Color image segmentation: a review

The topic of colour image segmentation has been and still is a hot issue in areas such as computer vision and image processing because of its wide range of practical applications. The urge has led to the development of numerous colour image segmentation algorithms to extract salient objects from colour images. However, because of the diverse imaging conditions in varying application domains, accuracy and robustness of several state-of-the-art colour image segmentation algorithms still leave room for further improvement. This dissertation reports on the development of a new image segmentation algorithm based on perceptual colour difference saliency along with binary morphological operations. The algorithm consists of four essential processing stages which are colour image transformation, luminance image enhancement, salient pixel computation and image artefact filtering. The input RGB colour image is first transformed into the CIE L*a*b colour image to achieve perceptual saliency and obtain the best possible calibration of the transformation model. The luminance channel of the transformed colour image is then enhanced using an adaptive gamma correction function to alleviate the adverse effects of illumination variation, low contrast and improve the image quality significantly. The salient objects in the input colour image are then determined by calculating saliency at each pixel in order to preserve spatial information. The computed saliency map is then filtered using the morphological operations to eliminate undesired factors that are likely present in the colour image. A series of experiments was performed to evaluate the effectiveness of the new perceptual colour difference saliency algorithm for colour image segmentation. This was accomplished by testing the algorithm on a large set of a hundred and ninety images acquired from four distinct publicly available benchmarks corporal. The accuracy of the developed colour image segmentation algorithm was quantified using four widely used statistical evaluation metrics in terms of precision, F-measure, error and Dice. Promising results were obtained despite the fact that the experimental images were selected from four different corporal and in varying imaging conditions. The results have indeed demonstrated that the performance of the newly developed colour image segmentation algorithm is consistent with an improved performance compared to a number of other saliency and non- saliency state-of-the-art image segmentation algorithms.

Segmentation is a low-level processing aimed at the partition of an image in disjoint regions, each one homogeneous with respect to some properties like intensity, texture, shape, etc. Such a task is needed in many high-level processing and applications in such diverse fields as remote-sensing, medical imaging, video coding, and industrial automation, just to name a few. In this work of thesis, we first deal with the problem of color based image segmentation, that is based on some form of homogeneity in the color/spectral properties of the image, and then move to the more complex task of texture based segmentation, where the aim is to recognize complex structures in the image which are typically non homogeneous in terms of spectral properties. Concerning color based segmentation, we focus on a specific class of Markov Random Field (MRF) probability models, namely the Tree-Structured Markov Random Fields (TS-MRF), recently proposed to provide a hierarchical multiscale description of images. Based on such a model, the unsupervised image segmentation is carried out by means of a sequence of nested class splits, where each class is modeled as a local binary MRF. As a first contribution, we first extend the model to generic tree structures removing the unnecessary binary constraint, and then devise a new TS-MRF unsupervised segmentation technique which improves upon the original algorithm by selecting a better tree structure and eliminating spurious classes. Such results are obtained by using the Mean-Shift procedure to estimate the number of pdf modes at each node, and to obtain a more reliable initial clustering for subsequent MRF optimization. To this end, we devise a new reliable and fast clustering algorithm based on the Mean-Shift technique, which makes use of a variable-bandwidth strategy based on the k-Nearest Neighbors (k-NN) technique, and is implemented with a speed-up strategy that cuts significantly the computational complexity. Experimental results on synthetic data and real life images from the remote sensing domain prove the potential of the proposed method. Turning to texture based segmentation, we present a novel multiscale texture model, and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled in turn by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC). The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmentation problem based on the H-MMC model. The ``fragmentation'' step allows one to find the elementary textures of the model, while the ``reconstruction'' step defines the hierarchical image segmentation based on a probabilistic measure (texture score) which takes into account both region scale and inter-region interactions. The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural images from the Berkeley dataset. Finally, an application of the TFR algorithm for the unsupervised segmentation of multiresolution remotely sensed images is proposed, based on the significant presence of textural content in last generation high-resolution satellite images. The obtained results further assess the potential of the proposed method for such real life applications.

This paper describes an efficient algorithm for color image segmentation based on a multiresolution application of a wavelet transform and watershed segmentation algorithm. The procedure toward complete segmentation consists of four steps: pyramid representation, image segmentation, region projection and region merging. First, pyramid representation creates multiresolution images using a wavelet transform. Second, image segmentation segments the lowest-resolution image of the pyramid using a watershed segmentation algorithm. Third, the segmented low-resolution image with label is projected into a full-resolution image (original image) by inverse wavelet transform. Finally, region merging merges the segmented regions using fuzzy similarity. Experimental results of the presented method can be applied to the segmentation of noise or degraded images as well as reduce over-segmentation.

