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

Method and device for acquiring LBP characteristics

An acquisition method and bit technology, applied in the field of image processing, can solve the problems of consumption, large system resources, low efficiency of LBP features, etc., and achieve the effect of improving acquisition efficiency, obvious efficiency, and reducing system resource consumption.

Active Publication Date: 2015-08-19
TENCENT TECH (SHENZHEN) CO LTD
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the embodiments of the present invention is to provide a method for acquiring LBP features, so as to solve the problem that a large amount of system resources are consumed when processing images in the prior art, and the efficiency of acquiring LBP features is low

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
  • Method and device for acquiring LBP characteristics
  • Method and device for acquiring LBP characteristics
  • Method and device for acquiring LBP characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] figure 2 The implementation process of the method for acquiring LBP features provided by the first embodiment of the present invention is shown, and the details are as follows:

[0027] In step S201, the gray value of the central pixel of the LBP feature to be calculated and the gray value of P pixels around the central pixel are acquired.

[0028] Specifically, the P pixels around the central pixel are related to the neighborhood radius R of the central pixel and the value defined by the user. For example, when the neighborhood radius R of the central pixel is 1, it includes 8 adjacent Pixel, the user can also define the adjacent pixels in the four directions of up, down, left and right.

[0029] The gray value of the pixel refers to the color depth of a point in a black and white image, generally ranging from 0 to 255, with white being 255 and black being 0. According to the needs of image storage and calculation, the gray value of the pixel can be compressed, such...

Embodiment 2

[0035] image 3 The implementation process of acquiring the LBP features provided by the second embodiment of the present invention is shown, and the details are as follows:

[0036] In step S301, allocate Q in the storage area N-1 storage units, each storage unit includes at least N-1 bits, and defines each storage unit and array (M 1 , M 2 , M 3 ... M N )correspond.

[0037] Specifically, the storage area may be a hard disk, a buffer, or a memory. In order to improve image processing efficiency and consider the size of the storage space, the storage area is generally set as a memory.

[0038] Since the range of the gray value of each pixel is [0, Q), the number of possible values ​​obtained by combining N-1 surrounding pixels with a fixed central pixel is Q N-1For each corresponding value, N-1 surrounding pixels correspond to N-1 cases of greater than or equal to or less than, and N-1 data bits are allocated to store the corresponding comparison results.

[0039] In s...

Embodiment 3

[0053] Figure 5 The implementation process of the method for acquiring LBP features provided by the third embodiment of the present invention is shown, and the details are as follows:

[0054] In step S501, the gray value of the central pixel of the LBP feature to be calculated and the gray value of P pixels around the central pixel are obtained.

[0055] In step S502, the acquired gray value data is compressed, the acquired gray value data is the gray value of the central pixel of the LBP feature to be calculated and the gray values ​​of P pixels around the central pixel value.

[0056] Wherein, the step of compressing the acquired gray value data is specifically:

[0057] According to the pre-stored gray value range, the acquired gray value data is compressed by a linear interpolation method.

[0058] In step S503, according to the corresponding relationship between the pre-stored gray value array and the LBP feature, search for the gray value of the central pixel of the...

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 invention is suitable for the field of image processing, and provides a method and device for acquiring LBP characteristics. The method comprises the steps: acquiring the gray value of a central pixel and the gray values of P pixels surrounding the central pixel, wherein the LBP characteristics of the central pixel need to be calculated; and searching the LBP characteristics corresponding to the gray value of the central pixel and the gray values of P pixels surrounding the central pixel according to the corresponding relation of a prestored gray value group and LBP characteristics. According to the invention, the LBP characteristics corresponding to the gray value group can quickly found through the preset initialization storage. The method and device can effectively reduce the consumption of system resources, improves the acquiring efficiency of LBP characteristics, and, especially, is higher in efficiency for the processing of big images or a plurality of images.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a method and device for acquiring LBP features. Background technique [0002] In the field of digital image processing and pattern recognition, LBP (full name in Chinese is Local Binary Patterns, full name in English is Local Binary Patterns) feature is an effective feature used to describe image texture features, and is widely used in image processing for pedestrian detection, Face recognition, face detection and other fields. [0003] Such as figure 1 In order to obtain a simple schematic diagram of LBP features, the distance between the central pixel and 8 adjacent pixels is R=1, and the gray value of the central pixel is the threshold value, and the 8 gray values ​​​​of its neighborhood are compared with the threshold , the pixel smaller than the threshold is represented by 0, otherwise it is represented by 1. Then read out 8 binary values ​​according to the set direction, w...

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 Applications(China)
IPC IPC(8): G06T7/00
Inventor 李岩
Owner TENCENT TECH (SHENZHEN) CO LTD