CN103632153B - Region-based image saliency map extracting method - Google Patents

Abstract

The invention discloses a region-based image saliency map extracting method. The method includes: firstly, calculating a global color histogram of an image to obtain an image saliency map based on the global color histogram; secondly, adopting superpixel segmentation technology to segment the image, calculating color contrast and space sparsity of each region, and weighting by the aid of similarity among the regions to obtain an image saliency map based on the region color contrast and an image saliency map based on the region space sparsity; finally, fusing the image saliency map based on the global color histogram, the image saliency map based on the region color contrast and the image saliency map based on the region space sparsity to obtain a final image saliency map. The method has the advantage that the obtained image saliency map can well reflect saliency changes of global and local regions, and conforms to image saliency semantic features.

Description

A kind of image saliency map extracting method based on region

Technical field

The present invention relates to the processing method of a kind of picture signal, especially relate to a kind of image saliency map based on region and carry Access method.

Background technology

Receive and in information processing in human vision, due to brain resource-constrained and external environment information importance district Not, in processing procedure, human brain environmental information to external world is not make no exception, but shows selection feature.People are seeing When seeing image or video segment, attention is not evenly distributed to each region of image, but pays close attention to some marking area Du Genggao.How marking area high for Saliency map in video being detected and to be extracted is computer vision and based on interior One important research contents of the field of video retrieval held.

Existing notable graph model is a kind of selective attention model simulating organism vision noticing mechanism, and it is by meter Calculate each pixel in terms of color, brightness, direction with the contrast of periphery background, and the saliency value of all pixels is constituted one Zhang Xianzhu schemes, but this kind of method can not extract image saliency map information well, this is because based on pixel notable special Levy the notable semantic feature that can not reflect well when human eye is watched, and marked feature based on region can be effectively improved How the stability extracted and accuracy, therefore, carry out region segmentation to image, how to put forward the feature of regional Take, how the marked feature of regional is described, how between significance and region and the region of gauge region itself Significance, be all notable figure based on region is extracted in need the problem researched and solved.

Summary of the invention

The technical problem to be solved is to provide one and meets notable semantic feature, and has higher extracted stability Image saliency map extracting method based on region with accuracy.

The present invention solves the technical scheme that above-mentioned technical problem used: a kind of image saliency map based on region is extracted Method, it is characterised in that comprise the following steps:

1. pending source images is designated as { I_i(x, y) }, wherein, i=1,2,3,1≤x≤W, 1≤y≤H, W represent { I_i (x, y) } width, H represents { I_i(x, y) } height, I_i(x y) represents { I_i(x, y) } in coordinate position be (x, pixel y) The color value of i-th component, the 1st component is that R component, the 2nd component are G component and the 3rd component is B component；

First { I is obtained_i(x, y) } quantized image and the global color histogram of quantized image, then according to { I_i(x, Y) quantized image }, obtains { I_i(x, y) } in the color category of each pixel, further according to { I_i(x, y) } quantized image Global color histogram and { I_i(x, y) } in the color category of each pixel, obtain { I_i(x, y) } based on the overall situation face The image saliency map of Color Histogram, is designated as { HS (x, y) }, wherein, HS (x, y) represent that in { HS (x, y) }, coordinate position is (x, y) The pixel value of pixel, also represent { I_i(x, y) } in coordinate position be (x, pixel y) based on global color histogram Saliency value；

3. use super-pixel cutting techniques by { I_i(x, y) } it is divided into the region of M non-overlapping copies, then by { I_i(x,y)} Again it is expressed as the set in M region, is designated as { SP_h, then calculate { SP_hThe similarity between regional in }, by { SP_h} In pth region and q-th region between similarity be designated as Sim (SP_p,SP_q), wherein, M >=1, SP_hRepresent { SP_hIn } The h region, 1≤h≤M, 1≤p≤M, 1≤q≤M, p ≠ q, SP_pRepresent { SP_hPth region in }, SP_qRepresent {SP_hQ-th region in }；

4. according to { SP_hThe similarity between regional in }, obtains { I_i(x, y) } based on field color contrast Image saliency map, be designated as { NGC (x, y) }, wherein, (x y) represents that in { NGC (x, y) }, coordinate position is (x, picture y) to NGC The pixel value of vegetarian refreshments；

5. according to { SP_hThe similarity between regional in }, obtains { I_i(x, y) } openness based on regional space Image saliency map, be designated as { NSS (x, y) }, wherein, (x y) represents that in { NSS (x, y) }, coordinate position is (x, picture y) to NSS The pixel value of vegetarian refreshments；

6. to { I_i(x, y) } image saliency map based on global color histogram { HS (x, y) }, { I_i(x, y) } based on The image saliency map of field color contrast NGC (x, y) } and { I_i(x, y) } the image openness based on regional space notable Figure { NSS (x, y) } merge, obtain { I_i(x, y) } final image saliency map, be designated as { Sal (x, y) }, will Sal (x, Y) in } coordinate position be (x, the pixel value of pixel y) be designated as Sal (x, y), Sal (x, y)=HS (x, y) × NGC (x, y) × NSS(x,y)。

Described step detailed process 2. is:

2.-1, to { I_i(x, y) } in the color value of each component of each pixel quantify respectively, obtain { I_i (x, y) } quantized image, be designated as { P_i(x, y) }, by { P_i(x, y) } in coordinate position be (x, the i-th component of pixel y) Color value be designated as P_i(x, y),Wherein, symbolFor rounding downwards symbol；

2.-2, { P is calculated_i(x, y) } global color histogram, be designated as H (k) | 0≤k≤4095}, wherein, H (k) table Show { P_i(x, y) } in belong to the number of all pixels of kth kind color；

2.-3, according to { P_i(x, y) } in the color value of each component of each pixel, calculate { I_i(x, y) } in corresponding The color category of pixel, by { I_i(x, y) } in coordinate position be that (x, the color category of pixel y) is designated as k_xy, k_xy=P₃ (x,y)×256+P₂(x,y)×16+P₁(x, y), wherein, P₃(x y) represents { P_i(x, y) } in coordinate position be (x, picture y) The color value of the 3rd component of vegetarian refreshments, P₂(x y) represents { P_i(x, y) } in coordinate position be (x, 2nd point of pixel y) The color value of amount, P₁(x y) represents { P_i(x, y) } in coordinate position be (x, the color value of the 1st component of pixel y)；