This paper presents a color recognition and segmentation of color image through a combination of a multi-scale fuzzy system, an image edge based on Prewitt operator and morphological operators. In the proposed algorithm, after converting image from RGB color space to hue-saturation-value (HSV) color space, different scales of fuzzy sets in hue channel is constructed according to the people's psychological cognition to color. The image color would be quickly recognized fuzzily as less than ten kinds on scale one. To improve the performance of the color recognition rate, recognized image need to be identified on scale two to distinguish different colors observed by human eyes with the same color scheme. Then, adopting Prewitt operator to extract image edge information and applying a sequence of some morphological operators to the edge image, completing the multi-scale segmentation of image with the integration of color and edge information. Finally, indicating its area and species of specific color. The proposed algorithm can automatically adjusted in the process of color recognition and segmentation of image, it achieves recognition and segmentation without supervision. The obtained result has a good consistency with man's subjective visual perception.

Multilevel thresholding segmentation of color images plays an important role in many fields. The pivotal procedure of this technique is determining the specific threshold of the images. In this paper, a hybrid preaching optimization algorithm (HPOA) for color image segmentation is proposed. Firstly, the evolutionary state strategy is adopted to evaluate the evolutionary factors in each iteration. With the introduction of the evolutionary state, the proposed algorithm has more balanced exploration-exploitation compared with the original POA. Secondly, in order to prevent premature convergence, a randomly occurring time-delay is introduced into HPOA in a distributed manner. The expression of the time-delay is inspired by particle swarm optimization and reflects the history of previous personal optimum and global optimum. To better verify the effectiveness of the proposed method, eight well-known benchmark functions are employed to evaluate HPOA. In the interim, seven state-of-the-art algorithms are utilized to compare with HPOA in the terms of accuracy, convergence, and statistical analysis. On this basis, an excellent multilevel thresholding image segmentation method is proposed in this paper. Finally, to further illustrate the potential, experiments are respectively conducted on three different groups of Berkeley images. The quality of a segmented image is evaluated by an array of metrics including feature similarity index (FSIM), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and Kapur entropy values. The experimental results reveal that the proposed method significantly outperforms other algorithms and has remarkable and promising performance for multilevel thresholding color image segmentation.

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.

본 논문에서는 새로운 주요객체 자동추출 알고리즘을 제안한다. 제안된 알고리즘은 크게 2단계 과정으로 요약될 수 있다. 1단계로 객체와 배경을 분리하는 영상분할 작업을 수행한다. 우선적으로 '인간은 3또는 4개의 주요 색상으로 축약하여 사물을 인식한다'는 연구 결과에 따라 K-means 알고리즘을 이용하여 3구역으로 분할하고, 분할된 영상 간 히스토그램 유사도를 계산하여 임계값 이상으로 유사하면 병합하는 과정을 수행한다. 2단계로 영상구도에 근거해 분할된 영상 중에 객체라고 지정하는 작업을 수행한다. 사람이 사진을 잘 찍기 위해서는 '주요객체의 위치를 영상구도에 맞추어 촬영하는 것이 바람직하다는 사실'에 근거하여 삼각구도를 바탕으로 가중치 마스크를 설계하여 객체위치를 역 추정하였다. 제안된 방법의 우수성을 보이기 위해 약 400개의 영상에 대해 실험하였으며, 최근에 발표된 KMCC, GBIS방법과도 비교하였다. A new algorithm for automatic extraction of interesting objects is proposed in this paper. The proposed algorithm can be summarized in two steps. First, segmentation of color image that split interesting objects and backgrounds is performed. According to the research stating, 'Humans perceive things by contracting color into three to four essential colors,' a color image is segmented into three regions utilizing k-mean algorithm, followed by annexing the regions when the similarities of them exceeds the critical value based on the calculation of degrees in the histogram similarity, Second, identifying the interesting objects out of the segmented image, partitioned by the image composition theory, is performed. To have a good picture, it is important to adjust positions of interesting objects according to picture composition. Extracting objects is a retro-deduction process using a weighted mask designed upon the triangular composition of picture. To prove the quality of the proposed method, experiments are performed over four hundreds images as well as comparison with recently proposed KMCC and GBIS methods.

