CN101533512B - Method for automatically extracting interesting image regions based on human visual attention system - Google Patents
Method for automatically extracting interesting image regions based on human visual attention system Download PDFInfo
- Publication number
- CN101533512B CN101533512B CN2009100221910A CN200910022191A CN101533512B CN 101533512 B CN101533512 B CN 101533512B CN 2009100221910 A CN2009100221910 A CN 2009100221910A CN 200910022191 A CN200910022191 A CN 200910022191A CN 101533512 B CN101533512 B CN 101533512B
- Authority
- CN
- China
- Prior art keywords
- image
- contrast
- input picture
- pixel
- center
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method for automatically extracting interesting image regions based on a human visual attention system, which mainly solves the problem that the prior method for extracting interesting regions cannot extract a plurality of interesting regions and edge information. The method comprises the following steps: calculating the local brightness contrast, global brightness contrast and edge of an input image; fusing characteristic graphs corresponding to the three characteristics through global nonlinear normalization merging algorithm so as to generate a contrast graph; calculating the position characteristics of the input image so as to establish a weighting graph; establishing a saliency graph corresponding to the input image through the contrast graph and the weighting graph; and segmenting out the interesting regions of the input image according to the saliency graph. The method can effectively extract a plurality of interesting regions in the input image, and is used in the technical field of image analysis and image compression.
Description
Technical field
The present invention relates to extract the method for interesting image regions, particularly extract the method for interesting image regions, be used for graphical analysis and Image Compression field through simulating human vision attention system.
Technical background
Along with the fast development of computer network communication technology, the internet provides information service, and especially image information develops rapidly.
The data of image information amount is huge, and how effectively processing image information becomes the research focus of image information service.For the human visual system, the INFORMATION IS NOT that image provided is of equal importance everywhere.Some zone of image provides people to understand the required main contents of image, is referred to as area-of-interest; And the other zone only provides some less important background content.Searching is published picture as area-of-interest, and graphical analysis, compression of images etc. is all had important meaning.
W.Osberger and A.J.Maeder are at article " Automatic identification ofperceptually important regions in the image "; In Proc.Int ' l Conf.Pattern Recognition; 1998; Among the pp.17-20, a kind of method of extracting area-of-interest based on human visual attention system is proposed.This method is come the analysis image characteristic factor with the basis that is divided into of image, confirms area-of-interest then.Therefore partitioning algorithm is depended in the success or failure of this method.People such as Itti Laurent are at article " A model of saliency-based visual attention for rapid scene analysis "; IEEE Trans.Pattern Analysis and Machine Intelligence; Vol.20, no.11, pp1254-1259; In 1998, a kind of method of extracting area-of-interest through these three characteristic factors of color, direction and brightness of analyzing each pixel is proposed.This method is easy to analyze and realize, and can accurately orient the approximate location of area-of-interest.Because the characteristic that adopts the gaussian pyramid model to come analysis image in this method, this is a kind of algorithm of down-sampling, and therefore unavoidable meeting loses some specifying informations of image in the operation, like marginal information etc.C.M.Priviter and L.W.Stark are at article " Algorithms for definingvisual region-of-interesting:Comparison with eye fixations "; IEEETrans.Pattern Anal.Machine Intell.vol.22; No.9, pp.970-982 is in 2000; Proposed based on the single characteristic of image, the segmentation algorithm directly extracts area-of-interest from image.This method is simple to operate, is easy to realize.For simple image, can effectively extract its area-of-interest; But for the image with complex background, this method effect is poor.SooYeong Kwak etc. are at article " Automatic salient-object extraction using the contrast map andsalient point "; In Advances in Multimedia Information Processing-PCM2004.vol.3332 of LNCS; Pp.138-145; Springer Berlin. and K.B.Chul etc. are at article " Automatic object-of-interest segmentation fromnature images ", in PROC.Int ' l Conf Pattern Recognition, 2006; Among the pp.45-48, the application focus window of proposition detects the method for well-marked target.These methods therefore in operating process, also can lose detailed information such as edge, and when a plurality of target occurring simultaneously in the image, application focus window method detect a plurality of well-marked targets and can lose efficacy owing to all be to adopt the model of Itti to set up remarkable figure.
