Color image segmentation using feedforward neural networks with FCM

Image segmentation is critical to image processing and pattern recognition. Basically, color image segmentation techniques are based on monochrome ones operating in different color spaces. A color image segmentation method in the RGB color space is reported in the paper, the image segmentation is used in the image about the disease spot and the normal spot of cucumber in the greenhouse, we determine the RGB threshold value, through counting the characteristic parameter of stochastic picture element in the different image spot. The combined methods of the main factor three threshold value R, G B decide the division. this method not only retain the image real color, but also have very good division effect.

The study of medical image analysis encompasses the various techniques for acquisition of images of biological structures pertaining to human body using radiations in different frequency ranges. The advancements in medical imaging over the past decades are enabling physicians to non-invasively peer inside the human body for the purpose of diagnosis and therapy. In this chapter, the objective is to focus on the studies relating to the analysis of endoscopic images of lower esophagus for abnormal region detection and identification of cancerous growth. Several color image segmentation techniques have been developed for automatic detection of cancerous regions in endoscopic images, which assists the physician for faster, proper diagnosis and treatment of the disease. These segmentation methods are evaluated for comparing their performances in different color spaces, namely, RGB, HSI, YCbCr, HSV, and CIE Lab. The segmented images are expected to assist the medical expert in drawing the biopsy samples precisely from the detected pathological legions. Further, various methods have been proposed for segmentation and classification of squamous cell carcinoma (SCC) from color microscopic images of esophagus tissue during pathological investigation. The efficacy of these methods has been demonstrated experimentally with endoscopic and microscopic image set and compared with manual segmentation done by medical experts. It is envisaged that the research in this direction eventually leads to the design and production of efficient intelligent computer vision systems for assisting the medical experts in their task of speedy accurate diagnosis of diseases and prescription of appropriate treatment of the patients.

segmentation divides an image into several constituent components such as color, structure, shape, and texture. It forms a major research topic for many image processing researchers as the applications are endless. Its applications include image enhancement, object detection, image retrieval, image compression, and medical image processing to name a few. The segmentation of color images is necessary for efficient pattern recognition and feature extraction involving various color spaces such as RGB, HSV and CIE L*A*B*, etc. This paper describes the different cluster based segmentation techniques used for segmenting the different color images and the resultant is analyzed with subjective and objective measures. Initially, registered color images are considered as input. Then the cluster based segmentation techniques namely K-Means clustering, Pillar-Kmeans clustering and Fuzzy C-means (FCM) clustering techniques are applied. Further, the segmented image is analyzed with measures such as compactness and execution time. From the experimental results, it has been observed that K-means and Pillar-Kmeans are the most suitable techniques for RGB, HSV and LAB color spaces than the FCM technique.

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.

The segmentation of acne vulgaris lesions is a crucial step for the classification and developing a severity assessment system. In this paper, an unsupervised technique is proposed for the segmentation of acne vulgaris lesions. The effect of color feature normalization on segmentation results is examined. Two types of normalization is performed — in the first type, the color feature values are restricted to the range [0 1] and in the second type, the color features are normalized such that their mean value is zero and their variance is one. The segmentation of acne lesions was carried out in the feature set formed by combining chromatic components from different color spaces such as YIQ, Lab, I1I2I3 and YCbCr. A dataset of fifty color images of acne patients have been used in this experimentation. The segmentation results show that normalization can significantly improve the segmentation results in YIQ and I1I2I3 color spaces. It has also found that comparatively good segmentation results can be obtained in high dimensional chromatic space.

In this paper, an unsupervised segmentation method using clustering is presented for color images. We propose to use a neural network based approach to automatic feature selection to achieve adaptive segmentation of color images. With a self-organizing feature map (SOFM), multiple color features can be analyzed, and the useful feature sequence (feature vector) can then be determined. The encoded feature vector is used in the final segmentation using fuzzy clustering. The proposed method has been applied in segmenting different types of color images, and the experimental results show that it outperforms the classical clustering method. Our study shows that the feature encoding approach offers great promise in automating and optimizing the segmentation of color images.

This paper proposes unsupervised perceptual segmentation of natural color images using a fuzzy-based hierarchical algorithm. L*a*b* color space is used to represent color features and statistical geometrical features are adopted as texture features. A fuzzy-based homogeneity measure makes a fusion of color features and texture features. Proposed hierarchical segmentation method is performed in four stages: simple splitting, local merging, global merging and boundary refinement. Experiments on segmentation of natural color images are presented to verify the effectiveness of the proposed method in obtaining perceptual segmentation.

