A Method for Image Description of Local Binary Pattern Based on Filter Bank

A local binary mode and filter bank technology, applied in the field of image processing, can solve problems such as difficult to maintain feature stability, and achieve robustness and anti-interference, accuracy and reliability advantages, accurate and effective face recognition effect

Active Publication Date: 2019-11-22
NANJING UNIV OF POSTS & TELECOMM
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, provide a local binary mode image description method based on filter banks, solve and reduce the influence of factors such as expression, occlusion, and illumination on facial features, which are difficult to maintain The problem of the stability of feature extraction to enhance the ability of LBP descriptors to represent images

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
  • A Method for Image Description of Local Binary Pattern Based on Filter Bank
  • A Method for Image Description of Local Binary Pattern Based on Filter Bank
  • A Method for Image Description of Local Binary Pattern Based on Filter Bank

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0031] Such as figure 1 As shown, the present invention has designed a kind of local binary mode image description method based on filter bank, and this method specifically comprises the following steps:

[0032] Step 1. Divide the input face image into blocks to obtain several image blocks, and adjacent image blocks overlap each other. Normalize all face images to the same size, and set the size of the image block according to actual needs [Block H , Block W ], and then divide the image into multiple different image blocks ImgBlock 1 ,ImgBlock 2 ,ImgBlock 3 ,...,ImgBlock N , and two adjacent image blocks overlap each other, preferably, an overlapping ratio is set between adjacent image blocks, and the overlapping ratio is 0.5.

[0033] Step 2. Carry out convolution filtering processing based on filter banks on each image block, and perform LBP encoding o...

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 discloses a local two -value pattern image description method based on the filter group, including: to obtain several image blocks for the input face images;Filter, and each image block after convolution filtering for LBP encoding to obtain several FBLBP values of each image block; statistics on several FBLBP values obtained by each image block to obtain each filter mode modeFBLBP histogram features, and combine FBLBP histogram features in all filter modes in the filter group in order into the FBLBP histogram feature of the image block;Get up to form the right characteristic vector of the face image.The present invention uses a local image and filter component to obtain a response instead of pixels to encode the image to obtain the multi -scale information of the image, so that the LBP operator is more robust and anti -interference, which can enhance the LBP descriptors to the image to the image.Activity ability.

Description

technical field [0001] The invention relates to a local binary mode image description method based on a filter bank, belonging to the technical field of image processing. Background technique [0002] Object detection is an important research topic in the field of computer vision, and has a wide range of applications in many fields such as intelligent video surveillance, human-computer interaction, and visual navigation. It is at the bottom of the entire video processing system and is the basis for various subsequent advanced processing such as target tracking, target classification, behavior recognition, scene understanding, etc. Target detection is the front-end link of the tracking system, and effective detection is the basis and premise to ensure the smooth progress of subsequent recognition and tracking. [0003] The local feature description operator is an important part of target feature extraction, and has been paid more and more attention by scholars in the field o...

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 & AuthorityPatents(China)
IPC IPC(8): G06K9/46
CPCG06V10/50G06V2201/07
Inventor孙宁闫恒超李晓飞
OwnerNANJING UNIV OF POSTS & TELECOMM