Summary of the invention
The objective of the invention is to overcome the defective and the deficiency that exist in the above-mentioned prior art; A kind of method for automatically extracting interesting image regions based on human visual attention system simple to operate is provided; Have the area-of-interest of the image of complex background with effective extraction, and a plurality of target objects that occur in the image.
For realizing above-mentioned purpose; Simulating human vision attention of the present invention system; Influence human visual system's rudimentary factor and senior factor in the analysis image, the contrast figure that these three the rudimentary factors in the local luminance contrast of the main analyzing influence vision system of the present invention, overall luminance contrast and edge are set up, and the weight map of this senior factor foundation of position; Set up significantly figure in conjunction with contrast figure and weight map, performing step is following:
(1) these three low-level features factors of local luminance contrast, overall luminance contrast and edge of each pixel of difference calculating input image;
(2) use these three low-level features factors of local luminance contrast, overall luminance contrast and edge that overall non-linear normalizing merge algorithm merges input picture, generate contrast figure;
(3), obtain the corresponding weight map of input picture according to the weight of each pixel of input picture this pixel of the position calculation in image in image;
(4), generate the remarkable figure of input picture by described contrast figure and weight map;
(5) area-of-interest of input picture is confirmed in the indication of the remarkable figure of basis.
Described calculating local luminance contrast is the luminance difference that calculates in each pixel subrange peripheral with it, and calculation procedure is following:
(2a) adopt Gaussian function that input picture is done smoothing processing:
Wherein, I is the former figure of input picture, and G (σ) is a Gaussian function, I (σ
i) be the image after the smoothing processing;
(2b) with Gaussian difference function calculation pixel with it absolute brightness difference in peripheral little field:
DoG(x,y,σ
1,σ
2)=|I(x,y,σ
1)-I(x,y,σ
2)|
Wherein: σ
iValue decision central pixel point and the degree of association of peripheral little field interior pixel point, establish σ here
1=1, I (x, y, σ
1) be through first variances sigma
1The pixel of image after the Gaussian function smoothing processing, I (x, y, σ
2) be through second variances sigma
2The pixel of image after the Gaussian function smoothing processing, DoG (x, y, σ
1, σ
2) be the local luminance contrast value;
(2 c) gets two different σ
2Value obtains two width of cloth luminance difference figure DoG1 and DoG2 respectively, through overall non-linear normalizing fusion method this two width of cloth image is merged, and obtains local luminance contrast figure.
Described according to the weight of each pixel of input picture this pixel of the position calculation in image in image, utilize following formula to calculate:
Wherein ' center ' is picture centre
zone; R is point (x; Y) to the distance of input picture central area, R is the distance of input picture edge to its center.
The present invention has following advantage:
1) the present invention according to influencing a plurality of factor analysis input pictures that the human vision system is paid close attention in the image, extracts the human eye area-of-interest, so can accurately extract the input picture area-of-interest owing to adopt the method for simulating human vision system.
2) each pixel that the present invention is based on input picture is done computing, so design process is simple, is easy to realize.
3) the present invention is owing to these three characteristics of local luminance contrast, overall luminance contrast and edge of analyzing each pixel of input picture, so can extract the marginal information of object.
4) the present invention is owing to adopt according to the remarkable indication of figure and seek area-of-interest, thereby can extract a plurality of area-of-interests simultaneously.
Embodiment
With reference to Fig. 1, concrete performing step of the present invention is following:
Step 1, these three low-level features factors of local luminance contrast, overall luminance contrast and edge of each pixel of calculating input image respectively.
(1a) calculate the local luminance contrast
Gaussian difference (Differential of Gaussian) function can be represented central pixel point and its difference between the pixel of field on every side effectively, so adopt the Gaussian difference function to calculate the luminance contrast in the regional area.
