All Projects → brookicv → imageRetrieval

brookicv / imageRetrieval

Licence: other
Image retrieval learning record

Programming Languages

c
50402 projects - #5 most used programming language
C++
36643 projects - #6 most used programming language
objective c
16641 projects - #2 most used programming language

Projects that are alternatives of or similar to imageRetrieval

Sola
Scene search On Liresolr for Animation. (and video)
Stars: ✭ 253 (+716.13%)
Mutual labels:  image-retrieval
panoramas-image-stitching
🖼 Stitching images into 360 panoramas
Stars: ✭ 155 (+400%)
Mutual labels:  opencv3
GPQ
Generalized Product Quantization Network For Semi-supervised Image Retrieval - CVPR 2020
Stars: ✭ 60 (+93.55%)
Mutual labels:  image-retrieval
CIRR
Official repository of ICCV 2021 - Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
Stars: ✭ 65 (+109.68%)
Mutual labels:  image-retrieval
cisip-FIRe
Fast Image Retrieval (FIRe) is an open source project to promote image retrieval research. It implements most of the major binary hashing methods to date, together with different popular backbone networks and public datasets.
Stars: ✭ 40 (+29.03%)
Mutual labels:  image-retrieval
gocv-playground
This repo contains various https://gocv.io/ examples
Stars: ✭ 29 (-6.45%)
Mutual labels:  opencv3
Delf Pytorch
PyTorch Implementation of "Large-Scale Image Retrieval with Attentive Deep Local Features"
Stars: ✭ 245 (+690.32%)
Mutual labels:  image-retrieval
DeepMask
A Keras implementation of DeepMask based on NIPS 2015 paper "Learning to Segment Object Candidates"
Stars: ✭ 15 (-51.61%)
Mutual labels:  opencv3
natural-language-joint-query-search
Search photos on Unsplash based on OpenAI's CLIP model, support search with joint image+text queries and attention visualization.
Stars: ✭ 143 (+361.29%)
Mutual labels:  image-retrieval
ESP32-CAM-MJPEG-Stream-Decoder-and-Control-Library
The library is MJPEG stream decoder based on libcurl and OpenCV, and written in C/C++.
Stars: ✭ 40 (+29.03%)
Mutual labels:  opencv3
Landmark-Retrival
Easy Landmark Image Recognition with TensorFlow Hub DELF Module
Stars: ✭ 20 (-35.48%)
Mutual labels:  image-retrieval
proxy-synthesis
Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)
Stars: ✭ 30 (-3.23%)
Mutual labels:  image-retrieval
Image-Retrieval
Image retrieval program made in Tensorflow supporting VGG16, VGG19, InceptionV3 and InceptionV4 pretrained networks and own trained Convolutional autoencoder.
Stars: ✭ 56 (+80.65%)
Mutual labels:  image-retrieval
SegSwap
(CVPRW 2022) Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
Stars: ✭ 46 (+48.39%)
Mutual labels:  image-retrieval
opencv3-setup
Raspberry Pi whiptail Menu driven Easy Install and Compile of opencv3 python from source files.
Stars: ✭ 47 (+51.61%)
Mutual labels:  opencv3
Openunreid
PyTorch open-source toolbox for unsupervised or domain adaptive object re-ID.
Stars: ✭ 250 (+706.45%)
Mutual labels:  image-retrieval
LabelRelaxation-CVPR21
Official PyTorch Implementation of Embedding Transfer with Label Relaxation for Improved Metric Learning, CVPR 2021
Stars: ✭ 37 (+19.35%)
Mutual labels:  image-retrieval
img classification deep learning
No description or website provided.
Stars: ✭ 19 (-38.71%)
Mutual labels:  image-retrieval
cnn-for-image-retrieval
🌅The code of post "Image retrieval using MatconvNet and pre-trained imageNet"
Stars: ✭ 623 (+1909.68%)
Mutual labels:  image-retrieval
Huawei DIGIX ImageRetri Top2
2020 DIGIX GLOBAL AI CHALLENGE - Digital Device Image Retrieval - Top2 WEARE队
Stars: ✭ 63 (+103.23%)
Mutual labels:  image-retrieval

Image Retrieval

在构建图像特征库的时候,通常不会使用原始的图像特征,这是由于Raw Feature有很多冗余信息,而且维度过高在构建特征数据库和匹配的时候效率较低。所以,通常要对提取到的原始特征进行重新编码。比较常用的三种编码方式:

  • BoF , Bog of Feature 源于文本处理的词袋模型(Bog,Bag of Words)
  • VLAD , Vector of Aggragate Locally Descriptor
  • FV , fisher vector

特征提取

  • vlfeat sift 特征提取
  • PCA降维
  • kmeans聚类

编码方式

  • BoF
  • VLAD
  • FV

源码结构说明

  • DBow3 开源的词袋模型库
    • src 源代码
    • test 简单的使用DBow3的测试代码
  • vlfeat 轻量级的视觉库
  • src 图像检索的源代码

version 0.1

上面一些基础的东西已经陆续实现了,接下来使用OpenCV实现一个简单的图像检索应用,包括:

  • Vocabulary的创建、保存、加载
  • 图像数据库的创建、保存、加载
  • 图像的vlad表示
  • 检索,返回类似的图片

 这里只使用的VLAD表示图像,而没有测试BoW的原因是,电脑不行,BoW需要的Vocabulary的尺寸太大,训练时间太长。

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].