2.-4, { I is calculated_i(x, y) } in the saliency value based on global color histogram of each pixel, by { I_i(x, Y) in } coordinate position be (x, the saliency value based on global color histogram of pixel y) be designated as HS (x, y), $\mathrm{HS}(x,y)=\underset{k=0}{\overset{4095}{\mathrm{\Σ}}}(H\left(k\right)\×D(k_{\mathrm{xy}},k)),$ $D(k_{\mathrm{xy}},k)=\sqrt{{(p_{k_{\mathrm{xy}},1}-p_{k,1})}^2+{(p_{k_{\mathrm{xy}},2}-p_{k,2})}^2+{(p_{k_{\mathrm{xy}},3}-p_{k,3})}^2},$ Wherein, D (k_xy, k) represent H (k) | the kth in 0≤k≤4095}_xyPlant the Euclidean distance between color and kth kind color, $p_{k_{\mathrm{xy}},2}=\mathrm{mod}(k_{\mathrm{xy}}/16),$ p_k,2=mod (k/16), Represent H (k) | 0≤k≤ Kth in 4095}_xyPlant the color value of the 1st component corresponding to color,Represent H (k) | the kth in 0≤k≤4095}_xy Plant the color value of the 2nd component corresponding to color,Represent H (k) | the kth in 0≤k≤4095}_xyPlant color corresponding The color value of the 3rd component, p_k,1Represent H (k) | the color of the 1st component that kth kind color in 0≤k≤4095} is corresponding Value, p_k,2Represent H (k) | the color value of the 2nd component that kth kind color in 0≤k≤4095} is corresponding, p_k,3Represent H (k) | The color value of the 3rd component that kth kind color in 0≤k≤4095} is corresponding, mod () is remainder number handling function；

2.-5, according to { I_i(x, y) } in the saliency value based on global color histogram of each pixel, obtain { I_i (x, y) } image saliency map based on global color histogram, be designated as { HS (x, y) }.

Described step 3. in { SP_hSimilarity Sim (the SP between pth region and q-th region in }_p,SP_q) Acquisition process is:

3.-1, to { SP_hThe color value of each component of each pixel in each region in } quantifies respectively, Obtain { SP_hThe quantization areas in each region in }, by { SP_hThe quantization areas in h region in } is designated as { P_h,i(x_h, y_h), by { P_h,i(x_h,y_h) in coordinate position be (x_h,y_h) the color value of i-th component of pixel be designated as P_h,i(x_h, y_h), it is assumed that { P_h,i(x_h,y_h) in coordinate position be (x_h,y_h) pixel at { I_i(x, y) } in coordinate position be (x, y), ThenWherein, 1≤x_h≤W_h,1≤y_h≤H_h, W_hRepresent { SP_hThe width in h region in } Degree, H_hRepresent { SP_hThe height in h region in }, symbolFor rounding downwards symbol；

3.-2, { SP is calculated_hThe color histogram of the quantization areas in each region in }, by { P_h,i(x_h,y_h) color Rectangular histogram is designated asWherein,Represent { P_h,i(x_h,y_h) in belong to the institute of kth kind color There is the number of pixel；

3.-3, to { SP_hThe color histogram of the quantization areas in each region in } is normalized operation, obtains correspondence Normalization after color histogram, by rightAfter the normalization obtained after being normalized operation Color histogram be designated as $\left\{{H^{\′}}_{{\mathrm{SP}}_h}\left(k\right)\right|0\≤k\≤4095\},{H^{\′}}_{{\mathrm{SP}}_h}\left(k\right)=\frac{H_{{\mathrm{SP}}_h}\left(k\right)}{\underset{h^{\′}=1}{\overset{M}{\mathrm{\Σ}}}{H}_{{\mathrm{SP}}_{h^{\′}}}\left(k\right)},$ Wherein,Represent {SP_hQuantization areas { the P in h region in }_h,i(x_h,y_h) in belong to the probability of occurrence of pixel of kth kind color,Represent { SP_hQuantization areas { the P in h' region in }_h',i(x_h',y_h') in belong to all pictures of kth kind color The number of vegetarian refreshments, 1≤x_h'≤W_h',1≤y_h'≤H_h', W_h'Represent { SP_hThe width in h' region in }, H_h'Represent { SP_hIn } The height in h' region, P_h',i(x_h',y_h') represent { P_h',i(x_h',y_h') in coordinate position be (x_h',y_h') pixel The color value of i-th component；

3.-4, { SP is calculated_hThe similarity between pth region and q-th region in }, is designated as Sim (SP_p,SP_q), Sim(SP_p,SP_q)=Sim_c(SP_p,SP_q)×Sim_d(SP_p,SP_q), Sim_c(SP_p,SP_q) represent { SP_hPth region in } with {SP_hThe color similarity between q region in }, ${\mathrm{Sim}}_c({\mathrm{SP}}_p,{\mathrm{SP}}_q)=\underset{k=0}{\overset{4095}{\mathrm{\Σ}}}\min ({H^{\′}}_{{\mathrm{SP}}_p}\left(k\right),{H^{\′}}_{{\mathrm{SP}}_q}\left(k\right)),$ Sim_d (SP_p,SP_q) represent { SP_hPth region in } and { SP_hThe spatial simlanty between q region in },Wherein, SP_pRepresent { SP_hPth region in }, SP_qRepresent { SP_hQ in } Individual region,Represent { SP_hQuantization areas { the P in pth the region in }_p,i(x_p,y_p) in belong to the picture of kth kind color The probability of occurrence of vegetarian refreshments,Represent { SP_hQuantization areas { the P in the q-th region in }_q,i(x_q,y_q) in belong to kth kind The probability of occurrence of the pixel of color, 1≤x_p≤W_p,1≤y_p≤H_p, W_pRepresent { SP_hThe width in pth the region in }, H_pTable Show { SP_hThe height in pth the region in }, P_p,i(x_p,y_p) represent { P_p,i(x_p,y_p) in coordinate position be (x_p,y_p) pixel The color value of the i-th component of point, 1≤x_q≤W_q,1≤y_q≤H_q, W_qRepresent { SP_hThe width in the q-th region in }, H_qRepresent {SP_hThe height in the q-th region in }, P_q,i(x_q,y_q) represent { P_q,i(x_q,y_q) in coordinate position be (x_q,y_q) pixel The color value of i-th component, min () for taking minimum value function,Represent { SP_hThe center pixel in pth region in } The coordinate position of point,Represent { SP_hThe coordinate position of the central pixel point in q-th region in }, symbol " ‖ ‖ " is for asking Europe Formula distance symbol.

