pochih / Cbir
🏞 A content-based image retrieval (CBIR) system
Stars: ✭ 407
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Cbir
Deep Ranking
Learning Fine-grained Image Similarity with Deep Ranking is a novel application of neural networks, where the authors use a new multi scale architecture combined with a triplet loss to create a neural network that is able to perform image search. This repository is a simplified implementation of the same
Stars: ✭ 64 (-84.28%)
Mutual labels: resnet, image-retrieval
Cnn Models
ImageNet pre-trained models with batch normalization for the Caffe framework
Stars: ✭ 355 (-12.78%)
Mutual labels: resnet
Person Reid gan
ICCV2017 Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
Stars: ✭ 301 (-26.04%)
Mutual labels: image-retrieval
Self Label
Self-labelling via simultaneous clustering and representation learning. (ICLR 2020)
Stars: ✭ 324 (-20.39%)
Mutual labels: resnet
Deepxi
Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.
Stars: ✭ 304 (-25.31%)
Mutual labels: resnet
Deeplabv3plus Pytorch
DeepLabv3, DeepLabv3+ and pretrained weights on VOC & Cityscapes
Stars: ✭ 337 (-17.2%)
Mutual labels: resnet
Computer Vision Leaderboard
Comparison of famous convolutional neural network models
Stars: ✭ 299 (-26.54%)
Mutual labels: image-retrieval
Pytorch classification
利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码
Stars: ✭ 395 (-2.95%)
Mutual labels: resnet
Hardnet
Hardnet descriptor model - "Working hard to know your neighbor's margins: Local descriptor learning loss"
Stars: ✭ 350 (-14%)
Mutual labels: image-retrieval
Metric
Minimal metrics for Go (counter/gauge/histogram). No dependencies. Compatible with expvar. Web UI included.
Stars: ✭ 319 (-21.62%)
Mutual labels: histogram
Rezero
Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"
Stars: ✭ 317 (-22.11%)
Mutual labels: resnet
Real Time Gesrec
Real-time Hand Gesture Recognition with PyTorch on EgoGesture, NvGesture, Jester, Kinetics and UCF101
Stars: ✭ 339 (-16.71%)
Mutual labels: resnet
Batch Dropblock Network
Official source code of "Batch DropBlock Network for Person Re-identification and Beyond" (ICCV 2019)
Stars: ✭ 304 (-25.31%)
Mutual labels: image-retrieval
Tf Faster Rcnn
Tensorflow Faster RCNN for Object Detection
Stars: ✭ 3,604 (+785.5%)
Mutual labels: resnet
Deepslide
Code for the Nature Scientific Reports paper "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks." A sliding window framework for classification of high resolution whole-slide images, often microscopy or histopathology images.
Stars: ✭ 315 (-22.6%)
Mutual labels: resnet
Artificio
Deep Learning Computer Vision Algorithms for Real-World Use
Stars: ✭ 326 (-19.9%)
Mutual labels: image-retrieval
Fpn tensorflow
A Tensorflow implementation of FPN detection framework.
Stars: ✭ 407 (+0%)
Mutual labels: resnet
Basic cnns tensorflow2
A tensorflow2 implementation of some basic CNNs(MobileNetV1/V2/V3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1/V2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet).
Stars: ✭ 374 (-8.11%)
Mutual labels: resnet
Intro
This repository contains a CBIR (content-based image retrieval) system
Extract query image's feature, and retrieve similar ones from image database
Image src
Part1: Feature Extraction
In this system, I implement several popular image features:
- color-based
- texture-based
- shape-based
- deep methods
all features are modulized
Feature Fusion
Some features are not robust enough, and turn to feature fusion
Dimension Reduction
The curse of dimensionality told that vectors in high dimension will sometimes lose distance property
Part2: Evaluation
CBIR system retrieves images based on feature similarity
Robustness of system is evaluated by MMAP (mean MAP), the evaluation formulas is refer to here
- image AP : average of precision at each hit
- depth=K means the system will return top-K images
- a correct image in top-K is called a hit
- AP = (hit1.precision + hit2.precision + ... + hitH.precision) / H
- class1 MAP = (class1.img1.AP + class1.img2.AP + ... + class1.imgM.AP) / M
- MMAP = (class1.MAP + class2.MAP + ... + classN.MAP) / N
Implementation of evaluation can found at evaluate.py
My database contains 25 classes, each class with 20 images, 500 images in total, depth=K will return top-K images from database
| Method | color | daisy | edge | gabor | HOG | vgg19 | resnet152 |
|---|---|---|---|---|---|---|---|
| Mean MAP (depth=10) | 0.614 | 0.468 | 0.301 | 0.346 | 0.450 | 0.914 | 0.944 |
Part3: Image Retrieval (return top 5 of each method)
Let me show some results of the system
query1 - women dress
query 
color 
daisy 
edge 
gabor 
HOG 
VGG19 
Resnet152 
query2 - orange
query 
color 
daisy 
edge 
gabor 
HOG 
VGG19 
Resnet152 
query3 - NBA jersey
query 
color 
daisy 
edge 
gabor 
HOG 
VGG19 
Resnet152 
query4 - snack
query 
color 
daisy 
edge 
gabor 
HOG 
VGG19 
Resnet152 
Part4: Usage of Repository
If you are interesting with the results, and want to try your own images,
Please refer to USAGE.md
The details are written inside.
Author
Po-Chih Huang / @pochih
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].