Color Image Segmentation Research Articles

Segmentation of images by color features: A survey

Image segmentation is an important stage for object recognition. Many methods have been proposed in the last few years for grayscale and color images. In this paper, we present a deep review of the state of the art on color image segmentation methods; through this paper, we explain the techniques based on edge detection, thresholding, histogram-thresholding, region, feature clustering and neural networks. Because color spaces play a key role in the methods reviewed, we also explain in detail the most commonly color spaces to represent and process colors. In addition, we present some important applications that use the methods of image segmentation reviewed. Finally, a set of metrics frequently used to evaluate quantitatively the segmented images is shown.

Design and implementation of a multivalued quantum circuit for threshold based color image segmentation

Design and implementation of a multivalued quantum circuit for threshold based color image segmentation

A Novel Unsupervised Two‐Stage Technique in Color Image Segmentation

A new unsupervised two-stage method for color image segmentation is proposed. The method contains coarse segmentation and delicate segmentation. In coarse segmentation, we adaptively choose a gray channel from CIE-lab color space. The Otsu method combined with a refinement to its threshold is applied to get global optimal segmentation. In delicate segmentation, a narrowband based procedure is applied to get more accurate contour of the object and local optimal segmentation is achieved. Our method finally balance the global optimal and the local optimal. The proposed method does not need initial contours or initial labels, thus it is more robust in certain applications. Experimental results of our method in MSRA1000 database show that our method is robust in segmenting objects and backgrounds when possessing weakly heterogeneous color. Our method firstly achieves global optimal and then achieves local optimal which draws a new and prospective outlook for segmenting color images.

Bottom-Up Merging Segmentation for Color Images With Complex Areas

Most color images obtained from the real world usually contain complex areas, such as nature scene images, remote sensing images, and medical images. All these type of images are very difficult to be separated accurately and automatically for complex color and structures included. In this paper, we focus on detecting hybrid cues of color image to segment complex scene in a bottom-up framework. The main idea of the proposed segmentation method is based on a two-step procedure: 1) a reasonable superpixels computing method is conducted and 2) a Mumford–Shah (M–S) optimal merging model is proposed for presegment suerpixels. First, a set of seed pixels is positioned at the lowest texture energy map computed from structure tensor diffusion features. Next, we implement a growing procedure to extract superpixels from selected seed pixels with color and texture cues. After that, a color-texture histograms feature is defined to measure similarity between regions, and an M–S optimal merging process is executed by comparing the similarity of adjacent regions with standard deviation constraints to get final segmentation. Extensive experiments are conducted on the Berkeley segmentation database, some remote sensing images, and medical images. The results of experiments have verified that the segmentation effectiveness of the proposed method in segmenting complex scenes and indicated that it is more robust and accurate than conventional methods.

Pareto-based interval type-2 fuzzy c-means with multi-scale JND color histogram for image segmentation

Although the interval type-2 fuzzy c-means clustering algorithm (IT2FCM) can well represent the uncertainty in data, there remain some problems to be solved: how to initialize cluster centers and how to determine fuzzifiers. In order to solve these issues of IT2FCM for color image segmentation, a pareto-based interval type-2 fuzzy c-means with multi-scale just noticeable difference color histogram (PIT2FC-MJND) is proposed in this paper. A multi-scale just noticeable difference (JND) color histogram is firstly constructed by using many distance thresholds and utilized to provide initial cluster centers. Then, a modified type-reduction and de-fuzzification mechanism on this multi-scale JND color histogram is designed for updating membership functions and cluster centers. Moreover, a pareto-based strategy for determining the combination of fuzzifiers is presented by using a global fuzzy compactness function and a fuzzy separation function which are based on the constructed multi-scale JND color histogram. The experimental results on real, Berkeley and Weizmann Images confirm the validity of the proposed approach.

Segmentación de Imágenes Basada en Entropía de Pixel

In this research, a new methodology for color image segmentation is proposed. In this approach, a pixel entropy derivative based rule is used. The algorithm is tested not only with good quality images, but also with some of them with light scattering and absortion problems. Preliminary results shows good performance of this algorithm.Keywords: Image processing, segmentation, entropy, feedback.

