Multi-class Image Segmentation Research Articles

Joint spectrogram segmentation and ridge-extraction method for separating multimodal guided waves in long bones

Ultrasonic guided waves (GWs) can be used to evaluate long bones effectively because of the ability to provide the information of the whole bone. In this study, a joint spectrogram segmentation and ridge-extraction (JSSRE) method was proposed to separate multiple modes in long bones. First, the Gabor time-frequency transform was applied to obtain the spectrogram of multimodal signals. Then, a multi-class image segmentation algorithm was used to find the corresponding region of each mode in the spectrogram, including an improved watershed transform and a region growing procedure. Finally, the ridges were extracted and the time domain signals representing individual modes were reconstructed from these ridges in each region. The validations of this method were discussed by simulated multimodal signals with different signal-to-noise ratios (SNR). The correlation coefficients between the original signals without noise and the reconstructed signals were calculated to analyze the results quantitatively. The results showed that the extracted ridges were in good agreement with generated theoretical dispersion curves, and the reconstructed signals were highly related to the original signals, even under the SNR=3 dB situation.

Context-based global multi-class semantic image segmentation by wireless multimedia sensor networks

Using context to aid object detection is becoming more popular among computer vision researchers. Our physical world is structured, and our perception as human beings does not neglect contextual information. In this paper, we propose a framework that is able to simultaneously detect and segment objects of different classes under context. Context is incorporated into our model as long-range pairwise interactions between pixels, which impose a prior on the labeling. Long-range interactions have seen seldom use in the computer vision literature, and we show how to use them to encode contextual information in our segmentation. Our framework formulates the multi-class image segmentation task as an energy minimization problem and finds a globally optimal solution under certain conditions using a single graph cut. We experimentally evaluate performance of our model on two publicly available datasets: the MSRC-1 and the CorelB datasets. Our results show the applicability of our model to the multi-class segmentation problem.

Multiclass Image Segmentation Based on Pixel and Segment Level

Multi-class image segmentation (or pixel labeling) is one of the most important and challenging tasks in computer vision. Currently, many different methods for this task can be broadly categorized into two types according to their choice of the partitioning of the image space, i.e., pixels or segments. However, each choice of the two types of methods comes with its share of advantages and disadvantages. In this study, we construct a novel CRF model to integrate features extracted from pixel and segment levels. We exploit segments generated by Constrained Parametric Min Cuts (CPMC) algorithm in the proposed framework, instead of commonly used unsupervised segmentation method (e.g., mean-shift approach). Additionally, the recognition based on these segments is also integrated into the model, which possible corrects classification mistakes caused by the unary term based on information derived from pixel level. We experimentally demonstrate our model’s quantitative and qualitative improvements over the baseline methods.

GEOMETRIC INVARIANTS CONSTRUCTION FOR SEMANTIC SCENE UNDERSTANDING FROM MULTIPLE VIEWS INSPIRED BY THE HUMAN VISUAL SYSTEM

Semantic scene understanding is one of the several significant goals of robotics. In this paper, we propose a framework that is able to construct geometric invariants for simultaneous object detection and segmentation using a simple pairwise interactive context term, for the sake of achieving a preliminary milestone of Semantic scene understanding. The context is incorporated as pairwise interactions between pixels, imposing a prior on the labeling. Our model formulates the multi-class image segmentation task as an energy minimization problem and finds a globally optimal solution using belief propagation and neural network. We experimentally evaluate the proposed method on three publicly available datasets: the MSRC-1, the CorelB datasets, and the PASCAL VOC database. Results show the applicability and efficacy of the proposed method to the multi-class segmentation problem.

Kernel-induced fuzzy clustering of image pixels with an improved differential evolution algorithm

A modified differential evolution (DE) algorithm is presented for clustering the pixels of an image in the gray-scale intensity space. The algorithm requires no prior information about the number of naturally occurring clusters in the image. It uses a kernel induced similarity measure instead of the conventional sum-of-squares distance. Use of the kernel function makes it possible to partition data that is linearly non-separable and non hyper-spherical in the original input space, into homogeneous groups in a transformed high-dimensional feature space. A novel search-variable representation scheme is adopted for selecting the optimal number of clusters from several possible choices. Extensive performance comparison over a test-suite of 10 gray-scale images and objective comparison with manually segmented ground truth indicates that the proposed algorithm has an edge over a few state-of-the-art algorithms for automatic multi-class image segmentation.

Multi-Class Segmentation with Relative Location Prior

Multi-class image segmentation has made significant advances in recent years through the combination of local and global features. One important type of global feature is that of inter-class spatial relationships. For example, identifying tree pixels indicates that pixels above and to the sides are more likely to be sky whereas pixels below are more likely to be grass. Incorporating such global information across the entire image and between all classes is a computational challenge as it is image-dependent, and hence, cannot be precomputed. In this work we propose a method for capturing global information from inter-class spatial relationships and encoding it as a local feature. We employ a two-stage classification process to label all image pixels. First, we generate predictions which are used to compute a local relative location feature from learned relative location maps. In the second stage, we combine this with appearance-based features to provide a final segmentation. We compare our results to recent published results on several multi-class image segmentation databases and show that the incorporation of relative location information allows us to significantly outperform the current state-of-the-art.

Image Segmentation Using Hidden Markov Gauss Mixture Models

Image segmentation is an important tool in image processing and can serve as an efficient front end to sophisticated algorithms and thereby simplify subsequent processing. We develop a multiclass image segmentation method using hidden Markov Gauss mixture models (HMGMMs) and provide examples of segmentation of aerial images and textures. HMGMMs incorporate supervised learning, fitting the observation probability distribution given each class by a Gauss mixture estimated using vector quantization with a minimum discrimination information (MDI) distortion. We formulate the image segmentation problem using a maximum a posteriori criteria and find the hidden states that maximize the posterior density given the observation. We estimate both the hidden Markov parameter and hidden states using a stochastic expectation-maximization algorithm. Our results demonstrate that HMGMM provides better classification in terms of Bayes risk and spatial homogeneity of the classified objects than do several popular methods, including classification and regression trees, learning vector quantization, causal hidden Markov models (HMMs), and multiresolution HMMs. The computational load of HMGMM is similar to that of the causal HMM.

Rough fuzzy set based scale space transforms and their use in image analysis

In this paper we present a multi-scale method based on the hybrid notion of rough fuzzy sets, coming from the combination of two models of uncertainty like vagueness by handling rough sets and coarseness by handling fuzzy sets. Marrying both notions lead to consider, as instance, approximation of sets by means of similarity relations or fuzzy partitions. The most important features are extracted from the scale spaces by unsupervised cluster analysis, to successfully tackle image processing tasks. Here, we report some results achieved by applying the method to multi-class image segmentation and edge detection, but it can be shown to be successfully applied to texture discrimination problem too.