Color Image Segmentation Problem Research Articles

Color and Texture Segmentation Using an Unified MRF Model

The color image segmentation problem has two main issues to be solved. The proper choice of a color model and the choice of an appropriate image model are the key issues in color image segmentation. In this work, Ohta (I1, I2, I3) is taken as the color model and different variants of Markov Random Field (MRF) models are proposed. In this regard, a Compound Markov Random Field (COMRF) model is porposed to take care of inter-color-plane and intra-color-plane interactions as well. In continuation to this model, a Constrained Compound Markov Random Field Model (CCOMRF) has been proposed to model the color images. The color image segmentation problem has been formulated in an unsupervised framework. The performance of the above proposed models has been compared with the standard MRF model and some of the state-of-the-art methods, and found to exhibit improved performance.

Unsupervised color image segmentation: A case of RGB histogram based K-means clustering initialization.

Color-based image segmentation classifies pixels of digital images in numerous groups for further analysis in computer vision, pattern recognition, image understanding, and image processing applications. Various algorithms have been developed for image segmentation, but clustering algorithms play an important role in the segmentation of digital images. This paper presents a novel and adaptive initialization approach to determine the number of clusters and find the initial central points of clusters for the standard K-means algorithm to solve the segmentation problem of color images. The presented scheme uses a scanning procedure of the paired Red, Green, and Blue (RGB) color-channel histograms for determining the most salient modes in every histogram. Next, the histogram thresholding is applied and a search in every histogram mode is performed to accomplish RGB pairs. These RGB pairs are used as the initial cluster centers and cluster numbers that clustered each pixel into the appropriate region for generating the homogeneous regions. The proposed technique determines the best initialization parameters for the conventional K-means clustering technique. In this paper, the proposed approach was compared with various unsupervised image segmentation techniques on various image segmentation benchmarks. Furthermore, we made use of a ranking approach inspired by the Evaluation Based on Distance from Average Solution (EDAS) method to account for segmentation integrity. The experimental results show that the proposed technique outperforms the other existing clustering techniques by optimizing the segmentation quality and possibly reducing the classification error.

An efficient optimal multilevel image thresholding with electromagnetism-like mechanism

Segmentation process is considered a major part of various image-processing applications due to its extreme inspiration on the subsequent image analysis. Thresholding is one of the simplest techniques for segmentation. In this paper, Renyi’s entropy is combined with electromagnetism-like mechanism optimization (EMO) to perform multilevel thresholding based color image segmentation. For statistical independent subsystems, Renyi’s entropy shows an extensive property and is applied to find best threshold value for image segmentation. The entropic parameter α can handle the additive information that is existent in the image. The feasibility of the EMO-Renyi’s based approach has been tested on various satellite and standard color images with bat algorithm (BAT), backtracking search algorithm (BSA), firefly algorithm (FA), particle swarm optimization (PSO), and wind driven optimization (WDO) for solving the multilevel color image thresholding problem. The analysis based on statistics of different optimization algorithms indicates the proposed EMO-Renyi’s algorithm to be more robust and precise for multilevel color image segmentation problem. These claims have been confirmed by comparing fidelity parameters such as mean error (ME), mean squared error (MSE), peak signal-to-noise ratio (PSNR), feature similarity index (FSIM), structure similarity index (SSIM) and entropy. Experiments on standard daily-life color images are conducted to prove the effectiveness of the proposed scheme. The results show that the proposed method can produce more promising segmentation results from the aspect of objective and subjective observations.

Oppositional symbiotic organisms search optimization for multilevel thresholding of color image

Selection of optimal threshold is the most crucial issue in threshold-based segmentation. In case of color image, this task is become challenging, because conventional color image segmentation has computational complexity and also it suffers from lack of accuracy. Various techniques such as threshold based, region growing, edge detection, graph cut, pixel classification, neural network, active contour, gray level co-occurrence matrix are proposed so far for image segmentation in the literature. Out of them, threshold-based segmentation is popular for its simplicity. To address the problem of color image segmentation, we propose an enhanced version of metaheuristic optimization algorithm called Opposition based Symbiotic Organisms Search (OSOS) to solve multilevel image thresholding technique for color image segmentation by introducing opposition based learning concepts to accelerate the convergence rate and enhance the performance of standard symbiotic organisms search (SOS). The performance of the proposed OSOS based algorithm is investigated thoroughly and compared with some existing techniques like Cuckoo Search (CS), BAT algorithm (BAT), artificial bee colony (ABC) and particle swarm optimization (PSO). The comparison is made by applying the algorithm to a set of color images taken from a well-known benchmark dataset (Berkeley Segmentation Dataset (BSDS)) and some of the color images collected for the COCO dataset. It is observed from the results that the performance of the OSOS based algorithm is promising with respect to standards SOS and others in terms of the values of objective functions as well as the values of some well-defined quality metrics such as peak signal-to-noise ratio (PSNR), structure similarity index (SSIM) and feature similarity index (FSIM). The results of the proposed algorithm may encourage the scientists and engineers to apply it into pattern recognition problems.