Precision agriculture is finding its roots in India. PA always deals with the accuracy and timely information about agriculture products. With the rapid development of computer hardware and software technology, the application of image processing technology in the agricultural research are playing key role [1]. Also, with the advantages of superior speed and accuracy, computer vision has attracted it as an alternative to human inspection [2]. In this paper, we have described a novel application of computer vision and color image segmentation for automating the precise yield prediction process of gerbera flower yield from the polyhouse images. The purpose of the present study is to design a decision support system that could generate flower yield information and serve as base for management & planning of flower marketing. Current study has applied the color image segmentation technique using threshold, to extract the flowers from the scene. Color is considered a fundamental physical property of agriculture products and foods in information analysis [3]. Using HSV color space and histogram analysis, flower color definition is done. Then by the image segmentation process, flowers were separated from the background & detected in the images. Image set with 75 images were tested with this technique.

Graph regularization for color image processing

This chapter is focused on spatially adaptive image processing for color images in the context of the General Adaptive Neighborhood Image Processing (GANIP) approach. The GANIP was first defined for gray-tone images and is here extended to color images. A set of local adaptive neighborhoods is defined for each image point, depending on the color intensity function of the image. These adaptive neighborhoods are then used as spatially adaptive operational windows for defining adaptive Choquet filters and adaptive morphological filters. The resulting adaptive operators are successfully applied and compared with the classical operators for image restoration, enhancement and segmentation of color images.

This paper proposes a color image segmentation algorithm based on affinity propagation clustering. Firstly, the color image is converted to other color space; and then color image is sampled, and the sampling data is clustered by affinity propagation algorithm with given the number, then we can get their class label of the rest data according to the maximum similarity rules; finally, using the regional combined methods ,we can remove independent small regions, and get revised image segmentation result. The simulation experiment shows that this method can achieve the application of affinity propagation algorithm in large-scale color image segmentation. And it has a faster processing speed and satisfactory segmentation results, more in line with the human whole visual perception.

Image segmentation refers to the process of dividing an image into multiple regions which represent meaningful areas. Image segmentation is an essential step for most image analysis tasks such as object recognition and tracking, pattern recognition, content-based image retrieval, etc. In recent years, a large number of image segmentation algorithms have been developed, but achieving accurate segmentation still remains a challenging task. Recently, reservoir computing (RC) has drawn much attention in machine learning as a new model of recurrent neural networks (RNN). Echo State Network (ESN) represents one efficient realization of RC, which is initially designed to facilitate learning in Recurrent Neural Networks. In this paper we investigate the viability of ESN as feature extractor for pixel classification based colour image segmentation. Extensive experiments are conducted on real world colour image datasets and the global ESN reservoir parameters are varied to identify their operating ranges that allow the use of the reservoir nodes internal activations as new pixel features for the colour image segmentation task. A simple feed forward neural network is used to realize the ESN readout function and classify these new features. The experimental results show that the proposed method achieves high performance image segmentation comparing with state-of-the-art techniques. In addition, a set of empirically derived guidelines for setting the reservoir global parameters are proposed.

Unsupervised construction of fuzzy measures through self-organizing feature maps and its application in color image segmentation

Color image segmentation algorithms are proposed based on granular computing clustering (GrCC).Firstly, the atomic hyperspherical granule is represented as the vector including the RGB value of pixel of color image and radii 0. Secondly, the union operator of two hyperspherical granules is designed to obtain the larger hyperspherical granule compared with these two hyperspherical granules.Thirdly, the granular computing clustering is developed by the union operator and the user-defined granularity threshold .Global Consistency Error (GCE), Variation of Information (VI), Rand Index (RI), and Loss Entropy (∆En) are used to evaluate the segmentations.Segmentations of the color images selected from internet and BSD300 show that segmentations by GrCC speed up the segmentation process and achieve the better segmentation performance compared with Kmeans and FCM segmentations.

The segmentation of colour images (RGB), distinguishing clusters of image points, representing for example background, leaves and flowers, is performed in a multi-dimensional environment. Considering a two dimensional environment, clusters can be divided by lines. In a three dimensional environment by planes and in an n-dimensional environment by n-1 dimensional structures. Starting with a complete data set the first neural network, represents an n-1 dimensional structure to divide the data set into two subsets. Each subset is once more divided by an additional neural network: recursive partitioning. This results in a tree structure with a neural network in each branching point. Partitioning stops as soon as a partitioning criterium cannot be fulfilled. After the unsupervised training the neural system can be used for the segmentation of images.