With reference to Fig. 2, the calculating of local luminance contrast is following among the present invention:
At first, adopt Gaussian function that input picture is done smoothing processing:
Wherein, I is the former figure of input picture, and G (σ) is a Gaussian function, I (σ
i) be the image after the smoothing processing,
Be the convolution symbol;
Secondly, employing Gaussian difference function calculation pixel is absolute brightness difference in peripheral little field with it, works as σ
iWhen big, image is fuzzy more by smoothing processing from little change for value, and each central pixel point has also comprised the information of more surrounding pixel point simultaneously, when getting different σ
iDuring value, the Gaussian difference function is:
DoG(x,y;σ
1,σ
2)=|I(x,y;σ
1)-I(x,y;σ
2)| (A)
I (x, y, σ wherein
1) be through first variances sigma
1The pixel of image after the pairing Gaussian convolution nuclear G1 smoothing processing, I (x, y, σ
2) be through second variances sigma
2The pixel of image after the Gaussian function smoothing processing, we establish σ here
1=1, and σ
1≠ σ
2, DoG (x, y, σ
1, σ
2) be that the Gaussian difference function is in (x, the value of y) locating;
Then, when utilizing in the Gaussian difference function detected image target object, its effect and σ
2The size of value and target object relevant, for the little target object of size, get its corresponding little σ
2Value, it is better that local contrast detects effect; And, get its big σ for the big target object of size
2Value, it is better that local contrast detects effect; In having no, under the situation of target object priori, get its minimum σ about image
2 1Value and maximum σ thereof
2 2Value obtains two Gaussian convolution nuclear G21 and G22, obtains two width of cloth luminance difference figure DoG1 and DoG2 according to formula (A),
At last, merge this two width of cloth luminance difference figure DoG1 and DoG2, obtain local contrast with the non-linear normalizing act of union.
(1b) calculate overall luminance contrast
When certain regional brightness is protruded in view picture figure among the width of cloth figure, certainly will attract observer's notice, overall luminance contrast is represented the contrast in brightness of each pixel and full figure, computing formula is following:
L wherein
m(x is that (x y) is the average gray value in 7 * 7 fields at center, L with some y)
MIt is the average gray value of full figure.
(1c) edge calculation zone
Fringe region is the highstrung zone of human visual system in the image, adopts canny operator extraction edge of image characteristic usually, and threshold value is made as 0.5.
Step 2 is set up the contrast figure of input picture.
The contrast figure that sets up input picture carries out through overall non-linear normalizing merge algorithm; This algorithm can overallly promote those only has the characteristic pattern of minority peak value; Overall situation compacting those have a lot of places all to have the characteristic pattern of similar big small leak in entire image, and its concrete steps are following:
(2a) will normalize to same dynamic range (0-1) by step (1a), (1b) and the local luminance contrast that (1c) calculates figure, overall luminance contrast figure and outline map;
(2b) seek the global maximum M of this three width of cloth figure respectively, and calculate all local peaked mean value M;
(2c) respectively to the corresponding amplification (M-M) of this three width of cloth figure overall situation
2Doubly, obtain figure after three width of cloth normalization;
(2d) three width of cloth figure additions after the normalization are obtained luminance contrast figure.
Step 3 is set up the weight map of input picture.
The human visual system pays close attention to the central area of input picture more, so the central area pixel weights of input picture are big, and the pixel weights of its fringe region are little, and concrete computing formula is following:
Wherein ' center ' is picture centre
zone; R is point (x; Y) to the distance of input picture central area, R is the distance of edge to the input picture center.
Step 4 is set up the remarkable figure of input picture.
According to the contrast figure and the weight map of above-mentioned steps 2 and step 3 gained input picture, the remarkable figure that sets up the image correspondence is:
SM(x,y)=CM(x,y)×W
center(x,y)
Wherein, CM is the contrast figure of input picture, W
CenterWeight map for input picture.