Described step detailed process 4. is:

4.-1, { SP is calculated_hThe color contrast in each region in }, by { SP_hThe color contrast in h region in } Degree is designated as ${\mathrm{NGC}}_{{\mathrm{SP}}_h}=\underset{q=1}{\overset{M}{\mathrm{\Σ}}}W({\mathrm{SP}}_h,{\mathrm{SP}}_q)\×\left|\right|m_{{\mathrm{SP}}_h}-m_{{\mathrm{SP}}_q}\left|\right|,$ Wherein, SP_hRepresent { SP_hThe h region in }, SP_qRepresent { SP_hQ-th region in },Represent { SP_hH in } Total number of the pixel comprised in region, Sim_d(SP_h,SP_q) represent { SP_hThe h region in } and { SP_hQ district in } Spatial simlanty between territory, Represent { SP_hIn the h region in } The coordinate position of central pixel point,Represent { SP_hThe coordinate position of the central pixel point in q-th region in }, symbol " ‖ ‖ " for seeking Euclidean distance symbol,Represent { SP_hThe color mean vector in h region in },Represent { SP_hIn } The color mean vector in q-th region；

4.-2, to { SP_hThe color contrast in each region in } is normalized operation, after obtaining the normalization of correspondence Color contrast, will be to { SP_hThe color contrast in h region in }Obtain after being normalized operation returns Color contrast after one change is designated as Wherein, NGC_minRepresent { SP_h} In M region in minimum color contrast, NGC_maxRepresent { SP_hColor contrast maximum in M region in }；

4.-3, { SP is calculated_hThe saliency value based on color contrast in each region in }, by { SP_hThe h district in } The saliency value based on color contrast in territory is designated as ${{\mathrm{NGC}}^{\′\′}}_{{\mathrm{SP}}_h}=\frac{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}(\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)\×{{\mathrm{NGC}}^{\′}}_{{\mathrm{SP}}_h})}{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)},$ Its In, Sim (SP_h,SP_q) represent { SP_hIn } similarity between h region and q-th region；

4.-4, by { SP_hThe saliency value based on color contrast in each region in } is as owning in corresponding region The saliency value of pixel, thus obtain { I_i(x, y) } image saliency map based on field color contrast, be designated as NGC (x, Y) }, wherein, (x y) represents that in { NGC (x, y) }, coordinate position is (x, the pixel value of pixel y) to NGC.

Described step detailed process 5. is:

5.-1, { SP is calculated_hThe spatial sparsity in each region in }, by { SP_hThe space in h region in } is sparse Property is designated as ${\mathrm{NSS}}_{{\mathrm{SP}}_h}=\frac{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}(\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)\×D_{{\mathrm{SP}}_h})}{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)},$ Wherein, Sim (SP_h,SP_q) represent { SP_hH in } Similarity between region and q-th region,Represent { SP_hThe central pixel point in the h region in } and { I_i(x, Y) Euclidean distance between central pixel point }；

5.-2, to { SP_hThe spatial sparsity in each region in } is normalized operation, after obtaining the normalization of correspondence Spatial sparsity, will be to { SP_hThe spatial sparsity in h region in }Obtain after being normalized operation returns Spatial sparsity after one change is designated as Wherein, NSS_minRepresent { SP_hIn } Spatial sparsity minimum in M region, NSS_maxRepresent { SP_hSpatial sparsity maximum in M region in }；

5.-3, { SP is calculated_hThe saliency value based on spatial sparsity in each region in }, by { SP_hThe h district in } The saliency value based on spatial sparsity in territory is designated as ${{\mathrm{NSS}}^{\′\′}}_{{\mathrm{SP}}_h}=\frac{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}(\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)\×{{\mathrm{NSS}}^{\′}}_{{\mathrm{SP}}_h})}{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)};$

5.-4, by { SP_hThe saliency value based on spatial sparsity in each region in } is as owning in corresponding region The saliency value of pixel, thus obtain { I_i(x, y) } the image saliency map openness based on regional space, be designated as NSS (x, Y) }, wherein, (x y) represents that in { NSS (x, y) }, coordinate position is (x, the pixel value of pixel y) to NSS.

Compared with prior art, it is an advantage of the current invention that:

1) the inventive method is by being calculated image saliency map based on global color histogram respectively, based on region face The image saliency map of color contrast and based on the openness image saliency map of regional space, and finally merge that to obtain image notable Figure, the image saliency map obtained can preferably reflect the notable situation of change in the global and local region of image, and stable Property and accuracy high.

2) the inventive method uses super-pixel cutting techniques to split image, and utilizes histogram feature to calculate respectively The color contrast of regional and spatial sparsity, finally utilize the similarity between region to be weighted, obtain final Image saliency map based on region, so can extract and meet notable semantic characteristic information.

Accompanying drawing explanation

Fig. 1 be the inventive method totally realize block diagram；

Fig. 2 a is the original image of " Image1 "；

Fig. 2 b is that true (the Ground truth) of " Image1 " image significantly schemes；

Fig. 2 c is the image saliency map based on global color histogram of " Image1 " image；

Fig. 2 d is the image saliency map based on field color contrast of " Image1 " image；

Fig. 2 e is the image saliency map openness based on regional space of " Image1 " image；

Fig. 2 f is the image saliency map that " Image1 " image is final；

Fig. 3 a is the original image of " Image2 "；

Fig. 3 b is that true (the Ground truth) of " Image2 " image significantly schemes；

Fig. 3 c is the image saliency map based on global color histogram of " Image2 " image；

Fig. 3 d is the image saliency map based on field color contrast of " Image2 " image；

Fig. 3 e is the image saliency map openness based on regional space of " Image2 " image；

Fig. 3 f is the image saliency map that " Image2 " image is final；

Fig. 4 a is the original image of " Image3 "；

Fig. 4 b is that true (the Ground truth) of " Image3 " image significantly schemes；

Fig. 4 c is the image saliency map based on global color histogram of " Image3 " image；

Fig. 4 d is the image saliency map based on field color contrast of " Image3 " image；

Fig. 4 e is the image saliency map openness based on regional space of " Image3 " image；

Fig. 4 f is the image saliency map that " Image3 " image is final；

Fig. 5 a is the original image of " Image4 "；

Fig. 5 b is that true (the Ground truth) of " Image4 " image significantly schemes；

Fig. 5 c is the image saliency map based on global color histogram of " Image4 " image；

Fig. 5 d is the image saliency map based on field color contrast of " Image4 " image；

Fig. 5 e is the image saliency map openness based on regional space of " Image4 " image；

Fig. 5 f is the image saliency map that " Image4 " image is final；

Fig. 6 a is the original image of " Image5 "；

Fig. 6 b is that true (the Ground truth) of " Image5 " image significantly schemes；

Fig. 6 c is the image saliency map based on global color histogram of " Image5 " image；

Fig. 6 d is the image saliency map based on field color contrast of " Image5 " image；

Fig. 6 e is the image saliency map openness based on regional space of " Image5 " image；

Fig. 6 f is the image saliency map that " Image5 " image is final.

