Salient Object Detection Based on Multiscale Segmentation and Fuzzy Broad Learning

2020 ◽  
Author(s):  
Xiao Lin ◽  
Zhi-Jie Wang ◽  
Lizhuang Ma ◽  
Renjie Li ◽  
Mei-E Fang
Keyword(s):  
Clustering Algorithm ◽  
Saliency Detection ◽  
Texture Features ◽  
Saliency Map ◽  
Label Propagation ◽  
Learning System ◽  
Saliency Maps ◽  
Novel Approach ◽  
Multiscale Segmentation ◽  
Benchmark Datasets

Abstract Saliency detection has been a hot topic in the field of computer vision. In this paper, we propose a novel approach that is based on multiscale segmentation and fuzzy broad learning. The core idea of our method is to segment the image into different scales, and then the extracted features are fed to the fuzzy broad learning system (FBLS) for training. More specifically, it first segments the image into superpixel blocks at different scales based on the simple linear iterative clustering algorithm. Then, it uses the local binary pattern algorithm to extract texture features and computes the average color information for each superpixel of these segmentation images. These extracted features are then fed to the FBLS to obtain multiscale saliency maps. After that, it fuses these saliency maps into an initial saliency map and uses the label propagation algorithm to further optimize it, obtaining the final saliency map. We have conducted experiments based on several benchmark datasets. The results show that our solution can outperform several existing algorithms. Particularly, our method is significantly faster than most of deep learning-based saliency detection algorithms, in terms of training and inferring time.

Hierarchical Saliency Detection via Probabilistic Object Boundaries

2017 ◽  
Vol 31 (06) ◽  
pp. 1755010 ◽  
Author(s):  
Haijun Lei ◽  
Hai Xie ◽  
Wenbin Zou ◽  
Xiaoli Sun ◽  
Kidiyo Kpalma ◽  
...  
Keyword(s):  
Computational Models ◽  
Saliency Detection ◽  
Spatial Coherence ◽  
Saliency Map ◽  
Object Boundary ◽  
Detection Model ◽  
Saliency Maps ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Center Bias

Though there are many computational models proposed for saliency detection, few of them take object boundary information into account. This paper presents a hierarchical saliency detection model incorporating probabilistic object boundaries, which is based on the observation that salient objects are generally surrounded by explicit boundaries and show contrast with their surroundings. We perform adaptive thresholding operation on ultrametric contour map, which leads to hierarchical image segmentations, and compute the saliency map for each layer based on the proposed robust center bias, border bias, color dissimilarity and spatial coherence measures. After a linear weighted combination of multi-layer saliency maps, and Bayesian enhancement procedure, the final saliency map is obtained. Extensive experimental results on three challenging benchmark datasets demonstrate that the proposed model outperforms eight state-of-the-art saliency detection models.

scholarly journals Explaining Neural Networks Using Attentive Knowledge Distillation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1280
Author(s):  
Hyeonseok Lee ◽  
Sungchan Kim
Keyword(s):  
Neural Networks ◽  
Model Prediction ◽  
Saliency Map ◽  
Model Parameters ◽  
Learning Capability ◽  
Fine Grained ◽  
Network Layers ◽  
Saliency Maps ◽  
Novel Approach ◽  
Knowledge Distillation

Explaining the prediction of deep neural networks makes the networks more understandable and trusted, leading to their use in various mission critical tasks. Recent progress in the learning capability of networks has primarily been due to the enormous number of model parameters, so that it is usually hard to interpret their operations, as opposed to classical white-box models. For this purpose, generating saliency maps is a popular approach to identify the important input features used for the model prediction. Existing explanation methods typically only use the output of the last convolution layer of the model to generate a saliency map, lacking the information included in intermediate layers. Thus, the corresponding explanations are coarse and result in limited accuracy. Although the accuracy can be improved by iteratively developing a saliency map, this is too time-consuming and is thus impractical. To address these problems, we proposed a novel approach to explain the model prediction by developing an attentive surrogate network using the knowledge distillation. The surrogate network aims to generate a fine-grained saliency map corresponding to the model prediction using meaningful regional information presented over all network layers. Experiments demonstrated that the saliency maps are the result of spatially attentive features learned from the distillation. Thus, they are useful for fine-grained classification tasks. Moreover, the proposed method runs at the rate of 24.3 frames per second, which is much faster than the existing methods by orders of magnitude.

