Font Size: a A A

Research On Vehicle Logo Recognition Method Based On SIFT

Posted on:2018-07-02Degree:MasterType:Thesis
Country:ChinaCandidate:C ChenFull Text:PDF
GTID:2322330542468918Subject:Control engineering
Abstract/Summary:PDF Full Text Request
Vehicle logo,as the key information of vehicle,combined with other vehicle characteristics will make managing vehicle more effectively in the intelligent transportation system.Vehicle logo recognition,as a not yet mature technology,has attracted the attention of scholars at home and abroad in recent years,it.In this paper,we researched the method of vehicle logo detection and vehicle logo recognition and then we developed vehicle logo recognition software based on the algorithm we proposed.The content of this paper can be divided into the following parts:(1)Research of vehicle logo detection algorithm.In the stage of image preprocessing,in order to tilt the vehicle this paper proposed a SIFT-based vehicle tilt detection and correction method.Then this paper studied a license plate detection method based on Adaboost learning and license plate characteristics,which improved license plate detection rate.At last a fine vehicle logo detection algorithm based on patch pixel intensity and weight matrix was proposed and the advantages of the algorithm was proved by comparing with other vehicle logo detection algorithms through experiment.(2)Research of vehicle logo recognition algorithm:In the aspect of vehicle logo feature extraction,a vehicle logo feature extraction algorithm based on the fusion of SIFT features and Dense-SIFT features was put forward after analyzing the strengths and weaknesses of SIFT features and Dense-SIFT features.Then Bag-of-words model was used to describe vehicle logo features and formed vehicle logo visual dictionary histogram.Considering Bag-of-words model's ignoring spatial structure information of objects,spatial pyramid model was introduced into Bag-of-words model.In the aspect of vehicle logo recognition,vehicle logo was classified by using Support Vector Machine which based on one-against-the-rest multi-classification strategy.Support Vector Machine's advantages was verified through the experiment.(3)Vehicle logo recognition software development:According to the overall requirements and architecture of the vehicle logo recognition software,the vehicle logo detection and recognition algorithm which proposed in this paper were achieved and the vehicle logo recognition software was developed.Then we introduced the software development and pivotal software module.At last software is tested and the performance of software is evaluated from two aspects of functional test and performance test.
Keywords/Search Tags:Vehicle Logo Detection, Vehicle Logo Recognition, SIFT, Bag-of-words Model, Support Vector Machine
PDF Full Text Request
Related items