Optimal sorting method of non-target images for continuous rapid visual presentation based on color moments
A non-target, color moment technology, applied in the field of electronic information, can solve the problems of ERP induction, classification result influence, error-prone ERP signal induction, etc., achieve good robustness, reduce time and space complexity, improve The effect of classification accuracy
Active Publication Date: 2022-06-07
XIDIAN UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The problem lies in ignoring the fact that the similarity between adjacent non-target pictures is too low, which leads to the ERP signal being easily induced by mistake, which affects the classification results.
However, the problem with this method is that Phash only takes the low-frequency part of the picture in order to tolerate some deformation of the picture, which causes the problem that the features cannot capture the details of the picture, which makes the processing effect of pure color pictures or approximate pure color pictures very poor
Adjacent non-target images of pure color with excessively large color differences are easily identified as similar images by the Phash algorithm, causing ERP to be induced, which in turn may determine the non-target image as the target image, resulting in false alarms
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0028] The following embodiments and effects of the present invention in conjunction with the accompanying drawings are described in detail:
[0029] Reference Figure 1 , the specific implementation steps of the present embodiment are as follows:
[0030] Step 1, perform feature extraction on the picture.
[0031] 1.1) Convert all unsorted non-target images in the continuous rapid visual demonstration from the original RGB color space representation to HSV color space representation, extract the pixel values of the three channels of H, S, and V, and calculate the first-order momentS, second-order moment σ s, and third-order moments of pixels on the three channels of H, S, and V, respectively:
[0032]
[0033]
[0034]
[0035] where h and w represent the height and width of the picture, respectively, P ij Represents the pixel value of column j of row i on each channel;
[0036] 1.2) First-order moment H on the H channel 1 , second-order moment H 2 , third-order moment H 3 ,...
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
Login to View More Abstract
The invention discloses an optimal sorting method for non-target pictures in continuous and rapid visual demonstration based on color moments, which mainly solves the problem of error-induced events caused by low similarity of adjacent pictures of non-target pictures in the existing continuous and rapid visual demonstration RSVP presentation Questions related to potential ERP. The implementation plan is: convert the RGB image into an HSV image, extract the color moment of the pixel on each channel of the HSV image as a feature; transform the pixel values of each channel of an HSV image to generate a simple transformed image, and manually complete the sorting of the simple transformed images , and at the same time sort according to the similarity of the simple transformation pictures, and combine the two sorting results to determine the weight parameters of each channel; for all non-target pictures, use the weight parameters of each channel to calculate the picture similarity and complete the sorting. The invention can realize the optimal sorting of RSVP non-target pictures, can effectively improve the quality of ERP, and can be used for brain-computer interface.
Description
Technical field [0001] The present invention belongs to the field of electronic information technology, mainly relates to a continuous rapid visual presentation in the non-target picture sorting method, can be used in the brain-computer interface. Background [0002] With the continuous progress of social information technology, the problem of information overload has become increasingly serious. As image and video data repositories are growing at an exponential rate, the size, diversity, and potential sparsity of "targets of interest" make it difficult to retrieve targets effectively. Continuous rapid visual demonstration RSVP is a BCI paradigm derived from the continuous development of brain-computer interface BCI technology in recent years, combined with the event-related potential ERP of the human visual system and the cerebral cortex, which is often used to help professionals, such as satellite image scouts, effectively classify a large number of pictures. [0003] The curre...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/583G06T7/90G06T5/00
CPCG06F16/5838G06T7/90G06T5/92
Inventor 李甫王冲吴昊冀有硕牛毅
Owner XIDIAN UNIV