An effective color image segmentation approach using neutrosophic adaptive mean shift clustering

Color image segmentation can be defined as dividing a color image into several disjoint, homogeneous, and meaningful regions based on the color information. This paper proposes an efficient segmentation algorithm for color images based on neutrosophic adaptive mean shift (NAMS) clustering. Firstly, an image is transformed in neutrosophic set and interpreted by three subsets: true, indeterminate, and false memberships. Then a filter is designed using indeterminacy membership value, and neighbors’ features are employed to alleviate indeterminacy degree of image. A new mean shift clustering, improved by neutrosophic set, is employed to categorize the pixels into different groups whose bandwidth is determined by the indeterminacy values adaptively. At last, the segmentation is achieved using the clustering results. Various experiments have been conducted to verify the performance of the proposed approach. A published method was then employed to take comparison with the NAMS on clean, low contrast, and noisy images, respectively. The results demonstrate the NAMS method achieves better performances on both clean image and low contrast and noisy images.

A Fast Color Image Segmentation Approach Using GDF with Improved Region-Level Ncut

Color image segmentation is fundamental in image processing and computer vision. A novel approach, GDF-Ncut, is proposed to segment color images by integrating generalized data field (GDF) and improved normalized cuts (Ncut). To start with, the hierarchy-grid structure is constructed in the color feature space of an image in an attempt to reduce the time complexity but preserve the quality of image segmentation. Then a fast hierarchy-grid clustering is performed under GDF potential estimation and therefore image pixels are merged into disjoint oversegmented but meaningful initial regions. Finally, these regions are presented as a weighted undirected graph, upon which Ncut algorithm merges homogenous initial regions to achieve final image segmentation. The use of the fast clustering improves the effectiveness of Ncut because regions-based graph is constructed instead of pixel-based graph. Meanwhile, during the processes of Ncut matrix computation, oversegmented regions are grouped into homogeneous parts for greatly ameliorating the intermediate problems from GDF and accordingly decreasing the sensitivity to noise. Experimental results on a variety of color images demonstrate that the proposed method significantly reduces the time complexity while partitioning image into meaningful and physically connected regions. The method is potentially beneficial to serve object extraction and pattern recognition.

Clustering-Based Color Image Segmentation Using Local Maxima

Color image segmentation has contributed significantly to image analysis and retrieval of relevant images. Color image segmentation helps the end user subdivide user input images into unique homogenous regions of similar pixels, based on pixel property. The success of image analysis is largely owing to the reliability of segmentation. The automatic segmentation of a color image into accurate regions without over-segmentation is a tedious task. Our paper focuses on segmenting color images automatically into multiple regions accurately, based on the local maxima of the GLCM texture property, with pixels spatially clustered into identical regions. A novel Clustering-based Image Segmentation using Local Maxima (CBIS-LM) method is presented. Our proposed approach generates reliable, accurate and non-overlapping multiple regions for the given user input image. The segmented regions can be automatically annotated with distinct labels which, in turn, help retrieve relevant images based on image semantics.

Length Measurement of Potato Leaf using Depth Camera

Leaf length is one of important parameters for crop growth estimation. In order to accurately obtain the plant leaf length, this paper proposes a slope linear hypothesis in which the leaf length could be measured in 3-D space with a right-angle model. A binocular stereo vision system was applied with RGB and depth image output. The projection of leaf could be obtained in RGB and depth image. The depth camera is used to obtain one right-angle side to correct the measurement result in RGB image. Four methods were present to compare the extract accuracy in the images. First, RGB images without leaf segmentation were used to extract leaf length (L1→) on the horizontal projection plane. Second, leaf length (L2→) were calculated with the right-angle model correction by depth image based on (L1→). Third, the preprocessing of RGB images was conducted with color image segmentation and morphological operation, then the leaf length (L3→) was extracted. Fourth, the correction leaf length (L4→) were obtained by depth image correction to L3→. Four prediction models were established to analyze L1→, L2→, L3→, and L4→ results. It is indicated that the prediction model based on the L2→ measurement has better performance, in which Rc2 is 0.7178 and Rv2 is 0.833.