Global biotic cross-pollination algorithm enhanced with evolutionary strategies for color image segmentation

Object segmentation is a prominent and challenging issue pertaining to image analysis and computer vision applications. This segmentation enables a higher number of applications like image retrieval, object recognition and object reconstruction. Considering this importance of object segmentation, the ultimate aim of the proposed research work in this paper is to focus on color image segmentation that is visually triggered using the GBCPA, popularly known as global biotic cross-pollination algorithm dependent on evolutionary strategy models. Evolutionary techniques imitate the procedure of genetic evolution and make utilization of the operators of recombination, mutation and selection to create the new-generation individuals. The new flower pollination optimization algorithm (FPOA) proposed in this paper aims to improve the objective characteristics of the basic FPOA approach. The significant contribution here mainly focused on preventing the premature convergence for dealing with the complicated constraints of the color image segmentation problem. The performance of GBCPA is tested over a Gould segmentation data set comprising of 715 images, both urban and rural images. The data set is tested under various evaluation techniques, and the proposed algorithm results in better accuracy than the other methods considered in comparison with the existing literature.

Human Pose Estimation in Images and Videos

Estimation of human poses is an interesting and challenging topic in the field of Computer vision. It includes some un-noticed challenges like background effect, the color of the dress, skin tones and many other unpredictable challenges. This is a workable concept because it can be used in sign language recognition, correlating various pose styles from different parts of the world and in medical applications. A deep structure which can represent a man’s body in different models will help in improved recognition of body parts and the spatial correlation between them. For hand detection, features based on hand shape and representation of geometrical details are derived with the help of hand contour. An adaptive and unsupervised approach based on Voronoi region is primarily used for the color image segmentation problem. This process includes identification of key points of the body, which may include body joints and parts. The identification parts will be tough due to small joints and occlusions. Identification of Image features is described in this paper with the help of Box Model Based Estimation, Speed up robust features and finally with Optical flow tracking algorithm. In Optical flow tracking algorithm, we have used Horn-Schunk algorithm to determine featural changes in the images.

Voronoï region-based adaptive unsupervised color image segmentation

Color image segmentation is a crucial step in many computer vision and pattern recognition applications. This paper introduces an adaptive and unsupervised approach based on Voronoï regions to solve the color image segmentation problem. The proposed method uses a hybrid of spatial and feature space Dirichlet tessellation followed by inter-Voronoï region proximal cluster merging to automatically find the number of clusters and cluster centroids in an image. Since, the Voronoï regions are much smaller compared to the whole image, Voronoï region-wise clustering improves the efficiency and accuracy of the number of clusters and cluster centroid estimation process. The proposed method was compared with four other adaptive unsupervised cluster-based image segmentation algorithms on three image segmentation evaluation benchmarks. The experimental results reported in this paper confirm that the proposed method outperforms the existing algorithms in terms of the image segmentation quality and results in much lower average execution time per image.

Hybridizing Differential Evolution with a Genetic Algorithm for Color Image Segmentation

This paper proposes a hybrid of differential evolution and genetic algorithms to solve the color image segmentation problem. Clustering based color image segmentation algorithms segment an image by clustering the features of color and texture, thereby obtaining accurate prototype cluster centers. In the proposed algorithm, the color features are obtained using the homogeneity model. A new texture feature named Power Law Descriptor (PLD) which is a modification of Weber Local Descriptor (WLD) is proposed and further used as a texture feature for clustering. Genetic algorithms are competent in handling binary variables, while differential evolution on the other hand is more efficient in handling real parameters. The obtained texture feature is binary in nature and the color feature is a real value, which suits very well the hybrid cluster center optimization problem in image segmentation. Thus in the proposed algorithm, the optimum texture feature centers are evolved using genetic algorithms, whereas the optimum color feature centers are evolved using differential evolution.

