Search

Convolutional neural networks have been widely used in image semantic segmentation. However, continuous downsampling operations in convolutional neural networks (such as pooling or convolution with step size) reduce the initial image resolution and lose the spatial details of the image, resulting in blurred image segmentation results. To alleviate this problem, in this paper we propose a multi-stage context refinement network (MCRNet) for semantic segmentation. Specifically, we first construct a Lowest-resolution Chain Context Aggregation (LCCA) module to encode rich semantic information. For obtaining more spatial detail information, we further build a High-resolution Context Attention Refinement (HCAR) module consisting of context feature extraction and context feature refinement. Finally, MCRNet fuses the context information generated by LCCA and HCAR for pixel prediction. Experimental results on three challenging semantic segmentation datasets, namely PASCAL VOC2012, ADE20K and Cityscapes, reveals that our proposed MCRNet is effective. [ABSTRACT FROM AUTHOR]

Cartoonization as a special type of artistic style transfer is a difficult image processing task. The current existing artistic style transfer methods cannot generate satisfactory cartoon-style images due to that artistic style images often have delicate strokes and rich hierarchical color changes while cartoon-style images have smooth surfaces without obvious color changes, and sharp edges. To this end, we propose a cartoon loss based generative adversarial network (CartoonLossGAN) for cartoonization. Particularly, we first reuse the encoder part of the discriminator to build a compact generative adversarial network (GAN) based cartoonization architecture. Then we propose a novel cartoon loss function for the architecture. It can imitate the process of sketching to learn the smooth surface of the cartoon image, and imitate the coloring process to learn the coloring of the cartoon image. Furthermore, we also propose an initialization strategy, which is used in the scenario of reusing the discriminator to make our model training easier and more stable. Extensive experimental results demonstrate that our proposed CartoonLossGAN can generate fantastic cartoon-style images, and outperforms four representative methods. [ABSTRACT FROM AUTHOR]

Due to the inconsistent imaging environment, the styles of multitemporal multispectral images (MSIs) are quite different, such as image brightness and transparency. For multitemporal MSIs with different styles, the “same object with different spectra” problem is one of the biggest challenges in change detection. To overcome the challenge, a novel unsupervised spatial–spectral feature learning (FL) framework based on style transformation (ST) (called STFL-CD) is proposed for MSI change detection in this article. For dual-temporal MSIs, the proposed STFl-CD algorithm consists of two phases: ST and spatial–spectral FL. Since the image styles are inconsistent under different imaging environments, the first innovation is to transform the image styles through unmixing and reconstruction. Through ST, the challenge of the “same object with different spectra” problem will be reduced fundamentally. By introducing the attention mechanism, the other innovation is to extract the joint spectral–spatial change features based on a 3-D convolutional neural network with spatial and channel attention. In addition, for multitemporal MSIs, a multitemporal version STFL-CD (MT-STFL-CD) framework is designed based on a recurrent neural network to learn the correlation features between multitemporal remote sensing images. Both of the visual and quantitative results on the real MSI datasets indicate that the proposed unsupervised STFL-CD frameworks have significant advantages on multitemporal MSI change detection. In particular, the performance of the proposed unsupervised STFL-CD algorithm is even comparable to that of the state-of-the-art supervised or semisupervised methods. [ABSTRACT FROM AUTHOR]

Many representation methods were built for gray image textures. However, they are not effective for color textures in general. To alleviate this problem, in this paper we propose a novel Compact Interchannel Sampling Difference Descriptor (CISDD) for color texture classification. In particular, considering sampling-based method can capture more directional information, we first use a heavy-tailed distribution, t-distribution to generate sample points in the image patch to calculate the micro-block difference. Then we model the interchannel relationship of color texture image by using dense micro-block differences. Furthermore, we utilize principal component analysis (PCA) to reduce the dimensions of the features encoded by the Fisher vector, and construct a Compact Interchannel Sampling Difference Descriptor (CISDD) for representing color texture image. Finally, experimental results on five published standard texture datasets (KTH-TIPS, VisTex, CUReT, USPTex and Colored Brodatz) reveal that CISDD is effective and outperforms thirteen representative color texture classification methods. [ABSTRACT FROM AUTHOR]

