Showing papers on "Segmentation-based object categorization published in 2019"

DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation

Abstract: Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.

Plant disease leaf image segmentation based on superpixel clustering and EM algorithm

Abstract: Plant disease leaf image segmentation plays an important role in the plant disease detection through leaf symptoms. A novel segmentation method of plant disease leaf image is proposed based on a hybrid clustering. The whole color leaf image is firstly divided into a number of compact and nearly uniform superpixels by superpixel clustering, which can provide useful clustering cues to guide image segmentation to accelerate the convergence speed of the expectation maximization (EM) algorithm, and then, the lesion pixels are quickly and accurately segmented from each superpixel by EM algorithm. The experimental results and the comparison results with similar approaches demonstrate that the proposed method is effective and has high practical value for plant disease detection.

Figure-ground image segmentation using feature-based multi-objective genetic programming techniques

Abstract: Figure-ground image segmentation is a process of separating regions of interest from a target image. Genetic programming has been employed to evolve segmentors that have the potential to capture high variations of images and conduct accurate segmentation. However, GP-based methods tend to evolve complex segmentors that have large sizes, are computationally expensive and difficult to interpret. Therefore, this work aims to balance the solution functionality with the complexity by applying multi-objective techniques to GP. Specifically, NSGA-II (nondominated sorting genetic algorithm) and SPEA2 (strength Pareto evolutionary algorithm) are selected as the base multi-objective techniques, in which a new Pareto dominance mechanism is designed, thus creating two new multi-objective techniques—INSGA-II (improved NSGA-II) and ISPEA2 (improved SPEA2). By applying the INSGA-II and ISPEA2 to GP, respectively, two novel multi-objective GP (MOGP) methods are proposed—INSGP and ISPGP. Both methods have two objectives: a solution functionality measure (i.e. the classification accuracy) and a solution complexity measure based on an exponential function. The results show that the proposed MOGP methods can evolve solutions with good trade-offs between the functionality and complexity, and INSGP is better at keeping solution diversity than ISPGP for the segmentation tasks in this paper. Moreover, the analyses on the evolved segmentors show that certain discriminatory patterns can be captured.

Color image segmentation by combining the convex active contour and the Chan Vese model

Abstract: In this paper, we present a robust and computationally efficient image segmentation technique based on a hybrid convex active contour and the Chan–Vese (CV) model. The proposed algorithm overcomes the drawbacks of existing image segmentation techniques which are heavily dependent upon the initial user input. Here, we propose to combine region-based and boundary-based techniques for segmentation so that we guarantee robustness across all types of images. We start with a either a geodesic-based or a dynamic region merging (DRM)-based contour before using the CV model. Contrary to the basic geodesic model, the random walk technique, and the snake-based convex active contour model, our algorithm works with minimal input and is shown to be independent of the location of the input pixels provided by the user. The algorithm works by initiating a contour which is either based on the geodesic distance or the DRM model. This contour is then used with the CV model to further refine the segmentation results. We tested the proposed algorithm on several standard databases using both subjective and objective measures. Our experimental results show that the proposed algorithm outperforms recently proposed approaches over indoor and outdoor images in terms of both processing time and segmentation accuracy.

Self-organizing neural networks for image segmentation based on multiphase active contour

Abstract: Image segmentation is a process of segregating foreground object from background object in an image. This paper proposes a method to perform image segmentation for the color and textured images with a two-step approach. In the first step, self-organizing neurons based on neural networks are used for clustering the input image, and in the second step, multiphase active contour model is used to get various segments of an image. The contours are initialized in the active contour model with the help of the self-organizing maps obtained as a result of first step. From the results, it is inferred that the proposed method provides better segmentation result for all types of images.

Striped-texture image segmentation with application to multimedia security

Abstract: In today’s rapid growth of volume of multimedia data, security is important yet challenging problem in multimedia applications. Image, which covers the highest percentage of the multimedia data, it is very important for multimedia security. Image segmentation is utilized as a fundamental preprocessing of various multimedia applications such as surveillance for security by breaking a given image into multiple salient regions. In this paper, we present a new image segmentation approach based on frequency-domain filtering for images with stripe texture, and generalize it to lattice fence images. Our method significantly reduces the impact of stripes on segmentation performance. The approach proposed in this paper consists of three phases. Given the images, we weaken the effect of stripe texture by filtering in the frequency domain automatically. Then, structure-preserving image smoothing is employed to remove texture details and extract the main image structures. Last, we use an effective threshold method to produce segmentation results. Our method achieves very promising results for the test image dataset and could benefit a number of new multimedia applications such as public security.

Mathematical Techniques for Biomedical Image Segmentation

Abstract: This article presents some mathematical methods for biomedical image segmentation that these authors have used, adapted, and developed. In particular, some segmentation strategies for blood vessel, atherosclerosis, and intracerebral hemorrhage images constitute one of the principal causes of death in all those countries where the classical epidemics do not have an important weight. In the field of biomedical, images have developed sophisticated algorithms for image segmentation, which go from the deformable models, bioinspired algorithms, and neural networks, among others. Many of these strategies for arriving at satisfactory results need a lot of computational time. For this reason, the proposal of simple, fast, and reliable algorithms for biomedical image segmentation will be always welcome. The remainder of the article is presented in section “ Materials and Methods .” Section “ Mathematical Techniques Theory ” outlines some mathematical techniques and theoretical aspects. In section “ Algorithms ,” we describe some of our algorithms. Section “ Segmentation of Blood Vessel Images ” demonstrates the experimental results, comparisons, and discussion. Finally, in section “ Conclusions ,” the most important conclusions are given.

Pavement image segmentation based on fast FCM clustering with spatial information in internet of things

Abstract: Pavement image segmentation needs to deal with noise spots and has real time requirement. The original FCM method only considers the pixel’s gray value and doesn’t fully utilize the spatial information of the image. A new fast FCM algorithm is proposed, and it has noise immunity. By comparing with other FCM algorithms, it achieves better segmentation results through less iteration times and more rapid runtime. It is an effective and noise-resistant algorithm for pavement image segmentation from video multimedia in IOT (internet of things) platform.