A novel color image multilevel thresholding based segmentation using nature inspired optimization algorithms

Multilevel thresholding for segmentation is an essential task and indispensable process in various applications. Conventional color multilevel thresholding based image segmentations are computationally expensive, and lack accuracy and stability. To address this issue, this paper introduces the comparative performance study of different objective functions using cuckoo search and other optimization algorithms to solve the color image segmentation problem via multilevel thresholding. During the optimization process, solutions are evaluated using Otsu or Kapur's method. Performance of the proposed approach has been assessed using a variety of benchmark images, and compared against three other nature inspired algorithms namely differential evolution (DE), wind driven optimization (WDO) and particle swam optimization (PSO) algorithms. Results have been analyzed both qualitatively and quantitatively, based on the fitness values of obtained best solutions and four popular performance measures namely PSNR, MSE, SSIM and FSIM indices as well. According to statistical analysis of different nature inspired optimization algorithms, Kapur's entropy was found to be more accurate and robust for multilevel colored satellite image segmentation problem. On the other hand, cuckoo search was found to be most promising for colored satellite image segmentation.

Block-based illumination-invariant representation for color images

Abstract Reflection effects such as shading, gloss, and highlight affect the appearance of color images greatly. Therefore, image representations invariant to these effects were proposed for color images. Most of the conventional invariant methods used the dichromatic reflection model assuming the presence of dielectric material in the captured image. Recently, a pixel-based invariant representation for color images, assuming that the image includes dielectric materials and metals, was introduced. However, the pixel-based representation was noisy and did not have sharp edges. This paper proposes a block-based illumination-invariant representation for color images including dielectric materials and metals. The proposed algorithm divides image into sub-blocks and applies the invariant equations within each block. Experiments show that the proposed algorithm has clear and sharp edges over the pixel-based algorithm. The results show the performance and stability of the proposed algorithm. As an application, the proposed invariant method is applied to color image segmentation problem.

Genetic algorithm and self organizing map based fuzzy hybrid intelligent method for color image segmentation

The grouping of pixels based on some similarity criteria is called image segmentation. In this paper the problem of color image segmentation is considered as a clustering problem and a fixed length genetic algorithm (GA) is used to handle it. The effectiveness of GA depends on the objective function (fitness function) and the initialization of the population. A new objective function is proposed to evaluate the quality of the segmentation and the fitness of a chromosome. In fixed length genetic algorithm the chromosomes have same length, which is normally set by the user. Here, a self organizing map (SOM) is used to determine the number of segments in order to set the length of a chromosome automatically. An opposition based strategy is adopted for the initialization of the population in order to diversify the search process. In some cases the proposed method makes the small regions of an image as separate segments, which leads to noisy segmentation. A simple ad hoc mechanism is devised to refine the noisy segmentation. The qualitative and quantitative results show that the proposed method performs better than the state-of-the-art methods.

Segmentation of color images using a linguistic 2-tuples model

In this paper we address the problem of color image segmentation transforming it into a decision making paradigm. A set of experts is provided, so that each expert assigns a preference degree of each pixel to every object of the image considering also the ignorance associated with such assignation. We represent the objects by means of fuzzy linguistic labels and using the decision-making model based on 2-tuples we apply an aggregation phase to classify each pixel. To obtain the segmented image we consider the preference values associated with a pixel and also with its neighbors. We test our segmentation method on Berkeley segmentation database [21] and we compare the experimental results with the ones obtained by FCM method [4] and MAP-ML method [17].

A Review: Color Image Segmentation Based on Color Space

Abstract: While the methods of gray image segmentation keeping innovation, researches on color image segmentation have a marked development, and the gray image segmentation provides research base for color image segmentation. At present, the problem of color image segmentation has become a fundamental one and had significant impact on both new pattern recognition algorithms and applications. In order to make the research in this field has a more comprehensive understanding, In this paper, several typical approaches are presented and discussed, and expected to seek an algorithm with better real-time and robustness. algorithm combining both SOFM and FCM clustering is selected to be better in robustness, and reduce the hassle of looking for a suitable feature space.

