Real-time implementations of image segmentation algorithms on shared memory multicore architecture: a survey (Conference Presentation)

Image segmentation has an important role in many image processing applications. Several methods exist for segmenting an image. However, this technique is still a relatively open topic for which various research works are regularly presented. With the recent developments on complex networks theory, image segmentation techniques based on graphs has considerably improved. In this paper, we present a new perspective of image segmentation, by applying three of the most efficient community detection algorithms, Louvain, infomap and stability optimization based on the louvain algorithm, and we extract communities in which the highest modularity feature is achieved. After we show that this measure is invariant to non-structural change on image, which mean that the image segmentation is also invariant to rotation. Finally we evaluate the three proposed algorithms for Berkeley database images, and we show that our results can outperform other segmentation methods in terms of accuracy and can achieve much better segmentation results.

7 - A survey on neutrosophic medical image segmentation

It is the key step of automatic apple picking and sorting to segment of the apple image in natural environment using image information processing technology. In order to improve the intellectualization of apple picking process and effectively extract the target of image segmentation, a novel image segmentation method of Huaniu apple based on pulse coupled neural network (PCNN) and watershed algorithm is proposed. Firstly, the PCNN model is improved and optimized on the basis of image RGB to L*A*B space conversion. Then, the improved PCNN combined with watershed algorithm was used to segment the apple image on considering the image texture and color feature information. The theoretical analysis and experimental results show that the novel method is effectively able to segment target image, and can preserve the image details and the edges as well. The proposed algorithm has better subjective vision effect and objective quality than the traditional watershed and other related algorithms.

There is a huge diversity of definitions of visually image segments, ranging from simple uniformly colored segments, textured segments, through symmetric patterns, and up to complex semantically meaningful objects. This diversity has led to a wide range of different approaches for image segmentation. In this paper we present a single unified framework for addressing this problem --- Segmentation by Composition. We define a good image segment as one which can be easily composed using its own pieces, but is difficult to compose using pieces from other parts of the image. This non-parametric approach captures a large diversity of segment types, yet requires no pre-definition or modelling of segment types, nor prior training. Based on this definition, we develop a segment extraction algorithm --- i.e., given a single point-of-interest, provide the best image segment containing that point. This induces a figure-ground image segmentation, which applies to a range of different segmentation tasks: single image segmentation, simultaneous co-segmentation of several images, and class-based segmentations.

Medical-image segmentation is of primary importance in the development of computer assisted detection (CAD) of mammographic masses. Image segmentation is used for finding regions of interest (ROI) within mammograms that are further processed to estimate their likelihood of being a potential lesion or mass. This task can be stated as follows: €œA gray-scale image is represented as a 1D array X = (x1, x2,...,xN), where xn is an input feature for pixel n and N is the total number of pixels in the image. The input feature vector xn may be a D dimensional vector or simply the gray-scale value of the pixel n. Let the underlying true segmentation of the image be denoted as Y = (y1, y2,..., yN). It is assumed that the number of classes is predetermined as a set of known class labels I‰l, where l Iµ {1,..., L{ and therefore the class label of pixel n is indicated as y n ∈{I‰ l } L l=1 . The task is to predict the A·n estimate of the segmentation for each pixel. In an automated system, such likelihood estimates are generated using a classifier that takes as input some features that describe region properties, e.g., image texture. The segmentation of digital mammograms is a difficult task. A number of different approaches have been adopted in this area with varying success. Broadly speaking, image segmentation can be carried out either as: (1) image preprocessing step with the main objective of identifying regions of interest (spatially coherent collection of pixels within the image) and a subsequent feature extraction and classification step is required to characterize a given region of interest as either €œnormal€ or €œsuspicious€; or (2) part of the overall classification scheme, where the likelihood of each pixel being €œsuspicious is calculated to generate a probability image using pixel-based features as input to a classifier. The probability image is thereafter thresholded to give both the segmentation and classification output. The main difference between (1) and (2) is that in the first case, image segmentation is needed before classification can be performed; whereas in the second case, classification and segmentation are both based on thresholding probability estimates of pixels and are achieved at the same time. The image segmentation approaches, with the aim of finding regions of interest, were first attempted in digital mammography with varying techniques, including global thresholding, region growing, region clustering, template matching, edge operators and filtering, and edge-based hybrid methods. Image segmentation is developed from pixel-based probability estimation is underpinned by modeling features using parametric methods, Gaussian mixture modeling, Markov random fields, and other methods. A detailed discussion on mammogram-based image segmentation with their algorithms is available in Singh and Bovis. Experience shows that it is quite difficult to select an outright winning image-segmentation method, since different approaches have been shown to be suitable for different data sets and show varied performance under different experimental conditions. However, there is a consensus that image segmentation in medical imaging is most successful when explicitly using a priori information about the problem to be studied.

The progress in the realm of image segmentation has helped farmers to use nominal inputs for higher production within limited time. Preliminary identification of diseases on fruits is limited to naked eyes since the majority of these symptoms can only be identified by microscopic visuals. Image segmentation plays a vital part in distinguishing their infected parts from the disinfected ones. In this paper, clustering is used as an approach in image segmentation to cautiously discover the affected parts of the fruits by segmenting the affected areas from the non-affected parts. Four clustering techniques—IS-KM, IS-FEKM, IS-MKM, and IS-FECA—were employed for this purpose. The quality of segmentation was evaluated using few performance measures like SC, RMSE, MSE, MAE, NAE, and PSNR. The result obtained using IS-FECA is more reasonable compared to the other methods. Roughly each value of performance parameters confers better results for IS-FECA-based image segmentation method, which means proper separation of diseased parts in fruits from their un-affected ones is attainable.