The brightness value of each point was represented the susceptibility of its correspondence image pixel in should significantly scheming, and significantly the brightness value of certain point is big more among the figure, representes that this conspicuousness in former figure is high more, attracts the vision system more attention.
Step 5, the area-of-interest of extraction input picture.
(5a) according to significantly scheming the characteristics that the high place of brightness attracts the vision system more concern, setting threshold extracts the high zone of brightness value among the remarkable figure:
Wherein, ROI is the figure after the input picture binaryzation, 1 representative effective coverage, and 0 represents inactive area; T is a segmentation threshold, and we establish the T value for peaked half the among the SM figure here.
(5b) obtain a width of cloth binary map according to formula (B), this binary map is made morphology handle, removing the interfered cell territory that some cause because of noise, its value is that 1 zone is area-of-interest in the binary map after treatment.
Claims (2)
1. the method for automatically extracting interesting image regions based on human visual attention system comprises the steps:
(1) these three low-level features factors of local luminance contrast, overall luminance contrast and edge of each pixel of difference calculating input image;
(2) use these three low-level features factors of local luminance contrast, overall luminance contrast and edge that overall non-linear normalizing merge algorithm merges input picture, generate contrast figure;
(3) utilize following formula to calculate the weights W of this pixel in image according to the position of each pixel of input picture in image
Center(x y), obtains the corresponding weight map of input picture:
Wherein ' center ' is picture centre
zone; R is point (x; Y) to the distance of input picture central area, R is the distance of input picture edge to its center;
(4), generate the remarkable figure of input picture by described contrast figure and weight map;
(5) area-of-interest of input picture is confirmed in the indication of the remarkable figure of basis.
2. the method for claim 1, the described calculating local luminance of its step (1) contrast is the luminance difference that calculates in each pixel subrange peripheral with it, calculation procedure is following:
(2a) adopt Gaussian function that input picture is done smoothing processing:
Wherein, I is the former figure of input picture, G (σ
i) be Gaussian function, I (σ
i) be the image after the smoothing processing;
(2b) with Gaussian difference function calculation pixel with it absolute brightness difference in peripheral little field:
DoG(x,y,σ
1,σ
2)=|I(x,y,σ
1)-I(x,y,σ
2)|
Wherein: σ
iValue decision central pixel point and the degree of association of peripheral little field interior pixel point, establish σ here
1=1,
I (x, y, σ
1) be through first variances sigma
1The pixel of image after the Gaussian function smoothing processing,
I (x, y, σ
2) be through second variances sigma
2The pixel of image after the Gaussian function smoothing processing, DoG (x, y, σ
1, σ
2) be the local luminance contrast value;
(2c) get two different σ
2Value obtains two width of cloth luminance difference figure DoG1 and DoG2 respectively, through overall non-linear normalizing fusion method this two width of cloth image is merged, and obtains local luminance contrast figure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2009100221910A CN101533512B (en) | 2009-04-24 | 2009-04-24 | Method for automatically extracting interesting image regions based on human visual attention system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2009100221910A CN101533512B (en) | 2009-04-24 | 2009-04-24 | Method for automatically extracting interesting image regions based on human visual attention system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101533512A CN101533512A (en) | 2009-09-16 |
CN101533512B true CN101533512B (en) | 2012-05-09 |
Family
ID=41104091
