| CPC G06V 10/462 (2022.01) [G06T 5/70 (2024.01); G06V 10/72 (2022.01)] | 1 Claim |
|
1. A computer implemented method of Salient Object detection in an image, comprising:
Step 1: Pre-processing an input image, in this step, a blurring Gaussian algorithm is applied to the image, then the image is transformed from RGB (Red-green-blue) color space to HSV (Hue-Saturation-Illumination) color space, and SLIC (Simple Linear Iterative Clustering) is applied to initialize superpixels and statistical analysis on color and spatial distribution of the superpixels with the following sub-steps:
An Image I(x, y) is RGB image convoluted with a Gaussian kernel k with a size of [3,3], and a sigma value of 0.5, according to the below formula:
I(x,y)←I(x,y)⊗k(i,j)
Providing a blurred image, Superpixel initialization from the blurred image I(x,y), uses a SLIC algorithm, with a parameter n as the maximum number of superpixels, after initialization, the original image is split into large superpixels S(i), where regions with similar characteristics are merged into a same superpixel, and location of superpixels is marked from small to large with directions from left to right, from up to down;
the original image is transformed from RGB space to HSV space, obtaining I′(x, y);
Step 2: Merge superpixels with similar color correlations according to the following:
With input as the set of superpixels S(i) computed at step 1, generate an HSV color distribution for each superpixel according to the below equation:
 where, bins is a number of groups divided from 256 gray levels, after calculating the color distribution for each superpixel, a matrix h(i) with size of m×8×8×8 (m is superpixel numbers);
From the h(i) matrix, calculate a color correlation matrix between the superpixels, using the Bhattacharyya Coefficient (BC) as follows:
 with BC being the Bhattacharyya Coefficient of two vectors:
BC(p,q)=−ln(10−1+Σ√piqi)
Proceed to merge neighboring superpixels with a similar color distribution wherein the superpixels with adjacent positions are superpixels that are directly linked to each other on the image, consequently, on the color correlation matrix, position (i,i+1) with BC lower than a predefined threshold, epsilon, then the two superpixels i and i+1 can be merged into a new superpixel;
After merging superpixels, the superpixels are updated, into new superpixels, as follows:
 Continue to perform two previous steps, until the number of superpixels remains constant, then terminate the superpixel merging process, and obtain the final superpixel {S(i)i1,2, . . . , n};
Step 3: Statistics on the color and spatial characteristics of the superpixels; based on the superpixels {S(i)i=1,2, . . . , n} that are merged after Step 2, determine descriptive statistics about a scale of the superpixel, a distance to the center of the image, initialization and calculate the correlation of color distribution, spatial distribution, and the contrast of superpixels via the following sub-steps:
Determine Statistics of the distance from the center of the superpixel to the center of the image and count the number of pixels in the superpixel, wherein the superpixels that are close to the center of the image will likely be the salient area;
The distance from the superpixel to the center point of the image is defined by the Euclidean distance from the center of the superpixel to the center point of the original image, calculated as follows:
 Where (cx, cy) is a center point of the original image, which is half a height and width of the image, respectively, and is the total number of pixels in the superpixel S(i);
Calculate the color correlation matrix color (i,j), as in step 2;
From the set of superpixels S(i), calculate a circumscribed circle filling index of each superpixel, through the following sub-steps:
call the center point of the i-th superpixel as ci, then the radius of the circumcircle of this superpixel is calculated as follows:
 The circumcircle filling index compact(i) of the superpixel is calculated by following equation:
 From set of superpixels S(i) computed at step 2 and the circumcircle filling index compact(i) computed at step 3, calculate a spatial correlation matrix between superpixels, according to the following formula:
 where ci, cj are center points of superpixels i, and j, respectively;
Compute a global contrast matrix between superpixels, where, superpixels with higher number of pixels have more effects on processing of evaluating saliency of the superpixels;
 Where npixeli is the number of pixels in superpixel i, also contrast(i,j) is normalized to [0,1] based on an interval [min(contrast), max(contrast)],
where, dot (·) describes the multiplication of two matrices;
Step 4: analyze a final estimation of a discriminant between superpixels; this step calculates a composite correlation matrix, and a saliency evaluation vector of the superpixel, and interpolates the saliency index of each pixel in the corresponding superpixel according to the sub-steps as follows:
Synthesize the composite correlation matrix, similar(i,j), is a combination of factors:
color correlation matrix, spatial correlation matrix, as follows:
similar(i,j)=color(i,j)×spatial(i,j)
The composite correlation matrix is considered a correlation matrix with the estimations being the color correlation matrix under the effect of the spatial correlation matrix as a coefficient matrix, larger superpixels (a large number of pixels) will have more effect;
the saliency evaluation vector of the superpixel, decision(i) is calculated from the pixel correlation matrix from step 4, the global contrast matrix from step 3, and the statistical results of the distance from the center of the superpixel to the center point of the original image from step 3 with sub-steps as follows:
Calculate an extended spatial matrix spread(i,j), using the composite correlation matrix similar(i,j) and distance d(i) as follows:
 Then matrix spread(i,j) is normalized to [0, 1] based on interval [min(spread), max(spread)];
This step compensates the convergence factor into the initial center point of superpixels, the closer superpixel is to the center the more it gets attention, and it is highly potential is a part of salient objects;
the saliency evaluation vector, decision(i) is a sequence of evaluation indices, calculated as follows:
 The decision(i) vector has a length that is equal to number of initialized superpixels, the larger values are the more salient they are;
Calculate saliency index of each pixel p(x,y) in HSV space via salient evaluation vector,
 Where N(p) is neighboring pixels of p(x,y) (eight points),
In the above equation, pixels with more popular color intensity m superpixel, the saliency index of those pixels are higher, where bin(p) is color intensity (h,s,v) in HSV space of the pixel p(x, y) after it is compressed into 3-bits, as follows:
 |