency is possible by applying the relevance feedback to react the paradigm which changes according to various lifestyles. Ultimately, this paper suggests empirical applications to verify the adequacy and validity of this system.

Color image processing with multi-peak resonant tunneling diodes

The article introduces a novel approach to color image processing that utilizes multi-peak resonant tunneling diodes for encoding color information in quantized states of the diodes. The Multi-Peak Resonant Tunneling Diodes (MPRTDs) are organized as a two-dimensional array of vertical pillars which are locally connected by programmable passive and active elements with a view to realizing a wide variety of color image processing functions such as quantization, color extraction, image smoothing, edge detection, and line detection. In order to process color information in the input images, two different methods for color representation schemes have been used: one using color mapping and the other using direct RGB representation. Finally, the article uses HSPICE simulation methods for the nestlist of the proposed RTD-based nanoarchitecture in order to verify a candidate of image functions by using the afore-mentioned representation methods.

20Clustered Domain Colors and Bag of Words Algorithm Based Image Retrieval

Bag of words algorithm is an efficient object recognition algorithm based on semantic features extraction and expression. It learns the virtues of the text-based search algorithm to make images a range of visual words, extract the semantic characters and carry out the detection and recognition of interesting objects. Bag of words algorithm is extracted from gray images and discard s color information of images. We propose in this paper a method of image retrieval based on clustered domain colors and bag of words algorithm. The results of experiments show that this method can improve the precision of retrieval efficiently.

Feature Extraction Based on Color Difference Algorithm for Moving Target Detection System

To improve the accuracy and robustness of the moving object detection in the image sequence, the author improves the traditional algorithm which is based on the gray-value difference. The author makes good use of the color information of images and applies the pixels in red, green, blue the three component value as its identifying information. According to the background image color composition, it adapts and adjusts the proportion of the three groups. Dynamic threshold is used to do the binarization separation of the background difference image. The simulation experiment shows, this algorithm makes full use of the color features of image and achieve the expected goal of high recognizability and good robustness.

Depth map misalignment correction and dilation for DIBR view synthesis

The quality of the synthesized views by Depth Image Based Rendering (DIBR) highly depends on the accuracy of the depth map, especially the alignment of object boundaries of texture image. In practice, the misalignment of sharp depth map edges is the major cause of the annoying artifacts at the disoccluded regions of the synthesized views. Conventional smooth filter approach blurs the depth map to reduce the disoccluded regions. The drawbacks are the degradation of 3D perception of the reconstructed 3D videos and the destruction of the texture in background regions. Conventional edge preserving filter utilizes the color image information in order to align the depth edges with color edges. Unfortunately, the characteristics of color edges and depth edges are very different which causes annoying boundaries artifacts in the synthesized virtual views. Recent solution of reliability-based approach uses reliable warping information from other views to fill the holes. However, it is not suitable for the view synthesis in video-plus-depth based DIBR applications. In this paper, a new depth map preprocessing approach is proposed. It utilizes Watershed color segmentation method to correct the depth map misalignment and then the depth map object boundaries are extended to cover the transitional edge regions of color image. This approach can handle the sharp depth map edges lying inside or outside the object boundaries in 2D sense. The quality of the disoccluded regions of the synthesized views can be significantly improved and unknown depth values can also be estimated. Experimental results show that the proposed method achieves superior performance for view synthesis by DIBR especially for generating large baseline virtual views.