Image Segmentation using Learning Vector Quantization of Artificial Neural Network

This paper presents color image segmentation application for road-sign detection and recognition system based on Learning vector Quantization (LVQ). In traffic-sign maintenance and in a visual driver assistance system, road-sign detection and recognition are two of the most important functions. Our system is able to detect and recognize the signs. Road signs provide drivers important information and help them to drive more safely and more easily by guiding and warning them and thus regulating their actions. The RGB images are converted into HSV color space, and segmented using LVQ depending on the hue values of each pixel in the HSV color space. LVQ neural network is used to detect the color from the images and recognize them with high accuracy and speed. The detection and recognition of traffic signs represents an important issue in the field of traffic sign analysis. The paper researches the existing traffic sign detection and recognition methods. Special attention has been given to the methods based on artificial neural networks. Some techniques extracted various features from the images containing traffic signs and used various detectors and classifiers to perform detection and recognition. The following examples of these methods can be mentioned: Histogram of Oriented Gradient (2) or (1) and (6) or Support Vector Machines (SVM) (5). Some authors have also used artificial neural networks (4). This paper, however, uses a method of neural network (NN) which has given successful results. For individual object identification in humans, Color discrimination plays an important role. Image segmentation is the basic and first step regarding image analysis and pattern recognition. In image processing, image segmentation is not only the critical and essential component but also it is a very difficult task. The actual operation of the algorithm determines the accuracy and quality of image analysis. Color segmentation is a process of extracting one or more connected regions from the image domain. These connected regions are satisfying the uniformity (homogeneity) criterion which is derived from the spectral components. These components are then defined with respect to some color spaced model such as RGB model. RGB is the most common model. In RGB model, a color point is defined by the color components of the corresponding pixel which are defined in the form of Red (R), Green (G) and Blue (B). This paper considers a color image segmentation problem as a pixel classification problem. .

Color Image Segmentation Based on Dynamic Model and Power Spectrum

In this paper, the locally coupled neural oscillator model and power spectrum are introduced to solve the color image segmentation problem. Firstly the single neuron oscillator model is developed, the model parameter is set so as to create limit circle simulating the activity of neuron. Then the locally coupled network model is developed, taking R, G, Bas external input separately, the network output three dynamic orbits representing R, G, B for each image point. Lastly, the power spectrum of the orbits is calculated for each image point, the color image is segmented using the calculated power spectrum. The performance is comparable to the results from other segmentation methods.

一种基于数据竞争的高分辨率图像的聚类分割算法

In recent years, robot technology has been rapidly developed and applied to every walk of life. With the promotion and popularization of the robot technology, requirement of using robot is becoming high and the demand of intelligent robots is particularly urgent. Machine vision is an important research direction in the field of intelligent robotics. In the robot vision system, the core problem is the targets extraction, and the image segmentation is the key technique of extracting targets accurately, rapidly and in real-time. Since the environment is complex and the targets are diverse, the amount of images data perceived by robots is large and the images are unpredictable. Thus, it is very important to extract and segment targets accurately. Aimed at the segmentation processing of high-resolution images, a novel clustering algorithm is proposed in this paper. According to the sum of the energy of data and their sizes, it recognizes the clustering representatives and members, and identifies the most probability members by the competition among data points. Then we apply the algorithm by combining the novel clustering algorithm into Mean Shift clustering algorithm in color image segmentation problem. The algorithm can quickly and efficiently achieve the targets segmentation of high-resolution images, and has good segmentation effect. The experiments show that the proposed approach has better clustering quality and is faster than the traditional clustering algorithm.

Maximum weighted likelihood via rival penalized EM for density mixture clustering with automatic model selection

Expectation-maximization (EM) algorithm (A.P. Dempster et al., 1977) has been extensively used in density mixture clustering problems, but it is unable to-perform model selection automatically. This paper, therefore, proposes to learn the model parameters via maximizing a weighted likelihood. Under a specific weight design, we give out a rival penalized expectation-maximization (RPEM) algorithm, which makes the components in a density mixture compete each other at each time step. Not only are the associated parameters of the winner updated to adapt to an input, but also all rivals' parameters are penalized with the strength proportional to the corresponding posterior density probabilities. Compared to the EM algorithm (A.P. Dempster et al., 1977), the RPEM is able to fade out the redundant densities from a density mixture during the learning process. Hence, it can automatically select an appropriate number of densities in density mixture clustering. We experimentally demonstrate its outstanding performance on Gaussian mixtures and color image segmentation problem. Moreover, a simplified version of RPEM generalizes our recently proposed RPCCL algorithm (Y.M. Cheung, 2002) so that it is applicable to elliptical clusters as well with any input proportion. Compared to the existing heuristic RPCL (L. Xu et al., 1993) and its variants, this generalized RPCCL (G-RPCCL) circumvents the difficult preselection of the so-called delearning rate. Additionally, a special setting of the G-RPCCL not only degenerates to RPCL and its Type A variant, but also gives a guidance to choose an appropriate delearning rate for them. Subsequently, we propose a stochastic version of RPCL and its type A variant, respectively, in which the difficult selection problem of delearning rate has been novelly circumvented. The experiments show the promising results of this stochastic implementation.