Improved Saliency Detection Method Research Articles

An improved saliency detection method based on hypercomplex Fourier transform

Saliency detection is a challenging direction in the field of computer vision. It can help us quickly obtain important information of image and video, and plays an important role in image compression, image segmentation, target recognition and other applications. Based on the Hypercomplex Fourier Transform (HFT) model, median filter and threshold segmentation are employed to obtain the image salient region, which solves the problem that the boundary is not clear and multiple targets cannot be separated, and achieves more accurate and stable detection effect.

Infrared and visible image fusion algorithm based on saliency detection and adaptive double-channel spiking cortical model

Based on the saliency detection which effectively extracts the saliency information of the image and the adaptive double-channel spiking cortical model (ADSCM) which has the advantages of global coupling, pulse synchronization, less parameters and high computational efficiency, which can well process information in dark areas, we proposed a new infrared and visible image fusion algorithm. Firstly, the infrared and visible images are decomposed into the base layer and the detail layers through the rolling guidance filter (RGF). Secondly, the base layer is fused with an improved saliency detection method, and the detail layers are fused by a directional gradient sum and an improved ADSCM. The experimental results show that the proposed method can also fully extract the target information of the infrared image while preserving the visible background information, in which the fusion effect is better than the traditional fusion algorithms.

Supervised Saliency Map Driven Segmentation of Lesions in Dermoscopic Images.

Lesion segmentation is the first step in most automatic melanoma recognition systems. Deficiencies and difficulties in dermoscopic images such as color inconstancy, hair occlusion, dark corners, and color charts make lesion segmentation an intricate task. In order to detect the lesion in the presence of these problems, we propose a supervised saliency detection method tailored for dermoscopic images based on the discriminative regional feature integration (DRFI). A DRFI method incorporates multilevel segmentation, regional contrast, property, background descriptors, and a random forest regressor to create saliency scores for each region in the image. In our improved saliency detection method, mDRFI, we have added some new features to regional property descriptors. Also, in order to achieve more robust regional background descriptors, a thresholding algorithm is proposed to obtain a new pseudo-background region. Findings reveal that mDRFI is superior to DRFI in detecting the lesion as the salient object in dermoscopic images. The proposed overall lesion segmentation framework uses detected saliency map to construct an initial mask of the lesion through thresholding and postprocessing operations. The initial mask is then evolving in a level set framework to fit better on the lesion's boundaries. The results of evaluation tests on three public datasets show that our proposed segmentation method outperforms the other conventional state-of-the-art segmentation algorithms and its performance is comparable with most recent approaches that are based on deep convolutional neural networks.

Saliency Detection Method Using Hypergraphs on Adaptive Multiscales

Saliency detection plays an important role in the fields of image processing and computer vision. We present an improved saliency detection method by means of hypergraphs on adaptive multi-scales (HAM). It first adjusts adaptively the ranges of pixel-values in ${R}, {G}, {B}$ channels in an input image and uses the three ranges to determine adaptive scales for the construction of hypergraphs. And then, the image is modeled as multiple hypergraphs on adaptive scales in which hyper-edges are clustered by means of the agglomerative mean-shift method. The HAM method can get more single-scale hypergraphs and thus has higher accuracy than the previous ones because hypergraphs are constructed on adaptive multi-scales instead of fixed scales. Extensive experiments on the published benchmark datasets demonstrate that the HAM method has improved the performance of detecting salient objects in input images, especially for the images with narrow ranges of pixel-values.