Comparative analysis of two leading evolutionary intelligence approaches for multilevel thresholding

The rapid advance of artificial intelligence has made complex image processing in real time possible. Multilevel thresholding has become a feasible way for image segmentation, even in the presence of poor contrast and external artefacts. Genetic algorithms (GAs) and particle swarm optimisation (PSO) are broadly recognised by far to be two dominating schemes which outperform classical ones on multilevel thresholding. Qualitative analysis can usually be applied to observe their superiority to all classical approaches. However, no convincing result is reached with respect to differences in performance between GAs and PSO. The existing segmentation practices are either examined by visual appeals exclusively, or evaluated quantitatively assuming perfect statistical distributions. To make thorough comparisons, comparative analysis of two leading multilevel thresholding approaches is conducted for true colour image segmentation. The information theory is also employed to analyse the outcomes of systematic approaches using diverse quantitative metrics from various aspects.

An Image Segmentation Method for Global Vision Robot Fish Competition

Image segmentation is a key link of vision system of the global vision bionic robot fish, and a precondition of target localization and tracking. In this paper, we propose a visual threshold method for color image segmentation. Firstly, a visualization research on the R, G and B components in different regions of the image is carried out to find out the main factors, which influence the image segmentation effect, and then an image segmentation method is proposed based on R and B components. It is proved by experiments that the image segmentation method is simple and practical, which is more suitable for the image segmentation and target tracking in our test-bed than the Gaussian mixture model. The image segmentation method also provides reference for other fields.

Improved Unsupervised Color Segmentation Using a Modified HSV Color Model and a Bagging Procedure in K-Means++ Algorithm

Accurate color image segmentation has stayed as a relevant topic between the researches/scientific community due to the wide range of application areas such as medicine and agriculture. A major issue is the presence of illumination variations that obstruct precise segmentation. On the other hand, the machine learning unsupervised techniques have become attractive principally for the easy implementations. However, there is not an easy way to verify or ensure the accuracy of the unsupervised techniques; so these techniques could lead to an unknown result. This paper proposes an algorithm and a modification to the HSV color model in order to improve the accuracy of the results obtained from the color segmentation using the K-means++ algorithm. The proposal gives better segmentation and less erroneous color detections due to illumination conditions. This is achieved shifting the hue and rearranging the H equation in order to avoid undefined conditions and increase robustness in the color model.

Image Processing using Color Space Models for Forensic Fiber Detection

The purpose of this study is to investigate the feasibility of automating fiber analysis in forensic science applications. In order to make self-directed collection of spectral data possible the number of measuring locations needs to be restricted to fibers only. Full scans of the samples would result in very large amounts of data of which only a small part carries actual information about the objects of interest.Images obtained by optical microscopes are used for preprocessing to find suitable candidates for measuring locations that subsequently may be used to control the microscope stage for spectroscopic measurements. This paper presents a method based on a nonlinear transform known to enhance the contrast in a way that makes segmentation on grayscale images possible. It further introduces an approach using the differences between the color channels of RGB images combined with common morphological operators to segment color images. A third application is presented that enables the search for fibers matching a query object in color based attributes, for which it is necessary to consider multiple color models. This approach reduces time and efforts significantly when trying to match one specific fiber to other samples.

A new method for building adaptive Bayesian trees and its application in color image segmentation

This paper presents a novel non-supervised clustering method based on adaptive Bayesian trees (ABT). A Bayesian framework is proposed for seeking modes of the underlying discrete distribution of the input data, and the data is represented by hierarchical clusters found using the adaptive Bayesian trees approach. The application of the proposed clustering technique to color image segmentation is investigated, exploring the inherent hierarchical tree structure of the proposed approach to represent color images hierarchically. The experimental results with the BSD300 dataset and 21 comparative methods that are representative of the art suggest that the proposed ABT clustering scheme potentially can be more reliable for segmenting color images than the comparative approaches. The proposed ABT approach achieved an average PRI value of 0.8148 and an average GCE value of 0.1701, suggesting that potentially the proposed scheme can improve over the comparative methods results. Also, the visual evaluation of the results confirm the competitiveness of the proposed approach. Other applications of the ABT clustering scheme in computer vision and pattern recognition currently are under investigation.