Convolutional Neural Network (CNN) has shown their advantages in salient object detection. CNN can generate great saliency maps because it can obtain high-level semantic information. And the semantic information is usually achieved by stacking multiple convolutional layers and pooling layers. However, multiple pooling operations will reduce the size of the feature map and easily blur the boundary of the salient object. Therefore, such operations are not beneficial to generate great saliency results. To alleviate this issue, we propose a novel edge information-guided hierarchical feature fusion network (HFFNet). Our network fuses features hierarchically and retains accurate semantic information and clear edge information effectively. Specifically, we extract image features from different levels of VGG. Then, we fuse the features hierarchically to generate high-level semantic information and low-level edge information. In order to retain better information at different levels, we adopt a one-to-one hierarchical supervision strategy to supervise the generation of low-level information and high-level information respectively. Finally, we use low-level edge information to guide the saliency map generation, and the edge guidance fusion is able to identify saliency regions effectively. The proposed HFFNet has been extensively evaluated on five traditional benchmark datasets. The experimental results demonstrate that the proposed model is fairly effective in salient object detection compared with 10 state-of-the-art models under different evaluation indicators, and it is superior to most of the comparison models. [ABSTRACT FROM AUTHOR]

Extracting the foreground from a given complex image is an important and challenging problem. Although there have been many methods to perform foreground extraction, most of them are time-consuming, and the trimaps used in the matting step are labeled manually. In this paper, we propose a fast interactive foreground extraction method based on the superpixel GrabCut and image matting. Specifically, we first extract superpixels from a given image and apply GrabCut on them to obtain a raw mask. Due to that the resulting mask border is hard and toothing, we further propose fast and adaptive trimaps (FATs), and construct an FATs-based shared matting for computing a refined mask. Finally, by interactive processing, we can obtain the final foreground. Experimental results on the BSDS500 and alphamatting datasets demonstrate that our proposed method is faster than five representative methods, and performs better than the interactive representative methods in terms of the three evaluation criteria: 1) mean square error; 2) sum of absolute difference; and 3) execution time. [ABSTRACT FROM AUTHOR]

In complex scenes, multiple objects are often concealed in cluttered backgrounds. Their saliency is difficult to be detected by using conventional methods, mainly because single color contrast can not shoulder the mission of saliency measure; other image features should be involved in saliency detection to obtain more accurate results. Using Dempster-Shafer (D-S) evidence theory based region classification, a novel method is presented in this paper. In the proposed framework, depth feature information extracted from a coarse map is employed to generate initial feature evidences which indicate the probabilities of regions belonging to foreground or background. Based on the D-S evidence theory, both uncertainty and imprecision are modeled, and the conflicts between different feature evidences are properly resolved. Moreover, the method can automatically determine the mass functions of the two-stage evidence fusion for region classification. According to the classification result and region relevance, a more precise saliency map can then be generated by manifold ranking. To further improve the detection results, a guided filter is utilized to optimize the saliency map. Both qualitative and quantitative evaluations on three publicly challenging benchmark datasets demonstrate that the proposed method outperforms the contrast state-of-the-art methods, especially for detection in complex scenes. [ABSTRACT FROM AUTHOR]

In complex scenes, foreground saliency can hardly be detected completely, which may further result in the ambiguous cues of objects for other computer vision tasks. In this letter, an extended locality-constrained linear self-coding (eLLsC) scheme is proposed to assist to solve the saliency detection problem under the complex scenes. The locality of both spatial relation and feature distance is preserved in eLLsC, thus making the transformed code involved in the manifold ranking to prompt the generation of the saliency map with more complete foreground and clearer boundary. Experimental results on three saliency detection benchmarks demonstrate the effectiveness of the proposed hybrid method. [ABSTRACT FROM AUTHOR]