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2009100221910A Expired - Fee Related CN101533512B (en) | 2009-04-24 | 2009-04-24 | Method for automatically extracting interesting image regions based on human visual attention system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101533512B (en) |
Families Citing this family (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2009357597B2 (en) * | 2009-12-30 | 2015-11-05 | Nokia Technologies Oy | Methods and apparatuses for facilitating content-based image retrieval |
CN101807300B (en) * | 2010-03-05 | 2012-07-25 | 北京智安邦科技有限公司 | Target fragment region merging method and device |
CN101847264B (en) * | 2010-05-28 | 2012-07-25 | 北京大学 | Image interested object automatic retrieving method and system based on complementary significant degree image |
CN102005057B (en) * | 2010-11-17 | 2012-07-25 | 中国科学院声学研究所 | Method for detecting region of interest of color image |
CN102036073B (en) * | 2010-12-21 | 2012-11-28 | 西安交通大学 | Method for encoding and decoding JPEG2000 image based on vision potential attention target area |
CN102063623B (en) * | 2010-12-28 | 2012-11-07 | 中南大学 | Method for extracting image region of interest by combining bottom-up and top-down ways |
FR2971861B1 (en) * | 2011-02-21 | 2013-02-22 | Essilor Int | METHOD FOR DETERMINING AT LEAST ONE GEOMETRIC-PHYSIOMY PARAMETER ASSOCIATED WITH THE MOUNTING OF AN OPHTHALMIC LENS IN A BEARER-FITTED GOGGING MOUNT |
CN102129693B (en) * | 2011-03-15 | 2012-07-25 | 清华大学 | Image vision significance calculation method based on color histogram and global contrast |
CN102158712B (en) * | 2011-03-22 | 2012-10-24 | 宁波大学 | Multi-viewpoint video signal coding method based on vision |
WO2012162878A1 (en) * | 2011-05-30 | 2012-12-06 | Technicolor (China) Technology Co., Ltd. | Method and device for determining saliency value of current block of image |
CN102509099B (en) * | 2011-10-21 | 2013-02-27 | 清华大学深圳研究生院 | Detection method for image salient region |
CN102509299B (en) * | 2011-11-17 | 2014-08-06 | 西安电子科技大学 | Image salient area detection method based on visual attention mechanism |
CN102521595B (en) * | 2011-12-07 | 2014-01-15 | 中南大学 | Method for extracting image region of interest based on eye movement data and bottom-layer features |
CN102855025B (en) * | 2011-12-08 | 2015-06-17 | 西南科技大学 | Optical multi-touch contact detection method based on visual attention model |
CN102568016B (en) * | 2012-01-03 | 2013-12-25 | 西安电子科技大学 | Compressive sensing image target reconstruction method based on visual attention |
JP5750381B2 (en) * | 2012-02-13 | 2015-07-22 | 株式会社日立製作所 | Region extraction processing system |
CN104156938B (en) * | 2013-05-14 | 2017-08-11 | 五邑大学 | A kind of image connectivity region description method and its application process in image registration |
CN103514580B (en) * | 2013-09-26 | 2016-06-08 | 香港应用科技研究院有限公司 | For obtaining the method and system of the super-resolution image that visual experience optimizes |
CN104658004B (en) * | 2013-11-20 | 2018-05-15 | 南京中观软件技术有限公司 | A kind of air refuelling auxiliary marching method based on video image |
CN104079934B (en) * | 2014-07-14 | 2017-02-15 | 武汉大学 | Method for extracting regions of interest in real-time video communication |
CN106828460A (en) * | 2017-03-02 | 2017-06-13 | 深圳明创自控技术有限公司 | A kind of safe full-automatic pilot for prevention of car collision |
CN108960247B (en) * | 2017-05-22 | 2022-02-25 | 阿里巴巴集团控股有限公司 | Image significance detection method and device and electronic equipment |
CN109242869B (en) * | 2018-09-21 | 2021-02-02 | 安徽科大讯飞医疗信息技术有限公司 | Image instance segmentation method, device, equipment and storage medium |
CN109615635A (en) * | 2018-12-06 | 2019-04-12 | 厦门理工学院 | The method and device of quality sorting is carried out to strawberry based on image recognition |
CN111414904B (en) * | 2019-01-08 | 2023-12-01 | 北京地平线机器人技术研发有限公司 | Method and device for processing data of region of interest |
CN110267041B (en) * | 2019-06-28 | 2021-11-09 | Oppo广东移动通信有限公司 | Image encoding method, image encoding device, electronic device, and computer-readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1999042950A1 (en) * | 1998-02-23 | 1999-08-26 | Arch Development Corporation | Lung nodule detection using edge gradient histograms |