Detailed description of the invention

Below in conjunction with accompanying drawing embodiment, the present invention is described in further detail.

The present invention propose a kind of based on region image saliency map extracting method, its totally realize block diagram as it is shown in figure 1, It comprises the following steps:

1. pending source images is designated as { I_i(x, y) }, wherein, i=1,2,3,1≤x≤W, 1≤y≤H, W represent { I_i (x, y) } width, H represents { I_i(x, y) } height, I_i(x y) represents { I_i(x, y) } in coordinate position be (x, pixel y) The color value of i-th component, the 1st component is that R component, the 2nd component are G component and the 3rd component is B component.

If the most only considering local significance, then image changes the background area significance of more violent edge or complexity Higher, and the internal significance in smooth target area is relatively low, so also needs to consider that overall situation significance, overall situation significance refer to respectively Pixel is relative to the significance degree of global image, and therefore first the present invention obtains { I_i(x, y) } quantized image and quantify figure The global color histogram of picture, then according to { I_i(x, y) } quantized image, obtain { I_i(x, y) } in the face of each pixel Color kind, further according to { I_i(x, y) } the global color histogram of quantized image and { I_i(x, y) } in the face of each pixel Color kind, obtains { I_i(x, y) } image saliency map based on global color histogram, be designated as { HS (x, y) }, wherein, HS (x, Y) represent that in { HS (x, y) }, coordinate position be (x, the pixel value of pixel y), also expression { I_i(x, y) } in coordinate position be (x, the saliency value based on global color histogram of pixel y).

In this particular embodiment, step detailed process 2. is:

2.-1, to { I_i(x, y) } in the color value of each component of each pixel quantify respectively, obtain { I_i (x, y) } quantized image, be designated as { P_i(x, y) }, by { P_i(x, y) } in coordinate position be (x, the i-th component of pixel y) Color value be designated as P_i(x, y),Wherein, symbolFor rounding downwards symbol.

2.-2, { P is calculated_i(x, y) } global color histogram, be designated as H (k) | 0≤k≤4095}, wherein, H (k) table Show { P_i(x, y) } in belong to the number of all pixels of kth kind color.

2.-3, according to { P_i(x, y) } in the color value of each component of each pixel, calculate { I_i(x, y) } in corresponding The color category of pixel, by { I_i(x, y) } in coordinate position be that (x, the color category of pixel y) is designated as k_xy, k_xy=P₃ (x,y)×256+P₂(x,y)×16+P₁(x, y), wherein, P₃(x y) represents { P_i(x, y) } in coordinate position be (x, picture y) The color value of the 3rd component of vegetarian refreshments, P₂(x y) represents { P_i(x, y) } in coordinate position be (x, 2nd point of pixel y) The color value of amount, P₁(x y) represents { P_i(x, y) } in coordinate position be (x, the color value of the 1st component of pixel y).

2.-4, { I is calculated_i(x, y) } in the saliency value based on global color histogram of each pixel, by { I_i(x, Y) in } coordinate position be (x, the saliency value based on global color histogram of pixel y) be designated as HS (x, y), $\mathrm{HS}(x,y)=\underset{k=0}{\overset{4095}{\mathrm{\Σ}}}(H\left(k\right)\×D(k_{\mathrm{xy}},k)),$ $D(k_{\mathrm{xy}},k)=\sqrt{{(p_{k_{\mathrm{xy}},1}-p_{k,1})}^2+{(p_{k_{\mathrm{xy}},2}-p_{k,2})}^2+{(p_{k_{\mathrm{xy}},3}-p_{k,3})}^2},$ Wherein, D (k_xy, k) represent H (k) | the kth in 0≤k≤4095}_xyPlant the Euclidean distance between color and kth kind color, $p_{k_{\mathrm{xy}},2}=\mathrm{mod}(k_{\mathrm{xy}}/16),$ p_k,2=mod (k/16), Represent H (k) | 0≤k≤ Kth in 4095}_xyPlant the color value of the 1st component corresponding to color,Represent H (k) | the kth in 0≤k≤4095}_xy Plant the color value of the 2nd component corresponding to color,Represent H (k) | the kth in 0≤k≤4095}_xyPlant color corresponding The color value of the 3rd component, p_k,1Represent H (k) | the color of the 1st component that kth kind color in 0≤k≤4095} is corresponding Value, p_k,2Represent H (k) | the color value of the 2nd component that kth kind color in 0≤k≤4095} is corresponding, p_k,3Represent H (k) | The color value of the 3rd component that kth kind color in 0≤k≤4095} is corresponding, mod () is remainder number handling function.

2.-5, according to { I_i(x, y) } in the saliency value based on global color histogram of each pixel, obtain { I_i (x, y) } image saliency map based on global color histogram, be designated as { HS (x, y) }.

3. use super-pixel (Superpixel) cutting techniques by { I_i(x, y) } it is divided into the region of M non-overlapping copies, so After by { I_i(x, y) } again it is expressed as the set in M region, it is designated as { SP_h, consider further that local significance, district similar in image Typically having relatively low significance between territory, therefore the present invention calculates { SP_hThe similarity between regional in }, by { SP_h} In pth region and q-th region between similarity be designated as Sim (SP_p,SP_q), wherein, M >=1, SP_hRepresent { SP_hIn } The h region, 1≤h≤M, 1≤p≤M, 1≤q≤M, p ≠ q, SP_pRepresent { SP_hPth region in }, SP_qRepresent {SP_hQ-th region in }.In the present embodiment, M=200 is taken.