Automatic modulation classification based on the combination of clustering and neural network

A Hybrid Technique for Color Image Segmentation: Application to the Fire Forest Images

In this article, we present an adaptive color similarity function defined in a modified hue‐saturation‐intensity color space, which can be used directly as a metric to obtain pixel‐wise segmentation of color images among other applications. The color information of every pixel is integrated as a unit by an adaptive similarity function thus avoiding color information scattering. As a direct application we present an efficient interactive, supervised color segmentation method with linear complexity respect to the number of pixels of the input image. The process has three steps: (1) Manual selection of few pixels in a sample of the color to be segmented. (2) Automatic generation of the so called color similarity image (CSI), which is a gray level image with all the gray level tonalities associated with the selected color. (3) Automatic threshold of the CSI to obtain the final segmentation. The proposed technique is direct, simple and computationally inexpensive. The evaluation of the efficiency of the color segmentation method is presented showing good performance in all cases of study. A comparative study is made between the behavior of the proposed method and two comparable segmentation techniques in color images using (1) the Euclidean metric of thea* andb* color channels rejectingL* and (2) a probabilistic approach ona* andb* in the CIE L*a*b* color space. Our testing system can be used either to explore the behavior of a similarity function (or metric) in different color spaces or to explore different metrics (or similarity functions) in the same color space. It was obtained from the results that the color parametersa* andb* are not independent of the luminance parameterL* as one might initially assume in the CIE L*a*b* color space. We show that our solution improves the quality of the proposed color segmentation technique and its quick result is significant with respect to other solutions found in the literature. The method also gives a good performance in low chromaticity, gray level and low contrast images. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 156–172, 2017

A two-layer dendritic lattice neural network is proposed to segment color images in the Red-Green-Blue (RGB) color space. The two layer neural network is a fully interconnected feed forward net consisting of an input layer that receives color pixel values, an intermediate layer that computes pixel interdistances, and an output layer used to classify colors by hetero-association. The two-layer net is first initialized with a finite small subset of the colors present in the input image. These colors are obtained by means of an automatic clustering procedure such as k-means or fuzzy c-means. In the second stage, the color image is scanned on a pixel by pixel basis where each picture element is treated as a vector and feeded into the network. For illustration purposes we use public domain color images to show the performance of our proposed image segmentation technique.

A new method of Modulation Recognition of communication signals is proposed based on Clustering Validity Indices. These indices provide a good basis for key feature extraction. To distinguish different modulation schemes, a Fuzzy C-mean (FCM) clustering is used to get the membership matrix of different clusters. Then, a clustering validity measure is applied to extract features. To enhance clustering results at low SNR, a neural network with a conjugate gradient learning algorithm is utilized. Fletcher-Reeves learning approach enhances the recognition rate and widely improves the speed and rate of convergence. Simulation results show the validity of proposed approach compared with other approaches using only clustering or using back propagation neural networks. Misclassification rate is less for low order MQAM signals. This algorithm is applicable in high order MQAM signals. In Non-cooperative Communications, the modulated signal parameters are unknown. Some Modulation Recognition algorithms rely on estimating these parameters first, then applying recognition algorithms. Proposed algorithm doesn't need any prior information to achieve modulation recognition.

Color texture segmentation based on image pixel classification

In this paper, we introduce improved segmentation method for segmenting breast MRI images using Kernelized Fuzzy C-Means and Support Vector Machine. Firstly, the new modified Kernelized FCM is constructed in this paper with inclusion of spatial neighborhood term. Then, the data are labeled by new FCM and the input vector for SVM classifier is generated by membership function of proposed new FCM. The robust SVM is proposed for providing effective segmentation result. In both KFCM and SVM, to enlighten the performance of dealing non linearity, the new Quadratic kernel function is used. In order to show the effectiveness of the proposed method, the experimental work is executed on artificially generated random data, and real dynamic contrast enhanced breast MRIs. The superiority of proposed method is proven by comparative analysis of result of proposed and existed methods. To work up the comparative analysis, Fuzzy Partition coefficient, Fuzzy Entropy and Silhouette method are utilized as a cluster validity measure in this paper. Finally, the experimental study shows our proposed method is promising method for segmenting medical images and complex data analysis.

Image segmentation is the process of dividing an image into homogenous regions. It is an essential step towards high-level image processing task such as image analysis, pattern recognition and computer vision. Processing of color images has become an important issue due to its huge usage in computer vision applications. It is observed that most of the color image segmentation techniques are derived from monochrome image segmentation. The techniques for segmentation of monochrome images are based on the principles of histogram thresholding, edge detection, region growing etc. Many color image segmentation algorithms using different color models and these principles are proposed. Extraction of objects within an image without a prior knowledge is one of the important issues in segmentation area. Novel approaches such as fuzzy set theory, neural network and neuro-fuzzy based segmentation are coming up to tackle this problem. This paper is an endeavor to review various algorithms and recent advances in color image segmentation.