All Projects → xinyuexy → Vehicle-Logo-Recognition

xinyuexy / Vehicle-Logo-Recognition

Licence: other
vehicle logo location and recognition

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Vehicle-Logo-Recognition

epic-awesome-gamer
🍷 Gracefully claim weekly free games and monthly content from Epic Store.
Stars: ✭ 600 (+3057.89%)
Mutual labels:  opencv-python
udacity-cvnd-projects
My solutions to the projects assigned for the Udacity Computer Vision Nanodegree
Stars: ✭ 36 (+89.47%)
Mutual labels:  opencv-python
Resolvedor-de-Sudoku
Resolver Sudoku de genina.com
Stars: ✭ 17 (-10.53%)
Mutual labels:  opencv-python
real-time-face-recognition
Real Time Face Recognition using FaceNet and OpenCV
Stars: ✭ 19 (+0%)
Mutual labels:  opencv-python
Fourier-and-Images
Fourier and Images
Stars: ✭ 81 (+326.32%)
Mutual labels:  opencv-python
rps-cv
A Rock-Paper-Scissors game using computer vision and machine learning on Raspberry Pi
Stars: ✭ 102 (+436.84%)
Mutual labels:  opencv-python
CV
Computer Vision applications using #Python and #OpenCV
Stars: ✭ 19 (+0%)
Mutual labels:  opencv-python
STUDENT-ATTENDANCE-USING-FACIAL-RECOGNITION-SYSTEM-OPENCV
No description or website provided.
Stars: ✭ 46 (+142.11%)
Mutual labels:  opencv-python
FaceRecoginition
利用opencv+keras+python实现人脸识别系统
Stars: ✭ 26 (+36.84%)
Mutual labels:  opencv-python
imagehub
Receive and save images from multiple Raspberry Pi's
Stars: ✭ 21 (+10.53%)
Mutual labels:  opencv-python
scarecrow
A Raspberry Pi powered, distributed (edge) computing camera setups that runs a Tensorflow object detection model to determine whether a person is on the camera. A plugin model allows actions based on the detection, such as playing audio, turning on lights, or triggering an Arduino.
Stars: ✭ 87 (+357.89%)
Mutual labels:  opencv-python
OpenCVB
OpenCV .Net application supporting several RGBD cameras - Kinect, Intel RealSense, Luxonis Oak-D, Mynt Eye D 1000, and StereoLabs ZED 2
Stars: ✭ 60 (+215.79%)
Mutual labels:  opencv-python
computer-vision
Notebook series on interesting topics in computer vision
Stars: ✭ 17 (-10.53%)
Mutual labels:  opencv-python
opencv-python-tutorial
📖 OpenCV-Python image processing tutorial for beginners
Stars: ✭ 2,761 (+14431.58%)
Mutual labels:  opencv-python
creeper
Makeshift Raspberry Pi Security Camera System
Stars: ✭ 29 (+52.63%)
Mutual labels:  opencv-python
VBT-Barbell-Tracker
A proof of concept app to optically track a barbell through its range of motion using OpenCV to give the lifter realtime feedback on concentric avg velocity, cutoff velocity, and displacement for a Velocity Based Training program.
Stars: ✭ 53 (+178.95%)
Mutual labels:  opencv-python
FaceRecog
Realtime Facial recognition system using Siamese neural network
Stars: ✭ 47 (+147.37%)
Mutual labels:  opencv-python
HandGesturesDroneController
Hand Gestures for Drone Control Using Deep Learning ✊ ✋ 🚁 ☝️ 🙌
Stars: ✭ 23 (+21.05%)
Mutual labels:  opencv-python
Python-Funscript-Editor
Funscript Editor written in Python with an motion tracking add-on to partially automate the generation of funscripts
Stars: ✭ 21 (+10.53%)
Mutual labels:  opencv-python
Face-Recognition-Attendance-System
A simple python script that recognises faces and mark attendance for the recognised faces in an excel sheet.
Stars: ✭ 57 (+200%)
Mutual labels:  opencv-python

基于python-opencv的车标定位与识别

环境:python2.7+opencv3.2.0

代码说明:

定位模块:location.py

  1. 定位车牌:在HSV下过滤蓝色-->边缘检测,腐蚀膨胀-->查找轮廓(满足长宽比和面积要求)
  2. 粗定位车标:根据定位出的车牌和车标相对位置,可大致定位车标范围
  3. 二次定位车标:对粗定位的车标范围进行二值化、边缘检测、形态学等操作以剔除背景再使用opencv函数查找轮廓,
    取满足要求的最大轮廓即为车标区域,将其存储在logo2.jpg

特征提取模块:recognition.py

  1. 采用LBP作为特征进行车标识别,分别实现了基本3x3LBP、圆形LBP以及uniform LBP。
  2. 使用圆形LBP。首先提取图像LBP,然后计算其LBPH(LBP的统计直方图)作为特征向量。

主模块:main.py

logo template文件夹下为训练用的车标模板,共七类,每一类30张车标图像。vehicle文件夹下为用于定位的卡口车辆图像。

  1. 建立特征库:读取每一类下车标图像,求LBPH后取平均值作为该类车标的特征向量。 使用两个列表分别保存每一类车标的特征向量和对应的类别标签,将其使用python对象 。 持久化到feature.dat文件中,下次直接载入即可。
  2. 预测:读取待识别车标(logo2.jpg),计算其LBPH,利用opencv直方图匹配函数将其与每一类的车标特征向量进行比较,最相似的即为该车标对应的类别

结果展示

车牌定位结果:

车标定位结果:

最终结果:

参考资料:

LBP原理及实现:http://blog.csdn.net/quincuntial/article/details/50541815
python-opencv:http://docs.opencv.org/trunk/d6/d00/tutorial_py_root.html

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].