Search

Oracle-bone inscriptions (OBIs), the oldest hieroglyphs in China, were mainly carved on cattle scapulars and tortoise shells, as well as other animal bones. However, automatically extracting OBI characters is a rather complex task due to their differences in character size, orientation, alignment and noisy background. Conventional techniques like Laplacian operation, gradient-edge, or connected component, cannot obtain satisfying results. Therefore, in this paper, instance segmentation methods under deep convolutional neural network were exploited to extract OBIs automatically. More specifically, a SOTA weakly supervised instance segmentation model was introduced to solve this problem, considering that the pixel-level annotation is notoriously time-consuming compared to the bounding boxes annotation, which is extremely serious for the annotation of OBI images because annotators' lack of domain knowledge. The model was trained by 3228 oracle rubbing images and were tested on 312 ones. Results demonstrated that this method can provide a feasible way to automatically extract OBIs from rubbing images (as shown in Fig. 1).

Oracle bone inscriptions (OBIs) are invaluable materials for recovering the economic and social forms for Shang Dynasty, one of the most ancient dynasties in China. It is very important to get the original OBIs from scanned images of oracle bone rubbings. To this end, researchers have to employ a very time-consuming method that they follow the inscriptions by handwritten tools, pixel by pixel and image by image. In this paper, an image segmentation method was proposed to overcome this limitation based on fully convolutional networks (FCN). In order to speed up training as well as boost the segmentation performance, a simple FCN with only convolutional layers was designed, where batch normalization was incorporated. The proposed method was tested on a real OBI image set (320 samples). Experimental results show that the proposed method is effective enough to get the OBIs from scanned images of oracle bone rubbings.

In the field of color texture segmentation, region-level Markov random field model (RMRF) has become a focal problem because of its efficiency in modeling the large-range spatial constraints. However, the RMRF defined on a single scale cannot describe the un-stationary essence of the image, which highly limits its robustness. Hence, by combining wavelet transformation and the RMRF model, we present a multi-scale RMRF (MsRMRF) model in wavelet domainin this paper. In the Bayesian framework, the proposed model seamlessly integrates the multi-scale information stemmed from both the original image and the region-level spatial constraints. Therefore, the new model can accurately describe the characteristics of different kinds of texture. Based on MsRMRF, an unsupervised segmentation algorithm is designed for segmenting color texture images. Both synthetic color texture images and remote sensing images are employed in the comparative experiments, and the experimental results show that the proposed method can obtain more accurate segmentation results than the competitors.

Automatic road extraction from High Resolution Remote Sensing Image is a challenging problem. In this paper we present a new approach for road automatically extraction which is based on topological derivative and mathematical morphology. This approach for road extraction can be divided into three main steps: using topological derivative for image segmentation, using mathematical morphology for road network identification and filtering. The experimental results show that this approach can effectively extract roads from high-resolution remote sensing image.

The Markov random field (MRF) model serves as one of the most powerful tools to improve the robustness of fuzzy c-means (FCM) clustering. However, the use of a pixel-level MRF makes the clustering deficient to deal with images with macro texture patterns. In order to overcome such a problem, this letter presents a novel method that segments images by combining FCM with the region-level MRF (RMRF) model. In this method, a fuzzy novel energy function is established for the RMRF model and utilized in the process of fuzzy clustering, which plays an important role in describing large-range variations of macro textures. Considering the complexity of image textures, a region-level mean template is also established to enhance the relationships between neighboring regions in terms of spectral and structural information. Experiments are conducted using high-resolution remote sensing images, which demonstrate that the proposed method can improve the segmentation accuracy compared with four state-of-the-art competitors.

This paper presents a variation of the fuzzy local information c-means clustering (FLICM) algorithm that provides color texture image clustering. The proposed algorithm incorporates region-level spatial, spectral, and structural information in a novel fuzzy way. The new algorithm, called RFLICM, combines FLICM and region-level Markov random field model (RMRF) together to make use of large scale interactions between image patches instead of pixels. RFLICM can overcome the weakness of FLICM when dealing with textured images and at the same time enhances the clustering performance. The major characteristic of RFLICM is the use of a region-level fuzzy factor, aiming to guarantee texture homogeneity and preserve region boundaries. Experiments performed on synthetic and remote sensing images show that RFLICM is effective in providing accuracy to color texture images.

This letter proposes an improved mean-shift filtering method. The method is added as a preprocessing step for regional segmentation methods, which aims at benefiting segmentations in a more general way. Using this method, first, a logistic regression model between two edge cues and semantic object boundaries is established. Then, boundary posterior probabilities are predicted by the model and associated with weights in the mean-shift filtering iteration. Finally, the filtered image, instead of the original image, is put into segmentation methods. In experiments, the regression model is trained with an aerial image, which is tested with an aerial image and a QuickBird image. Two popular segmentation methods are adopted for evaluations. Both quantitative and qualitative evaluations reveal that the presented procedure facilitates a superior image segmentation result and higher classification accuracy.

In the tree-structured Markov random field (TS-MRF) model, a sequence of MRFs was hierarchically defined on the single spatial resolution in the format of a tree structure which might suffer from the deficiency of modeling the nonstationary property of a given image. In order to overcome such a problem and motivated by nonredundant directional selectivity and highly discriminative nature of the wavelet representation, we attempt to introduce the TS-MRF model into the wavelet domain and propose a new image modeling method-WTS-MRF, in which each MRF is defined over a multiresolution subset of the lattice sites corresponding to the wavelet decomposition. Based on WTS-MRF, a supervised image segmentation algorithm is carried out, and experiment on a remotely sensed image proves the better performance than the supervised segmentation algorithm based on the TS-MRF model.