US20080143739A1 (en) * | 2006-12-13 | 2008-06-19 | Harris Jerry G | Method and System for Dynamic, Luminance-Based Color Contrasting in a Region of Interest in a Graphic Image |
CN101282479A (en) * | 2008-05-06 | 2008-10-08 | 武汉大学 | Method for encoding and decoding airspace with adjustable resolution based on interesting area |
CN101378480A (en) * | 2007-08-31 | 2009-03-04 | 卡西欧计算机株式会社 | Tone correcting apparatus, tone correcting method and tone correcting programe |
-
2009
- 2009-04-24 CN CN2009100221910A patent/CN101533512B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1999042950A1 (en) * | 1998-02-23 | 1999-08-26 | Arch Development Corporation | Lung nodule detection using edge gradient histograms |
US20080143739A1 (en) * | 2006-12-13 | 2008-06-19 | Harris Jerry G | Method and System for Dynamic, Luminance-Based Color Contrasting in a Region of Interest in a Graphic Image |
CN101378480A (en) * | 2007-08-31 | 2009-03-04 | 卡西欧计算机株式会社 | Tone correcting apparatus, tone correcting method and tone correcting programe |
CN101282479A (en) * | 2008-05-06 | 2008-10-08 | 武汉大学 | Method for encoding and decoding airspace with adjustable resolution based on interesting area |
Non-Patent Citations (1)
Title |
---|
王艳娟等.图像感兴趣区域自动提取算法.《科学技术与工程》.2007,第7卷(第12期),2867-2871. * |
Also Published As
Publication number | Publication date |
---|---|
CN101533512A (en) | 2009-09-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101533512B (en) | Method for automatically extracting interesting image regions based on human visual attention system | |
Kheradmandi et al. | A critical review and comparative study on image segmentation-based techniques for pavement crack detection | |
Maldonado Jr et al. | Automatic green fruit counting in orange trees using digital images | |
CN103902977B (en) | Face identification method and device based on Gabor binary patterns | |
EP1693782B1 (en) | Method for facial features detection | |
CN101599124B (en) | Method and device for segmenting characters from video image | |
Lin et al. | Robust license plate detection using image saliency | |
Liu et al. | Automatic segmentation of focused objects from images with low depth of field | |
CN101944178B (en) | Significant region extraction method for intelligent monitoring | |
CN110415208A (en) | A kind of adaptive targets detection method and its device, equipment, storage medium | |
US20180218496A1 (en) | Automatic Detection of Cutaneous Lesions | |
US20210233245A1 (en) | Computer-implemented method of detecting foreign object on background object in an image, apparatus for detecting foreign object on background object in an image, and computer-program product | |
Dhar et al. | An efficient real time moving object detection method for video surveillance system | |
Lei et al. | Evaluation and modeling of depth feature incorporated visual attention for salient object segmentation | |
Gao et al. | Agricultural image target segmentation based on fuzzy set | |
Hitimana et al. | Automatic estimation of live coffee leaf infection based on image processing techniques | |
CN106446920B (en) | A kind of stroke width transform method based on gradient amplitude constraint | |
CN104318216A (en) | Method for recognizing and matching pedestrian targets across blind area in video surveillance | |
CN104063682A (en) | Pedestrian detection method based on edge grading and CENTRIST characteristic | |
CN102156879B (en) | Human target matching method based on weighted terrestrial motion distance | |
Fang et al. | 1-D barcode localization in complex background | |
Arévalo et al. | Detecting shadows in QuickBird satellite images | |
CN107146230A (en) | Merge the SAR image segmentation method of cost based on K S distances | |
Zhang et al. | Finger-vein recognition based on gradient distribution and self-adaptive recovery model | |
Konstantinidis et al. | A probabilistic feature fusion for building detection in satellite images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120509 Termination date: 20190424 |
|
CF01 | Termination of patent right due to non-payment of annual fee |