In this particular embodiment, step 3. in { SP_hThe similarity Sim between pth region and q-th region in } (SP_p,SP_q) acquisition process be:

3.-1, to { SP_hThe color value of each component of each pixel in each region in } quantifies respectively, Obtain { SP_hThe quantization areas in each region in }, by { SP_hThe quantization areas in h region in } is designated as { P_h,i(x_h, y_h), by { P_h,i(x_h,y_h) in coordinate position be (x_h,y_h) the color value of i-th component of pixel be designated as P_h,i(x_h, y_h), it is assumed that { P_h,i(x_h,y_h) in coordinate position be (x_h,y_h) pixel at { I_i(x, y) } in coordinate position be (x, y), ThenWherein, 1≤x_h≤W_h,1≤y_h≤H_h, W_hRepresent { SP_hThe width in h region in } Degree, H_hRepresent { SP_hThe height in h region in }, symbolFor rounding downwards symbol.

3.-2, { SP is calculated_hThe color histogram of the quantization areas in each region in }, by { P_h,i(x_h,y_h) color Rectangular histogram is designated asWherein,Represent { P_h,i(x_h,y_h) in belong to the institute of kth kind color There is the number of pixel.

3.-3, to { SP_hThe color histogram of the quantization areas in each region in } is normalized operation, obtains correspondence Normalization after color histogram, by rightAfter the normalization obtained after being normalized operation Color histogram be designated as $\left\{{H^{\′}}_{{\mathrm{SP}}_h}\left(k\right)\right|0\≤k\≤4095\},{H^{\′}}_{{\mathrm{SP}}_h}\left(k\right)=\frac{H_{{\mathrm{SP}}_h}\left(k\right)}{\underset{h^{\′}=1}{\overset{M}{\mathrm{\Σ}}}{H}_{{\mathrm{SP}}_{h^{\′}}}\left(k\right)},$ Wherein,Represent {SP_hQuantization areas { the P in h region in }_h,i(x_h,y_h) in belong to the probability of occurrence of pixel of kth kind color,Represent { SP_hQuantization areas { the P in h' region in }_h',i(x_h',y_h') in belong to all pictures of kth kind color The number of vegetarian refreshments, 1≤x_h'≤W_h',1≤y_h'≤H_h', W_h'Represent { SP_hThe width in h' region in }, H_h'Represent { SP_hIn } The height in h' region, P_h',i(x_h',y_h') represent { P_h',i(x_h',y_h') in coordinate position be (x_h',y_h') pixel The color value of i-th component.

3.-4, { SP is calculated_hThe similarity between pth region and q-th region in }, is designated as Sim (SP_p,SP_q), Sim(SP_p,SP_q)=Sim_c(SP_p,SP_q)×Sim_d(SP_p,SP_q), Sim_c(SP_p,SP_q) represent { SP_hPth region in } with {SP_hThe color similarity between q region in }, ${\mathrm{Sim}}_c({\mathrm{SP}}_p,{\mathrm{SP}}_q)=\underset{k=0}{\overset{4095}{\mathrm{\Σ}}}\min ({H^{\′}}_{{\mathrm{SP}}_p}\left(k\right),{H^{\′}}_{{\mathrm{SP}}_q}\left(k\right)),$ Sim_d (SP_p,SP_q) represent { SP_hPth region in } and { SP_hThe spatial simlanty between q region in },Wherein, SP_pRepresent { SP_hPth region in }, SP_qRepresent { SP_hQ in } Individual region,Represent { SP_hQuantization areas { the P in pth the region in }_p,i(x_p,y_p) in belong to the picture of kth kind color The probability of occurrence of vegetarian refreshments,Represent { SP_hQuantization areas { the P in the q-th region in }_q,i(x_q,y_q) in belong to kth kind The probability of occurrence of the pixel of color, 1≤x_p≤W_p,1≤y_p≤H_p, W_pRepresent { SP_hThe width in pth the region in }, H_pTable Show { SP_hThe height in pth the region in }, P_p,i(x_p,y_p) represent { P_p,i(x_p,y_p) in coordinate position be (x_p,y_p) pixel The color value of the i-th component of point, 1≤x_q≤W_q,1≤y_q≤H_q, W_qRepresent { SP_hThe width in the q-th region in }, H_qRepresent {SP_hThe height in the q-th region in }, P_q,i(x_q,y_q) represent { P_q,i(x_q,y_q) in coordinate position be (x_q,y_q) pixel The color value of i-th component, min () for taking minimum value function,Represent { SP_hThe center pixel in pth region in } The coordinate position of point,Represent { SP_hThe coordinate position of the central pixel point in q-th region in }, symbol " ‖ ‖ " is for asking Europe Formula distance symbol.

4. according to { SP_hThe similarity between regional in }, obtains { I_i(x, y) } based on field color contrast Image saliency map, be designated as { NGC (x, y) }, wherein, (x y) represents that in { NGC (x, y) }, coordinate position is (x, picture y) to NGC The pixel value of vegetarian refreshments.

In this particular embodiment, step detailed process 4. is:

4.-1, { SP is calculated_hThe color contrast in each region in }, by { SP_hThe color contrast in h region in } Degree is designated as ${\mathrm{NGC}}_{{\mathrm{SP}}_h}=\underset{q=1}{\overset{M}{\mathrm{\Σ}}}W({\mathrm{SP}}_h,{\mathrm{SP}}_q)\×\left|\right|m_{{\mathrm{SP}}_h}-m_{{\mathrm{SP}}_q}\left|\right|,$ Wherein, SP_hRepresent { SP_hThe h region in }, SP_qRepresent { SP_hQ-th region in },Represent { SP_hH in } Total number of the pixel comprised in region, Sim_d(SP_h,SP_q) represent { SP_hThe h region in } and { SP_hQ district in } Spatial simlanty between territory, Represent { SP_hIn the h region in } The coordinate position of central pixel point,Represent { SP_hThe coordinate position of the central pixel point in q-th region in }, symbol " ‖ ‖ " for seeking Euclidean distance symbol,Represent { SP_hThe color mean vector in h region in }, will { SP_hIn } The color vector of all pixels in h region is averaging and obtainsRepresent { SP_hThe face in the q-th region in } Color mean vector.

4.-2, to { SP_hThe color contrast in each region in } is normalized operation, after obtaining the normalization of correspondence Color contrast, will be to { SP_hThe color contrast in h region in }Obtain after being normalized operation returns Color contrast after one change is designated as Wherein, NGC_minRepresent { SP_hIn } M region in minimum color contrast, NGC_maxRepresent { SP_hColor contrast maximum in M region in }.