scholarly journals Research on an Infrared Multi-Target Saliency Detection Algorithm under Sky Background Conditions

Sensors ◽  
2020 ◽  
Vol 20 (2) ◽  
pp. 459
Author(s):  
Shaosheng Dai ◽  
Dongyang Li
Keyword(s):  
Saliency Detection ◽  
Infrared Image ◽  
Detection Algorithm ◽  
Saliency Map ◽  
Phase Spectrum ◽  
Background Suppression ◽  
Suppression Effect ◽  
Multi Scale ◽  
Saliency Maps ◽  
Image Saliency

Aiming at solving the problem of incomplete saliency detection and unclear boundaries in infrared multi-target images with different target sizes and low signal-to-noise ratio under sky background conditions, this paper proposes a saliency detection method for multiple targets based on multi-saliency detection. The multiple target areas of the infrared image are mainly bright and the background areas are dark. Combining with the multi-scale top hat (Top-hat) transformation, the image is firstly corroded and expanded to extract the subtraction of light and shade parts and reconstruct the image to reduce the interference of sky blurred background noise. Then the image obtained by a multi-scale Top-hat transformation is transformed from the time domain to the frequency domain, and the spectral residuals and phase spectrum are extracted directly to obtain two kinds of image saliency maps by multi-scale Gauss filtering reconstruction, respectively. On the other hand, the quaternion features are extracted directly to transform the phase spectrum, and then the phase spectrum is reconstructed to obtain one kind of image saliency map by the Gauss filtering. Finally, the above three saliency maps are fused to complete the saliency detection of infrared images. The test results show that after the experimental analysis of infrared video photographs and the comparative analysis of Receiver Operating Characteristic (ROC) curve and Area Under the Curve (AUC) index, the infrared image saliency map generated by this method has clear target details and good background suppression effect, and the AUC index performance is good, reaching over 99%. It effectively improves the multi-target saliency detection effect of the infrared image under the sky background and is beneficial to subsequent detection and tracking of image targets.

Saliency Optimization and Integration Via Iterative Bootstrap Learning

2018 ◽  
Vol 32 (09) ◽  
pp. 1859016
Author(s):  
Liming Li ◽  
Xiaodong Chai ◽  
Shuguang Zhao ◽  
Shubin Zheng ◽  
Shengchao Su
Keyword(s):  
Multiple Scales ◽  
Saliency Detection ◽  
Saliency Map ◽  
Input Image ◽  
Training Data ◽  
Data Sets ◽  
Saliency Maps ◽  
Training Samples ◽  
Public Data

This paper proposes an effective method to elevate the performance of saliency detection via iterative bootstrap learning, which consists of two tasks including saliency optimization and saliency integration. Specifically, first, multiscale segmentation and feature extraction are performed on the input image successively. Second, prior saliency maps are generated using existing saliency models, which are used to generate the initial saliency map. Third, prior maps are fed into the saliency regressor together, where training samples are collected from the prior maps at multiple scales and the random forest regressor is learned from such training data. An integration of the initial saliency map and the output of saliency regressor is deployed to generate the coarse saliency map. Finally, in order to improve the quality of saliency map further, both initial and coarse saliency maps are fed into the saliency regressor together, and then the output of the saliency regressor, the initial saliency map as well as the coarse saliency map are integrated into the final saliency map. Experimental results on three public data sets demonstrate that the proposed method consistently achieves the best performance and significant improvement can be obtained when applying our method to existing saliency models.