The widely used energy features extracted from the wavelet domain can effectively represent the common image textures. However, they are not robust to the rotated textures. In this letter, we propose a multiscale rotation-invariant representation (MRIR) of textures by using multiscale sampling. Particularly, a multiscale wavelet transform is used to decompose the magnitude pattern (MP) mapping of a texture. Furthermore, the sign pattern (SP) mapping of a texture is used as a step function, which is further sampled and used to fit the wavelet subbands of the MP mapping for computing the sampled directional mean vectors (SDMVs) of the subbands. Moreover, we construct frequency vectors (FVs) of those SP mappings for capturing the structural information of textures. Finally, we can obtain the MRIR vector of an image texture by concatenating those SDMVs and FVs for texture classification. The comprehensive experimental results demonstrate that our proposed approach outperforms six representative texture classification methods. [ABSTRACT FROM PUBLISHER]

Local binary pattern (LBP) is a frequently‐used texture descriptor. Lots of LBP‐variants have been proposed to improve its performance of representing textures. However, most of them ignore the global and neighbour‐difference information of an image texture. In this study, the authors propose a structural difference histogram representation by fusing the segmented structure pattern (SSP), the refined LBP (RLBP) and the neighbour‐difference pattern (NDP) for texture classification. Particularly, the segmented structure, which contains the global contour information of an image texture, is first constructed to compute its SSP histogram feature. Simultaneously, the RLBP is defined to represent the local texture information. Furthermore, the NDP is presented to describe differences between neighbours of a centre pixel in the local patch of texture images. Experimental results on Brodatz and Columbia‐Utrecht reflectance databases indicate that the proposed method can achieve the satisfactory classification accuracy compared with several representative methods. [ABSTRACT FROM AUTHOR]

Abstract: Feature extraction is an important processing procedure in texture classification. For feature extraction in the wavelet domain, the energies of subbands are usually extracted for texture classification. However, the energy of one subband is just a specific feature. In this paper, we propose an efficient feature extraction method for texture classification. In particular, feature vectors are obtained by c-means clustering on the contourlet domain as well as using two conventionally extracted features that represent the dispersion degree of contourlet subband coefficients. The c-means clustering algorithm is initialized via a nonrandom initialization scheme. By investigating these feature vectors, we employ a weighted for comparing any two feature vectors that represent the corresponding subbands of two images and define a new distance between two images. According to the new distance, a k-Nearest Neighbor (kNN) classifier is utilized to perform texture classification, and experimental results show that our proposed approach outperforms five current state-of-the-art texture classification approaches. [Copyright &y& Elsevier]

As a newly developed 2-D extension of the wavelet transform using multiscale and directional filter banks, the contourlet transform can effectively capture the intrinsic geometric structures and smooth contours of a texture image that are the dominant features for texture classification. In this paper, we propose a novel Bayesian texture classifier based on the adaptive model-selection learning of Poisson mixtures on the contourlet features of texture images. The adaptive model-selection learning of Poisson mixtures is carried out by the recently established adaptive gradient Bayesian Ying-Yang harmony learning algorithm for Poisson mixtures. It is demonstrated by the experiments that our proposed Bayesian classifier significantly improves the texture classification accuracy in comparison with several current state-of-the-art texture classification approaches. [ABSTRACT FROM AUTHOR]

In this letter, we propose an efficient one-nearest-neighbor classifier of texture via the contrast of local energy histograms of all the wavelet subbands between an input texture patch and each sample texture patch in a given training set. In particular, the contrast is realized with a discrepancy measure which is just a sum of symmetrized Kullback–Leibler divergences between the input and sample local energy histograms on all the wavelet subbands. It is demonstrated by various experiments that our proposed method obtains a satisfactory texture classification accuracy in comparison with several current state-of-the-art texture classification approaches. [ABSTRACT FROM PUBLISHER]