In the field of remote-sensed image segmentation, it is very important to obtain semantic results. However, in high resolution remote sensed images, different complex patterns always have components with the same spectrum, which makes it rather difficult to extract such patterns only through traditional clustering methods. In this paper, a novel multi-stage region-level clustering method is proposed to solve this problem. Firstly, the initial oversegmentation is obtained by using the Mean Shift algorithm, based on which a region adjacent graph (RAG) is built; Then, FCM is employed to get the spectral-based segmentation result; After that, the context clues for each region is calculated according to the label and size of neighboring regions, followed by the second FCM clustering on each set of regions with the same label to distinct regions with the same spectrum but belongs to different objects; Rearranging all of these clustering results to form the finial processing unit, this algorithm goes a step further to calculate more accurate context clues, and use the third FCM to obtain the final segmentation result. Experiments on the high resolution remote-sensed images have shown the superiority to the competitions.

It is rather difficult for low-level visual features to describe the need for specific applications of image understanding, which results in the inconsistency between vision information and application need. In this paper, a new model is proposed to reduce this gap by combining low-level visual features with semantic features. It uses the output of neural network as the semantic feature, which is accompanied with the priori label features to describe the image after making normalization. And then, the proposed method employs Potts to model the distribution of label priori, and utilizes the Bayesian network to classify images. Several experiments on both synthetic and real images have verified that this method can get more accurate segmentation.

In order to overcome the poor anti-noise performance of traditional fuzzy C-Means (FCM) algorithm in image segmentation, a novel improved FCM algorithm was proposed in this paper based on Particle Swarm Optimization (PSO) algorithm and Markov Random Field (MRF) model, which can make full use of the global searching ability of PSO and the spatial information integrating ability of MRF for image segmentation. In this algorithm, the image segmentation is converted to a PSO optimization problem, in which the fitness function is set up to containing the spatial information based on the spectral value and the neighboring pixels modeled by MRFs. And segmentation results can be iteratively obtained during the PSO iterations according to the newly designed membership function of FCM in which the spatial information is integrated. The experiments herein reported in this paper illustrate the better performance of this algorithm than the traditional FCM algorithm and the PSO algorithm for image segmentation.

The traditional multi-resolution Markov random field (MRMRF) model uses two-component Markov random field model on each resolution, and requires training data to estimate the necessary model parameters, which is unsuitable for unsupervised image segmentation. Under this circumstance, a new multi-resolution Markov random field model with variable potential for unsupervised texture image segmentation is presented. The new model solves this problem by introducing a variable potential function for multi-level logistic distribution (MLL) model on each scale. Using this method, the new model can automatically estimate model parameters and produce accurate unsupervised segmentation results. The results obtained on synthetic texture images and remote sensing images demonstrate that a better segmentation is achieved by our model than the traditional MRMRF model.

This paper proposes an image segmentation algorithm based on the multiresolution Markov Random Fields (MRMRF) model by incorporating edge information. The discrete wavelet transform (DWT) is utilized as a multiresolution technique to obtain feature information at multiple scales and provide computational efficiency. On each scale, the low-frequency wavelet coefficients are employed as image features, while the high-frequency ones are served as computing the edge strength, which is embedded in the label field modeling and makes our algorithm more adaptive to image contents. At the primary scale, there are no high-frequency wavelet coefficients to be used, and the edge strength is calculated by image gradients both on horizontal and vertical directions. Image segmentation is successively carried out with MAP criterion from the coarsest resolution to the finest one, and this algorithm has been successfully tested both on synthetic and remote sensed images.

We propose a context model for the fusion of the multiscale segmented images obtained by HMT model in wavelet domain. It is produced based on fuzzy logical method, and it can integrate different kinds of contextual information in a controllable way. Using such a context model, we can improve the accuracy of texture classification and boundary localization.

In this paper, a new texture segmentation method based on MRMRF in wavelet domain is proposed. Unlike the common used MRMRF, a variable weighting parameter is employed to combine the feature field and the labeling field, which makes the two random fields dominant successively in the procedure of image segmentation and makes it possible to get a more accurate segmentation result. Experimental results demonstrate that the proposed method is effective for texture image segmentation.

An object-oriented, multiscale feature extraction approach is proposed for the land-cover classification of high spatial resolution images. The approach provides more discriminative features by considering the spatial context information from different segmentation levels. It consists of three successive substeps: segmentation by mean-shift algorithm, an iteratively merging process controlled by merging cost function and range-of-scale parameter, and feature extraction from linked multilevel image partitions. The mean-shift method is to get boundary-preserved and spectrally homogeneous over-segmentation regions. Then, a family of nested image partitions is constructed by a merging procedure. Meanwhile, every region of the finest scale is linked to image objects of its superlevels. Finally, every region in the finest scale is treated as a basic analysis unit, and the feature vectors are created by stacking statistics from the region and their superlevels. A support vector machine is used as a classifier and the method on two widely used high spatial resolution data sets over Pavia City, Italy, are evaluated. Compared with results reported in many papers, the result indicates superior accuracy.