4.-3, { SP is calculated_hThe saliency value based on color contrast in each region in }, by { SP_hThe h district in } The saliency value based on color contrast in territory is designated as ${{\mathrm{NGC}}^{\′\′}}_{{\mathrm{SP}}_h}=\frac{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}(\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)\×{{\mathrm{NGC}}^{\′}}_{{\mathrm{SP}}_h})}{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)},$ Its In, Sim (SP_h,SP_q) represent { SP_hIn } similarity between h region and q-th region.

4.-4, by { SP_hThe saliency value based on color contrast in each region in } is as owning in corresponding region The saliency value of pixel, i.e. for { SP_hThe h region in }, by { SP_hH region in } based on color contrast Saliency value is as the saliency value of all pixels in this region, thus obtains { I_i(x, y) } based on field color contrast Image saliency map, be designated as { NGC (x, y) }, wherein, (x y) represents that in { NGC (x, y) }, coordinate position is (x, picture y) to NGC The pixel value of vegetarian refreshments.

5. according to { SP_hThe similarity between regional in }, obtains { I_i(x, y) } openness based on regional space Image saliency map, be designated as { NSS (x, y) }, wherein, (x y) represents that in { NSS (x, y) }, coordinate position is (x, picture y) to NSS The pixel value of vegetarian refreshments.

In this particular embodiment, step detailed process 5. is:

5.-1, { SP is calculated_hThe spatial sparsity in each region in }, by { SP_hThe space in h region in } is sparse Property is designated as ${\mathrm{NSS}}_{{\mathrm{SP}}_h}=\frac{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}(\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)\×D_{{\mathrm{SP}}_h})}{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)},$ Wherein, Sim (SP_h,SP_q) represent { SP_hH in } Similarity between region and q-th region,Represent { SP_hThe central pixel point in the h region in } and { I_i(x, Y) Euclidean distance between central pixel point }.

5.-2, to { SP_hThe spatial sparsity in each region in } is normalized operation, after obtaining the normalization of correspondence Spatial sparsity, will be to { SP_hThe spatial sparsity in h region in }Obtain after being normalized operation returns Spatial sparsity after one change is designated as Wherein, NSS_minRepresent { SP_hIn } Spatial sparsity minimum in M region, NSS_maxRepresent { SP_hSpatial sparsity maximum in M region in }.

5.-3, { SP is calculated_hThe saliency value based on spatial sparsity in each region in }, by { SP_hThe h district in } The saliency value based on spatial sparsity in territory is designated as ${\mathrm{NS}{S}^{\′\′}}_{{\mathrm{SP}}_h}=\frac{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}(\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)\×{{\mathrm{NSS}}^{\′}}_{{\mathrm{SP}}_h})}{\underset{q=1}{\overset{M}{\mathrm{\Σ}}}\mathrm{Sim}({\mathrm{SP}}_h,{\mathrm{SP}}_q)}.$

5.-4, by { SP_hThe saliency value based on spatial sparsity in each region in } is as owning in corresponding region The saliency value of pixel, i.e. for { SP_hThe h region in }, by { SP_hH region in } based on spatial sparsity Saliency value is as the saliency value of all pixels in this region, thus obtains { I_i(x, y) } openness based on regional space Image saliency map, be designated as { NSS (x, y) }, wherein, (x y) represents that in { NSS (x, y) }, coordinate position is (x, picture y) to NSS The pixel value of vegetarian refreshments.

6. to { I_i(x, y) } image saliency map based on global color histogram { HS (x, y) }, { I_i(x, y) } based on The image saliency map of field color contrast NGC (x, y) } and { I_i(x, y) } the image openness based on regional space notable Figure { NSS (x, y) } merge, obtain { I_i(x, y) } final image saliency map, be designated as { Sal (x, y) }, will Sal (x, Y) in } coordinate position be (x, the pixel value of pixel y) be designated as Sal (x, y), Sal (x, y)=HS (x, y) × NGC (x, y) × NSS(x,y)。

Hereinafter just utilize Image1 in the notable object images storehouse MSRA that Microsoft Research, Asia provides by the inventive method, The notable figure of five groups of images of Image2, Image3, Image4 and Image5 extracts.Fig. 2 a gives the original of " Image1 " Image, Fig. 2 b gives true (the Ground truth) of " Image1 " image significantly to scheme, and Fig. 2 c gives " Image1 " image Image saliency map based on global color histogram, Fig. 2 d give the based on field color contrast of " Image1 " image Image saliency map, Fig. 2 e give the image saliency map openness based on regional space of " Image1 " image, Fig. 2 f gives The image saliency map that " Image1 " image is final；Fig. 3 a gives the original image of " Image2 ", and Fig. 3 b gives " Image2 " True (the Ground truth) of image significantly schemes, and Fig. 3 c gives the figure based on global color histogram of " Image2 " image As notable figure, Fig. 3 d gives the image saliency map based on field color contrast of " Image2 " image, Fig. 3 e gives The image saliency map openness based on regional space of " Image2 " image, Fig. 3 f give the image that " Image2 " image is final Notable figure；Fig. 4 a gives the original image of " Image3 ", and Fig. 4 b gives the true (Ground of " Image3 " image Truth) significantly scheming, Fig. 4 c gives the image saliency map based on global color histogram of " Image3 " image, Fig. 4 d is given The image saliency map based on field color contrast of " Image3 " image, Fig. 4 e give " Image3 " image based on district The openness image saliency map of domain space, Fig. 4 f give the image saliency map that " Image3 " image is final；Fig. 5 a gives The original image of " Image4 ", Fig. 5 b gives true (the Ground truth) of " Image4 " image significantly to scheme, and Fig. 5 c is given The image saliency map based on global color histogram of " Image4 " image, Fig. 5 d give " Image4 " image based on district The image openness based on regional space that the image saliency map of territory color contrast, Fig. 5 e give " Image4 " image is notable Figure, Fig. 5 f give the image saliency map that " Image4 " image is final；Fig. 6 a gives the original image of " Image5 ", and Fig. 6 b gives True (the Ground truth) that gone out " Image5 " image significantly schemes, Fig. 6 c give " Image5 " image based on the overall situation face The image saliency map of Color Histogram, Fig. 6 d give " Image5 " image image saliency map based on field color contrast, Fig. 6 e gives the image saliency map openness based on regional space of " Image5 " image, Fig. 6 f gives " Image5 " image Final image saliency map.From Fig. 2 a to Fig. 6 f it can be seen that use the image saliency map that the inventive method obtains owing to considering The notable situation of change in global and local region, therefore, it is possible to meet notable semantic feature well.