Prior Fusion and Feature Transformation-Based Principal Component Analysis for Saliency Detection

2018 ◽  
Vol 32 (08) ◽  
pp. 1855013
Author(s):  
Dongjing Shan ◽  
Chao Zhang
Keyword(s):  
Principal Component Analysis ◽  
Saliency Detection ◽  
Principal Component ◽  
Feature Space ◽  
Component Analysis ◽  
Saliency Map ◽  
Feature Transformation ◽  
Benchmark Datasets ◽  
Pca Method ◽  
Linear Transform

In this paper, we propose a prior fusion and feature transformation-based principal component analysis (PCA) method for saliency detection. It relies on the inner statistics of the patches in the image for identifying unique patterns, and all the processes are done only once. First, three low-level priors are incorporated and act as guidance cues in the model; second, to ensure the validity of PCA distinctness model, a linear transform for the feature space is designed and needs to be trained; furthermore, an extended optimization framework is utilized to generate a smoothed saliency map based on the consistency of the adjacent patches. We compare three versions of our model with seven previous methods and test them on several benchmark datasets. Different kinds of strategies are adopted to evaluate the performance and the results demonstrate that our model achieves the state-of-the-art performance.

scholarly journals A novel attention model for salient structure detection in seismic volumes

2021 ◽  
Vol 1 (1) ◽  
pp. 31-45
Author(s):  
Muhammad Amir Shafiq ◽  
◽  
Zhiling Long ◽  
Haibin Di ◽  
Ghassan AlRegib ◽  
...  
Keyword(s):  
Seismic Data ◽  
System Modeling ◽  
Saliency Detection ◽  
Spectral Projection ◽  
Detection Algorithm ◽  
Saliency Map ◽  
Seismic Interpretation ◽  
Imaging Data ◽  
Attention Model ◽  
Saliency Maps

<abstract><p>A new approach to seismic interpretation is proposed to leverage visual perception and human visual system modeling. Specifically, a saliency detection algorithm based on a novel attention model is proposed for identifying subsurface structures within seismic data volumes. The algorithm employs 3D-FFT and a multi-dimensional spectral projection, which decomposes local spectra into three distinct components, each depicting variations along different dimensions of the data. Subsequently, a novel directional center-surround attention model is proposed to incorporate directional comparisons around each voxel for saliency detection within each projected dimension. Next, the resulting saliency maps along each dimension are combined adaptively to yield a consolidated saliency map, which highlights various structures characterized by subtle variations and relative motion with respect to their neighboring sections. A priori information about the seismic data can be either embedded into the proposed attention model in the directional comparisons, or incorporated into the algorithm by specifying a template when combining saliency maps adaptively. Experimental results on two real seismic datasets from the North Sea, Netherlands and Great South Basin, New Zealand demonstrate the effectiveness of the proposed algorithm for detecting salient seismic structures of different natures and appearances in one shot, which differs significantly from traditional seismic interpretation algorithms. The results further demonstrate that the proposed method outperforms comparable state-of-the-art saliency detection algorithms for natural images and videos, which are inadequate for seismic imaging data.</p></abstract>

scholarly journals A Survey on Approaches for Saliency Detection with Visual Attention

2018 ◽  
Vol 232 ◽  
pp. 02007
Author(s):  
Qi Zhang
Keyword(s):  
Deep Learning ◽  
Visual Attention ◽  
Visual Cues ◽  
Saliency Detection ◽  
Saliency Map ◽  
Local Context ◽  
Natural Scenes ◽  
Benchmark Datasets ◽  
The Difference

Most existing approaches for detecting salient areas in natural scenes are based on the saliency contrast within the local context of image. Nowadays, a few approaches not only consider the difference between the foreground objects and the surrounding background areas, but also consider the saliency objects as the candidates for the center of attention from the human’s perspective. This article provides a survey of saliency detection with visual attention, which exploit visual cues of foreground salient areas, visual attention based on saliency map, and deep learning based saliency detection. The published works are explained and descripted in detail, and some related key benchmark datasets are briefly presented. In this article, all documents are published from 2013 to 2018, giving an overview of the progress of the field of saliency detection.

scholarly journals Automatic fish detection in underwater videos by a deep neural network-based hybrid motion learning system

2019 ◽  
Vol 77 (4) ◽  
pp. 1295-1307 ◽  
Author(s):  
Ahmad Salman ◽  
Shoaib Ahmad Siddiqui ◽  
Faisal Shafait ◽  
Ajmal Mian ◽  
Mark R Shortis ◽  
...  
Keyword(s):  
Neural Network ◽  
Hybrid Approach ◽  
Learning System ◽  
Detection Accuracy ◽  
Novel Approach ◽  
Benchmark Datasets ◽  
Fish Detection ◽  
Hybrid Motion ◽  
Candidate Regions ◽  
Detection And Localization

