scispace - formally typeset
Patent

Depth study based method for detecting salient regions in natural image

Han Junwei, +3 more
TLDR
In this article, a depth study method for detecting salient regions in a natural image is proposed, where a certain number of pictures are selected from a natural images database, basic features of the images are extracted to form a training sample, subsequently, the extracted features are studied by using a depth-study model so as to obtain enhanced advanced features which are more abstractive and more distinguishable, and finally, a classifier is trained by using studied features.
Abstract: 
The invention relates to a depth study method for detecting salient regions in a natural image. During a training phase, a certain number of pictures are selected from a natural image database, basic features of the images are extracted to form a training sample, subsequently, the extracted features are studied by using a depth study model so as to obtain enhanced advanced features which are more abstractive and more distinguishable, and finally, a classifier is trained by using studied features. During a testing phase, as to any test image, firstly, the base features are extracted, secondly, the enhanced advanced features are extracted by using the trained depth model, finally, salience is predicted by using the classifier, and a predicted value of each pixel point serves as a salient value of the point. In such a way, a salient image of the whole image can be obtained, and the higher the salient value is, the more salient the image is.

read more

Citations
More filters
Patent

Rapid target detection method based on convolutional neural network

Hanzi Wang, +2 more
TL;DR: In this article, the authors proposed a rapid target detection method based on a convolutional neural network and relates to computer vision technology, which consists of the following steps: training CNN parameters by utilizing a training set, solving the problem of max-pooling losing feature by using an expander graph and generating a discriminative complete feature graph, and estimating the generalization error of the linear classifier on the discriminator by using a probable approximately correct learning framework.
Patent

Target detection method and device

Jia Huizhu, +3 more
TL;DR: In this article, a target detection method and device are used for solving the problem that according to an existing pedestrian detecting method, the detection precision is low when multiple targets are detected.
Patent

RGBD image salience detection method based on hypergraph model

Ren Jianqiang, +1 more
TL;DR: Zhang et al. as discussed by the authors proposed an RGBD image salience detection method based on a hypergraph model, which includes conducting hyperpixel segmentation for a color image to be detected and a depth image, calculating neighborhood depth contrast graphs for each hyperpixel area of the depth image and extracting hyper pixel areas on the boundary of the image to construct a boundary background hyperedge.
Patent

Apparatus and method for processing image

Ye-Hoon Kim, +2 more
TL;DR: In this paper, an image processing method for estimating a region of interest based on information of interest learned by a data recognition model satisfying a certain condition from among a plurality of data recognition models and for setting a focus are provided.
Patent

Method for detecting image saliency region for deep learning

Guo Lihua, +1 more
TL;DR: In this article, a method for detecting an image saliency region for deep learning combines image multi-scale features and image segmentation information of the deep learning, and may achieve good salience region detection performance at a fast processing speed.
References
More filters
Journal ArticleDOI

A model of saliency-based visual attention for rapid scene analysis

Laurent Itti, +2 more
- 01 Nov 1998 - 
TL;DR: In this article, a visual attention system inspired by the behavior and the neuronal architecture of the early primate visual system is presented, where multiscale image features are combined into a single topographical saliency map.
Patent

Computation of intrinsic perceptual saliency in visual environments, and applications

Christof Koch, +1 more
TL;DR: In this article, the image is analyzed at multiple spatial scales and over multiple feature channels to determine the likely saliency of different portions of the image. And the detection may be improved by second order statistics, e.g. mean and the standard deviations of different image portions relative to other portions.
Patent

Detection method for image salient region

Haoqian Wang, +3 more
TL;DR: In this article, a detection method for an image salient region, which comprises the following steps: 1) carrying out color space conversion; 2) partitioning to divide; 3) respectively determining the initial saliency values of N pixel blocks; 4) correcting the initial Saliency values obtained in the step 3) by the color distance of each pixel block in a CIELab color space to obtain the saliency value of the Npixel blocks.