Claims (4)

1. an image saliency map extracting method based on region, it is characterised in that comprise the following steps:

1. pending source images is designated as { I_i(x, y) }, wherein, i=1,2,3,1≤x≤W, 1≤y≤H, W represent { I_i(x, Y) width }, H represents { I_i(x, y) } height, I_i(x y) represents { I_i(x, y) } in coordinate position be (x, the i-th of pixel y) The color value of individual component, the 1st component is that R component, the 2nd component are G component and the 3rd component is B component；

First { I is obtained_i(x, y) } quantized image and the global color histogram of quantized image, then according to { I_i(x,y)} Quantized image, obtain { I_i(x, y) } in the color category of each pixel, further according to { I_i(x, y) } quantized image complete Office's color histogram and { I_i(x, y) } in the color category of each pixel, obtain { I_i(x, y) } straight based on global color The image saliency map of side's figure, is designated as { HS (x, y) }, and wherein, (x y) represents that in { HS (x, y) }, coordinate position is (x, picture y) to HS The pixel value of vegetarian refreshments, also represents { I_i(x, y) } in coordinate position be (x, pixel y) based on global color histogram aobvious Work value；

Described step detailed process 2. is:

2.-1, to { I_i(x, y) } in the color value of each component of each pixel quantify respectively, obtain { I_i(x,y)} Quantized image, be designated as { P_i(x, y) }, by { P_i(x, y) } in coordinate position be (x, the color of the i-th component of pixel y) Value is designated as P_i(x, y),Wherein, symbolFor rounding downwards symbol；

2.-2, { P is calculated_i(x, y) } global color histogram, be designated as H (k) | 0≤k≤4095}, wherein, H (k) represents { P_i (x, y) } in belong to the number of all pixels of kth kind color；

2.-3, according to { P_i(x, y) } in the color value of each component of each pixel, calculate { I_i(x, y) } in respective pixel The color category of point, by { I_i(x, y) } in coordinate position be that (x, the color category of pixel y) is designated as k_xy, k_xy=P₃(x,y) ×256+P₂(x,y)×16+P₁(x, y), wherein, P₃(x y) represents { P_i(x, y) } in coordinate position be (x, pixel y) The color value of the 3rd component, P₂(x y) represents { P_i(x, y) } in coordinate position be (x, the face of the 2nd component of pixel y) Colour, P₁(x y) represents { P_i(x, y) } in coordinate position be (x, the color value of the 1st component of pixel y)；

2.-4, { I is calculated_i(x, y) } in the saliency value based on global color histogram of each pixel, by { I_i(x, y) } in Coordinate position be (x, the saliency value based on global color histogram of pixel y) be designated as HS (x, y), Wherein, D (k_xy, k) represent H (k) | the kth in 0≤k≤4095}_xyPlant the Euclidean distance between color and kth kind color, p_k,2=mod (k/16), Represent H (k) | the kth in 0≤k≤4095}_xyKind of color corresponding the The color value of 1 component,Represent H (k) | the kth in 0≤k≤4095}_xyPlant the color of the 2nd component corresponding to color Value,Represent H (k) | the kth in 0≤k≤4095}_xyPlant the color value of the 3rd component corresponding to color, p_k,1Represent { H (k) | the color value of the 1st component that kth kind color in 0≤k≤4095} is corresponding, p_k,2Represent H (k) | 0≤k≤4095} In the color value of the 2nd component corresponding to kth kind color, p_k,3Represent H (k) | the kth kind color pair in 0≤k≤4095} The color value of the 3rd component answered, mod () is remainder number handling function；

2.-5, according to { I_i(x, y) } in the saliency value based on global color histogram of each pixel, obtain { I_i(x,y)} Image saliency map based on global color histogram, be designated as { HS (x, y) }；

3. use super-pixel cutting techniques by { I_i(x, y) } it is divided into the region of M non-overlapping copies, then by { I_i(x, y) } again It is expressed as the set in M region, is designated as { SP_h, then calculate { SP_hThe similarity between regional in }, by { SP_hIn } Similarity between pth region and q-th region is designated as Sim (SP_p,SP_q), wherein, M >=1, SP_hRepresent { SP_hH in } Individual region, 1≤h≤M, 1≤p≤M, 1≤q≤M, p ≠ q, SP_pRepresent { SP_hPth region in }, SP_qRepresent { SP_hIn } Q-th region；

4. according to { SP_hThe similarity between regional in }, obtains { I_i(x, y) } figure based on field color contrast As notable figure, being designated as { NGC (x, y) }, wherein, (x y) represents that in { NGC (x, y) }, coordinate position is (x, pixel y) to NGC Pixel value；

5. according to { SP_hThe similarity between regional in }, obtains { I_i(x, y) } the figure openness based on regional space As notable figure, being designated as { NSS (x, y) }, wherein, (x y) represents that in { NSS (x, y) }, coordinate position is (x, pixel y) to NSS Pixel value；

6. to { I_i(x, y) } image saliency map based on global color histogram { HS (x, y) }, { I_i(x, y) } based on region The image saliency map of color contrast NGC (x, y) } and { I_i(x, y) } the image saliency map openness based on regional space NSS (x, y) } merge, obtain { I_i(x, y) } final image saliency map, be designated as { Sal (x, y) }, will Sal (x, Y) in } coordinate position be (x, the pixel value of pixel y) be designated as Sal (x, y), Sal (x, y)=HS (x, y) × NGC (x, y) ×NSS(x,y)。

A kind of image saliency map extracting method based on region the most according to claim 1, it is characterised in that described step The most 3. { SP in_hSimilarity Sim (the SP between pth region and q-th region in }_p,SP_q) acquisition process be:

3.-1, to { SP_hThe color value of each component of each pixel in each region in } quantifies respectively, obtains {SP_hThe quantization areas in each region in }, by { SP_hThe quantization areas in h region in } is designated as { P_h,i(x_h,y_h), will {P_h,i(x_h,y_h) in coordinate position be (x_h,y_h) the color value of i-th component of pixel be designated as P_h,i(x_h,y_h), it is assumed that {P_h,i(x_h,y_h) in coordinate position be (x_h,y_h) pixel at { I_i(x, y) } in coordinate position be (x, y), thenWherein, 1≤x_h≤W_h,1≤y_h≤H_h, W_hRepresent { SP_hThe width in h region in }, H_hRepresent { SP_hThe height in h region in }, symbolFor rounding downwards symbol；

