Unlock instant, AI-driven research and patent intelligence for your innovation.

An optimization method for saliency detection based on k-means cluster fitting

A technology of k-means clustering and optimization methods, which is applied in the directions of instruments, computing, character and pattern recognition, etc.

Active Publication Date: 2020-09-01
FUZHOU UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Since the same saliency detection algorithm uses the same model to detect salient regions, the calculated saliency map shows similar defects compared with the manually annotated annotation map.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An optimization method for saliency detection based on k-means cluster fitting
  • An optimization method for saliency detection based on k-means cluster fitting
  • An optimization method for saliency detection based on k-means cluster fitting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0070] The present invention is based on the significance detection optimization method of K-means cluster fitting, such as figure 1 , 2 As shown, including the following steps:

[0071] Step S1: Extract the scene GIST features of the image; including the following steps:

[0072] Step S11: For any image, calculate the average value of the three color channels of R, G, and B for each pixel to obtain an intensity image. The calculation formula is:

[0073]

[0074] Among them, (x, y) is the spatial position coordinates of the pixel, q (x, y) is the intensity image of the pixel (x, y), R (x, y), G (x, y), B (x ,y) are the R, G, and B color channels of the pixel (x, y) respectively;

[0075] Step S12: Perform Discrete Fourier Transform (DFT) on the intensity image q(x, y):

[0076]

[0077] Where f x , F y Are the spatial frequency variables of the x and y co...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention relates to a saliency detection optimization method based on K-means clustering fitting, comprising the following steps: step S1: extracting the scene GIST feature of the image; step S2: extracting the color histogram feature of the image; step S3: according to the scene GIST feature and color histogram feature calculate the similarity between images; step S4: perform K-means clustering on the image set according to the similarity between images, and divide it into k mutually independent image clusters; step S5: calculate each image cluster the fitting model; step S6: determine the image cluster to which the new input image belongs, and apply the fitting model of the image cluster to the saliency map of the input image for optimization. This method is suitable for the optimization of various saliency detection algorithms, and the optimization effect is obvious.

Description

Technical field [0001] The invention relates to the technical fields of image and video processing and computer vision, in particular to a saliency detection optimization method based on K-means cluster fitting. Background technique [0002] People pay attention to the important parts of the image and can automatically extract this information. At present, many saliency detection algorithms for extracting important information of images have been proposed. In 2013, Scharfenberger et al. proposed a saliency detection algorithm based on statistical structural differences. The algorithm uses probabilistic graph models and visual attention constraints to detect saliency objects. In 2014, Kim et al. proposed a saliency detection algorithm based on high-dimensional color space conversion, which maps RGB colors in low-dimensional space to the feature matrix of high-dimensional color space, and detects the salient area by finding the optimal linear combination of color coefficients . ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/32G06K9/46G06K9/62
CPCG06V10/50G06V10/25G06V10/56G06F18/23213
Inventor 牛玉贞林文奇柯逍陈羽中
Owner FUZHOU UNIV