Robust and automatic cell detection and segmentation from microscopic images of non‐setae phytoplankton species

Saliency-based marker-controlled watershed method was proposed to detect and segment phytoplankton cells from microscopic images of non-setae species. This method first improved IG saliency detection method by combining saturation feature with colour and luminance feature to detect cells from microscopic images uniformly and then produced effective internal and external markers by removing various specific noises in microscopic images for efficient performance of watershed segmentation automatically. The authors built the first benchmark dataset for cell detection and segmentation, including 240 microscopic images across multiple phytoplankton species with pixel-wise cell regions labelled by a taxonomist, to evaluate their method. They compared their cell detection method with seven popular saliency detection methods and their cell segmentation method with six commonly used segmentation methods. The quantitative comparison validates that their method performs better on cell detection in terms of robustness and uniformity and cell segmentation in terms of accuracy and completeness. The qualitative results show that their improved saliency detection method can detect and highlight all cells, and the following marker selection scheme can remove the corner noise caused by illumination, the small noise caused by specks, and debris, as well as deal with blurred edges.

An improved saliency detection method based on non-uniform quantification and channel-weighted color distance

We propose a non-uniform quantification method for RGB channels based on the visual sensitivities of human eyes to the red, green and blue colors, and give weights to RGB channels which are used to compute the channel-weighted color distances. Furthermore, we design a saliency detection method using the non-uniform quantification method and the channel-weighted color distances measurement. We first quantify the values in RGB channels in different step-lengths and determine the weights wr, wg and wb based on the visual sensitivities of human eyes to the three-primary colors. And then we convert the quantified image into that in Lab color space, which are segmented into some regions, and compute the channel-weighted color distance using the weights wL, wa and wb, which are computed from the weights wr, wg and wb and the transformation from RGB color space to Lab color space. The saliency of each region is computed using the weighted distances and spatial weights. The proposed non-uniform quantification method and the channel-weighted color distance measurement can be used for the applications based on color features in the field of image processing and computer vision. Experimental results show that our methods can improve the efficiency and performance of saliency detection to some extent.

S-CNN-BASED SHIP DETECTION FROM HIGH-RESOLUTION REMOTE SENSING IMAGES

Reliable ship detection plays an important role in both military and civil fields. However, it makes the task difficult with high-resolution remote sensing images with complex background and various types of ships with different poses, shapes and scales. Related works mostly used gray and shape features to detect ships, which obtain results with poor robustness and efficiency. To detect ships more automatically and robustly, we propose a novel ship detection method based on the convolutional neural networks (CNNs), called SCNN, fed with specifically designed proposals extracted from the ship model combined with an improved saliency detection method. Firstly we creatively propose two ship models, the “V” ship head model and the “||” ship body one, to localize the ship proposals from the line segments extracted from a test image. Next, for offshore ships with relatively small sizes, which cannot be efficiently picked out by the ship models due to the lack of reliable line segments, we propose an improved saliency detection method to find these proposals. Therefore, these two kinds of ship proposals are fed to the trained CNN for robust and efficient detection. Experimental results on a large amount of representative remote sensing images with different kinds of ships with varied poses, shapes and scales demonstrate the efficiency and robustness of our proposed S-CNN-Based ship detector.

S-CNN-BASED SHIP DETECTION FROM HIGH-RESOLUTION REMOTE SENSING IMAGES

Abstract. Reliable ship detection plays an important role in both military and civil fields. However, it makes the task difficult with high-resolution remote sensing images with complex background and various types of ships with different poses, shapes and scales. Related works mostly used gray and shape features to detect ships, which obtain results with poor robustness and efficiency. To detect ships more automatically and robustly, we propose a novel ship detection method based on the convolutional neural networks (CNNs), called SCNN, fed with specifically designed proposals extracted from the ship model combined with an improved saliency detection method. Firstly we creatively propose two ship models, the “V” ship head model and the “||” ship body one, to localize the ship proposals from the line segments extracted from a test image. Next, for offshore ships with relatively small sizes, which cannot be efficiently picked out by the ship models due to the lack of reliable line segments, we propose an improved saliency detection method to find these proposals. Therefore, these two kinds of ship proposals are fed to the trained CNN for robust and efficient detection. Experimental results on a large amount of representative remote sensing images with different kinds of ships with varied poses, shapes and scales demonstrate the efficiency and robustness of our proposed S-CNN-Based ship detector.