Color Image Segmentation Using Fuzzy Clustering and Fusion: Application to Biomedical Images

Color Image Segmentation Using Fuzzy Clustering and Fusion: Application to Biomedical Images

Color Image Edge Detection Based on Fuzzy Rule Based Approach

Edge detection method is one of the important techniques in Image Segmentation, which is used to find out the objects in the input image in exact manner. An edge is the boundary between an object and background and it indicates the boundary between overlapping objects. One of the most commonly used operation analysis is edge detection, which is used for enhancing and detecting edges in the image. It removes useless data, noise and frequencies while preserving the important structural properties in an image. Fuzzy Logic techniques have been used in image understanding applications such as detection of edges, feature extraction, classification, and clustering. Fuzzy logic possess the ability to mimic the human mind to employ modes of reasoning that are approximate rather than exact form effectively. Edge detection in gray images has lot of methods to locate edges and it has several set of algorithms to represent it. But the images produce more information in scenes i.e., color images have few numbers of methods to segment it. So, this paper represent color image segmentation methods in the literature and getting to prepare novel segmentation method by extracting the color channels in the RGB image with combined form of masking, filtering and Thresholding methods. This paper discuss about RGB color model and fuzzy membership functions method and particularly explain about the usage of fuzzy membership functions which are used to create different combination of mask with some sort of rules based on RGB channel extraction to scan the separated channel image and include Threshold and filtering concepts for further to produce the output image in well enhanced way.

A Fuzzy Clustering Approach for Complex Color Image Segmentation Based on Gaussian Model with Interactions between Color Planes and Mixture Gaussian Model

In complex color images, colors inside a homogeneous region might be contradistinctive and the distribution could not be described by a simple Gaussian distribution as used in traditional image segmentation algorithms. Based on the characteristics that the red, green, and blue color planes are not independent and pixels in the same neighborhood system might stand for the same object, we introduce a Gaussian model containing the interactions between different color planes to strengthen the connections both on a color plane and between color planes in a neighborhood system. Consequently, a Gaussian mixture model with the prior distribution, defined by Markov random field and acting as the weight, is employed to describe the distribution of color measures inside a homogeneous region. With the Gaussian mixture model containing the interactions between color planes, we proposed a fuzzy clustering approach for complex color image segmentation. Experiments on synthetic and real-color images, in which homogeneous regions are complex, show that the proposed algorithm compares favorably with the compared algorithms developed for the same purpose.

Implementation Segmentation of Color Image with Detection of Color to Detect Object

Detection of objects in an image 2 dimensional is a process which is quite complex to do. Object detection required a computer vision approach to the desired part of the object can be recognizable computer accurately. The method in this research using waterfall method. This research will describe the application of color segmentation method with the color detection of a digital image to produce image segment object in the form of blob so that the computer can be detected. The object detection process will process the resulting color segment by the process of segmentation so that can know the number of detected objects, the area and the center of the object. This application can take pictures with laptop or notebook webcam. The result of color segmentation based on color detection is strongly influenced by color samples and color tolerance values to which the segmentation process is based. Lighting, location, texture, and contour of objects or background image will greatly affect the results of segmentation and object detection.

Angle-based twin parametric-margin support vector machine for pattern classification

In this paper, a novel angle-based twin parametric-margin support vector machine (ATP-SVM) is proposed, which can efficiently handle heteroscedastic noise. Taking motivation from twin parametric-margin support vector machine (TPMSVM), ATP-SVM determines two nonparallel parametric-margin hyperplanes, such that the angle between their normal is maximized. Unlike TPMSVM, it solves only one modified quadratic programming problem (QPP) with fewer number of representative samples. Further, it avoids the explicit computation of inverse of matrices in the dual and has efficient learning time as compared to other single problem classifiers like nonparallel SVM based on one optimization problem (NSVMOOP).The efficacy of ATP-SVM is tested by conducting experiments on a wide range of benchmark UCI datasets. ATP-SVM is extended for multi-category classification using state-of-the-art one-against-all (OAA) and binary tree (BT) based multi-category classification approaches. This work also proposes the application of ATP-SVM for segmentation of color images.