Abstract It is interesting to develop effective fish sampling techniques using underwater videos and image processing to automatically estimate and consequently monitor the fish biomass and assemblage in water bodies. Such approaches should be robust against substantial variations in scenes due to poor luminosity, orientation of fish, seabed structures, movement of aquatic plants in the background and image diversity in the shape and texture among fish of different species. Keeping this challenge in mind, we propose a unified approach to detect freely moving fish in unconstrained underwater environments using a Region-Based Convolutional Neural Network, a state-of-the-art machine learning technique used to solve generic object detection and localization problems. To train the neural network, we employ a novel approach to utilize motion information of fish in videos via background subtraction and optical flow, and subsequently combine the outcomes with the raw image to generate fish-dependent candidate regions. We use two benchmark datasets extracted from a large Fish4Knowledge underwater video repository, Complex Scenes dataset and the LifeCLEF 2015 fish dataset to validate the effectiveness of our hybrid approach. We achieve a detection accuracy (F-Score) of 87.44% and 80.02% respectively on these datasets, which advocate the utilization of our approach for fish detection task.

scholarly journals Detecting Saliency in Infrared Images via Multiscale Local Sparse Representation and Local Contrast Measure

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Xin Wang ◽  
Chunyan Zhang ◽  
Chen Ning ◽  
Yuzhen Zhang ◽  
Guofang Lv
Keyword(s):  
Sparse Representation ◽  
Background Noise ◽  
Saliency Detection ◽  
Infrared Image ◽  
Saliency Map ◽  
Local Contrast ◽  
Infrared Images ◽  
Saliency Maps ◽  
Contrast Measure ◽  
Local Sparse Representation

For infrared images, it is a formidable challenge to highlight salient regions completely and suppress the background noise effectively at the same time. To handle this problem, a novel saliency detection method based on multiscale local sparse representation and local contrast measure is proposed in this paper. The saliency detection problem is implemented in three stages. First, a multiscale local sparse representation based approach is designed for detecting saliency in infrared images. Using it, multiple saliency maps with various scales are obtained for an infrared image. These maps are then fused to generate a combined saliency map, which can highlight the salient region fully. Second, we adopt a local contrast measure based technique to process the infrared image. It divides the image into a number of image blocks. Then these blocks are utilized to calculate the local contrast to generate a local contrast measure based saliency map. In this map, the background noise can be suppressed effectually. Last, to make full use of the advantages of the above two saliency maps, we propose combining them together using an adaptive fusion scheme. Experimental results show that our method achieves better performance than several state-of-the-art algorithms for saliency detection in infrared images.

scholarly journals Automatic segmentation and recognition of red and white cells in stool microscopic images of human

2020 ◽  
Vol 185 ◽  
pp. 03024
Author(s):  
Guanghui Kong ◽  
Zhiyong Wang ◽  
Xiuchao Wan ◽  
Fengjun Xue
Keyword(s):  
Saliency Detection ◽  
Automatic Segmentation ◽  
Texture Features ◽  
Detection Algorithm ◽  
Saliency Map ◽  
Support Vector ◽  
Microscopic Images ◽  
Initial Segmentation ◽  
Low Efficiency ◽  
Watershed Method

Aiming to solve the problem of low efficiency in manually recognizing the red and white cells in stool microscopic images, we propose an automatic segmentation method based on iterative corrosion with marker-controlled watershed segmentation and an automatic recognition method based on support vector machine (SVM) classification. The method first obtains saliency map of the images in HSI and Lab color spaces through saliency detection algorithm, then fuses the salient images to complete the initial segmentation. Next, we segment the red and white cells completely based on the initial segmentation images using marker-controlled watershed algorithm and other complementary methods. According to the differences in geometrical and texture features of red and white cells such as area, perimeter, circularity, energy, entropy, correlation and contrast, we extract them as feature vectors to train SVM and finally complete the classification and recognition of red and white cells. The experimental results indicate that our proposed marker-controlled watershed method can help increase the segmentation and recognition accuracy. Moreover, since it is also less susceptible to the heteromorphic red and white cells, our method is effective and robust.

Sign in / Sign up

Export Citation Format

Share Document