3.-2, { SP is calculated_hThe color histogram of the quantization areas in each region in }, by { P_h,i(x_h,y_h) color histogram Seal isWherein,Represent { P_h,i(x_h,y_h) in belong to all pictures of kth kind color The number of vegetarian refreshments；

3.-3, to { SP_hThe color histogram of the quantization areas in each region in } is normalized operation, obtains returning of correspondence Color histogram after one change, by rightFace after the normalization obtained after being normalized operation Color Histogram is designated as Wherein,Represent { SP_hIn } Quantization areas { the P in h region_h,i(x_h,y_h) in belong to the probability of occurrence of pixel of kth kind color,Represent {SP_hQuantization areas { the P in h' region in }_h',i(x_h',y_h') in belong to the number of all pixels of kth kind color, 1 ≤x_h'≤W_h',1≤y_h'≤H_h', W_h'Represent { SP_hThe width in h' region in }, H_h'Represent { SP_hThe h' region in } Height, P_h',i(x_h',y_h') represent { P_h',i(x_h',y_h') in coordinate position be (x_h',y_h') the i-th component of pixel Color value；

3.-4, { SP is calculated_hThe similarity between pth region and q-th region in }, is designated as Sim (SP_p,SP_q), Sim (SP_p,SP_q)=Sim_c(SP_p,SP_q)×Sim_d(SP_p,SP_q), Sim_c(SP_p,SP_q) represent { SP_hPth region in } with {SP_hThe color similarity between q region in },Sim_d (SP_p,SP_q) represent { SP_hPth region in } and { SP_hThe spatial simlanty between q region in },Wherein, SP_pRepresent { SP_hPth region in }, SP_qRepresent { SP_hQ-th in } Region,Represent { SP_hQuantization areas { the P in pth the region in }_p,i(x_p,y_p) in belong to the pixel of kth kind color The probability of occurrence of point,Represent { SP_hQuantization areas { the P in the q-th region in }_q,i(x_q,y_q) in belong to kth kind face The probability of occurrence of the pixel of color, 1≤x_p≤W_p,1≤y_p≤H_p, W_pRepresent { SP_hThe width in pth the region in }, H_pRepresent {SP_hThe height in pth the region in }, P_p,i(x_p,y_p) represent { P_p,i(x_p,y_p) in coordinate position be (x_p,y_p) pixel The color value of i-th component, 1≤x_q≤W_q,1≤y_q≤H_q, W_qRepresent { SP_hThe width in the q-th region in }, H_qRepresent {SP_hThe height in the q-th region in }, P_q,i(x_q,y_q) represent { P_q,i(x_q,y_q) in coordinate position be (x_q,y_q) pixel The color value of i-th component, min () for taking minimum value function,Represent { SP_hThe center pixel in pth region in } The coordinate position of point,Represent { SP_hThe coordinate position of the central pixel point in q-th region in }, symbol " | | | | " be Seek Euclidean distance symbol.

A kind of image saliency map extracting method based on region the most according to claim 2, it is characterised in that described step Rapid detailed process 4. is:

4.-1, { SP is calculated_hThe color contrast in each region in }, by { SP_hThe color contrast note in h region in } For Wherein, SP_hRepresent { SP_hThe h region in }, SP_qRepresent { SP_hQ-th region in },Represent { SP_hH in } Total number of the pixel comprised in region, Sim_d(SP_h,SP_q) represent { SP_hThe h region in } and { SP_hQ district in } Spatial simlanty between territory, Represent { SP_hIn in the h region in } The coordinate position of imago vegetarian refreshments,Represent { SP_hThe coordinate position of the central pixel point in q-th region in }, symbol " | | | | " for seeking Euclidean distance symbol,Represent { SP_hThe color mean vector in h region in },Represent { SP_hIn } The color mean vector in q-th region；

4.-2, to { SP_hThe color contrast in each region in } is normalized operation, obtains the face after the normalization of correspondence Color contrast, will be to { SP_hThe color contrast in h region in }The normalization obtained after being normalized operation After color contrast be designated as Wherein, NGC_minRepresent { SP_hM in } Color contrast minimum in individual region, NGC_maxRepresent { SP_hColor contrast maximum in M region in }；

4.-3, { SP is calculated_hThe saliency value based on color contrast in each region in }, by { SP_hH region in } Saliency value based on color contrast is designated as Wherein, Sim (SP_h,SP_q) represent { SP_hIn } similarity between h region and q-th region；

4.-4, by { SP_hThe saliency value based on color contrast in each region in } is as all pixels in corresponding region Saliency value, thus obtain { I_i(x, y) } image saliency map based on field color contrast, be designated as { NGC (x, y) }, its In, (x y) represents that in { NGC (x, y) }, coordinate position is (x, the pixel value of pixel y) to NGC.

A kind of image saliency map extracting method based on region the most according to claim 3, it is characterised in that described step Rapid detailed process 5. is:

5.-1, { SP is calculated_hThe spatial sparsity in each region in }, by { SP_hThe spatial sparsity note in h region in } For Wherein, Sim (SP_h,SP_q) represent { SP_hThe h region in } And the similarity between q-th region,Represent { SP_hThe central pixel point in the h region in } and { I_i(x, y) } Euclidean distance between central pixel point；

5.-2, to { SP_hThe spatial sparsity in each region in } is normalized operation, obtains the sky after the normalization of correspondence Between openness, will be to { SP_hThe spatial sparsity in h region in }The normalization obtained after being normalized operation After spatial sparsity be designated as Wherein, NSS_minRepresent { SP_hM district in } Spatial sparsity minimum in territory, NSS_maxRepresent { SP_hSpatial sparsity maximum in M region in }；

5.-3, { SP is calculated_hThe saliency value based on spatial sparsity in each region in }, by { SP_hH region in } Saliency value based on spatial sparsity is designated as

5.-4, by { SP_hThe saliency value based on spatial sparsity in each region in } is as all pixels in corresponding region Saliency value, thus obtain { I_i(x, y) } the image saliency map openness based on regional space, be designated as { NSS (x, y) }, its In, (x y) represents that in { NSS (x, y) }, coordinate position is (x, the pixel value of pixel y) to NSS.