Particle Swarm Optimization (PSO) is population based stochastic algorithm to form clusters with the help of fitness functions. PSO clustering algorithm is widely used in pattern recognition methods such as image segmentation where PSO defines less number of clusters compared to conventional clustering approaches. Level Sets image segmentation aided with the clustering gives fast convergence towards the desired boundaries of the object to be segmented. Here in this paper a novel approach of image segmentation using PSO clustering applied to Level sets is been presented where PSO performs better than KFCM by generating more compact clusters and larger inter cluster separation. The proposed method is successfully implemented on the images and results obtained show the effectiveness of the approach.

The cell image segmentation has very high practical significance in medical diagnosis. But the cell image has the problems of accretive cells, incoherent cell boundary, and the internal cavity that make it difficult to image segmentation. In this paper, a watershed algorithm based on distance transform is proposed to solve images of cells adhesion. Firstly, image enhancement is carried out as the image preprocessing, then the OTSU threshold segmentation is used to rough segment the image, finally the watershed algorithm by optimizing the seed points is adopt for fine segmentation. Experiment results showed that the proposed algorithm is effectively solved the problems of cell adhesion and over-segmentation, the image segmentation accuracy is more than the traditional watershed algorithm, and remained the cell shape in maximum extent. Therefore, the watershed segmentation based on distance transformation transform is practical according to the accretive cell images.

Neural networks have proved to be effective in solving a wide range of problems. As problems become more and more demanding, they require larger neural networks, and the time used for learning is consequently greater. Parallel implementations of learning algorithms are therefore vital for a useful application. Implementation, however, strongly depends on the features of the learning algorithm and the underlying hardware architecture. For this experimental work a dynamic problem was chosen which implicates the use of recurrent neural networks and a learning algorithm based on the paradigm of learning automata. Two parallel implementations of the algorithm were applied - one on a computing cluster using MPI and OpenMP libraries and one on a graphics processing unit using the CUDA library. The performance of both parallel implementations justifies the development of parallel algorithms.

Critical to any automated surveillance system is the recognition component. Since the inception of Pattern Recognition & Image processing, researchers across the globe continue to propose newer facial recognition algorithms. Each of these facial algorithms has its own pros and cons. A typical facial recognition algorithm consists of three steps namely: facial detection, feature extraction and recognition. In this paper we discuss serial and parallel implementation of four standard facial recognition algorithms namely, Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Independent Component Analysis (ICA) and FISHER Face. Work presented in this paper consists of two sections. In section 1, we discuss serial and parallel implementation of the algorithms. Section 2, presents a comparative performance analysis of the above 4 algorithms. A major challenge in this effort is the ability to explore and exploit concurrency in existing facial recognition algorithms to improve performance. Based on the algorithms performance, we have made few suggestions regarding the suitability of each of these algorithms for different domains/applications. All algorithms are implemented using open source OPENCV and OPENMP libraries.

Routing plays a major role in VANETs by helping a vehicle to reach the destination by finding an optimal path. These routing decisions are affected by the congestion on roads. Several approaches have been proposed to improve this problem of handling congestion thorough various traffic management strategies. ACO is being used in literature to provide routing in real time environment. Modified Ant Colony Optimization (MACO) algorithm is used to reduce the travel time of the journey by avoiding congested routes. This paper proposes a parallel implementation for MACO algorithm in order to further reduce the travel time due to faster computation using GPUs for the vehicles on move. Parallel implementation is done using parallel architecture on the Graphics Processing Unit (GPU) at NVIDIA GeForce 710 M using C language running CUDA (Compute Unified Device Architecture) toolkit 7.0 on Microsoft Visual Studio 2010. The obtained results for proposed parallel MACO when compared with the parallel implementation of the standard Dijkstra algorithm and that of the existing MACO algorithm on a real world North-West Delhi map with an increased number of vehicles significantly reduce the travel time.

Brain tumor segmentation based on a hybrid clustering technique

In this chapter we explain special approaches for image binarization and segmentation of still images or video frames, in the latter case with attention to ensuring temporal consistency. We discuss mean-shift segmentation in detail. We also provide a general view on image segmentation as (another) labelling example in computer vision, introduce segmentation this way from an abstract point of view, and discuss belief-propagation solutions for this labelling framework.

As a classical method of image segmentation in mathematical morphology, the watershed transform has been applied successively into some fields like remote sensing image processing, biomedical and computer vision applications. However the watershed transform is a relatively time consuming task and classical watershed algorithms have a strong recursive nature, so straightforward parallel ones have a very low efficiency. Mekjster and Roerdink (1996; 1995) have proposed an alternative algorithm (M-R for short) which consists of three stages aimed to exploit parallelism fully. The M-R algorithm has much limitation and some underlying logical errors, therefore we present an improved parallel watershed algorithm based on a directed valued graph called components graph for image segmentation. We firstly point out the limits of the M-R algorithm, then describe the theory and steps of our algorithm in detail. Finally, experimental studies and performance measurements are given.

A novel approach for segmentation of good, normal and bad quality fingerprint image is proposed in this paper. Which is different from traditional methods that usually use certain features to segment diversified image. This work is divided in three steps: firstly, we enhance the quality of image to remove great many false traces effectively and got a uniform background. Secondly, we have extracted the background of ridge area and finally; we segment the foreground from background. Our results shows that the proposed technique successfully segments the good, normal and bad quality fingerprint images and also enhance the quality of image. We have evaluated the performance of the segmented image through objective and subjective quality measures like mean, standard deviation and Fourier spectrum. We have tested this technique for 3200 images taken from database FVC2002. Our technique yields better results as compared to traditional segmentation techniques. The results that we have achieved are more useful in automatic fingerprint recognition system