Online Machine Learning tools

 

 Multiclass Image Classification

https://teachablemachine.withgoogle.com/train/image

Volume Fractions

Thesis

[1] Smooth Interface Reconstruction from Volume Fraction Data Using Variational
Techniques and Level Set Methods

https://escholarship.org/content/qt2466j56f/qt2466j56f_noSplash_4c9dcb1c6cacafb1bcdc4a7bab220630.pdf?t=odypru

 

Volume Fractions in Rectangular Grids

Analytical Relations Connecting Linear Interfaces and Volume Fractions in Rectangular Grids
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.536.848&rep=rep1&type=pdf
[1] Markers - A front-tracking algorithm for accurate representation of surface tension (Zaleski)
https://hal.archives-ouvertes.fr/hal-01445441/document



[2] Level Set Methods (LSM)
[2.1] Tutorial Level Set vs Marching Methods https://math.berkeley.edu/~sethian/2006/Explanations/level_set_explain.html

[2.2-1] Part I (Def) https://wiseodd.github.io/techblog/2016/11/05/levelset-method/
[2.2-2] Part II(Application for segmentation) https://wiseodd.github.io/techblog/2016/11/20/levelset-segmentation/

Transformers in Computer Vision

 

[1] Review https://sh-tsang.medium.com/review-vision-transformer-vit-406568603de0

[2] Colab ViT Tutorial https://colab.research.google.com/github/hirotomusiker/schwert_colab_data_storage/blob/master/notebook/Vision_Transformer_Tutorial.ipynb

[3] ViT pytorch https://github.com/lucidrains/vit-pytorch

[4] Vit Keras https://wandb.ai/ayush-thakur/keras_cv_vit/reports/Image-Classification-Using-Vision-Transformer-and-KerasCV--VmlldzozNTE4MzMz

[5] Fine tunning https://huggingface.co/blog/fine-tune-vit

[6] Full material https://github.com/cmhungsteve/Awesome-Transformer-Attention

Amazonas deforestation

 

Main page

[1] http://terrabrasilis.dpi.inpe.br/en/home-page/

Dataset

[2] http://www.dpi.inpe.br/prodesdigital/dadosn/

[3] 2005-2009 http://www.dpi.inpe.br/prodesdigital/dadosn/mosaicos/

[4] Image 9GB http://www.dpi.inpe.br/prodesdigital/dadosn/mosaicos/2019/

VideoChat Background Filter

 

[1] https://github.com/scumjr/cameo

 

Keypoints from Pose Estimation

 

 [1]  https://google.github.io/mediapipe/solutions/pose

 

Jetson Nano Resources

 

[1] NVIDIA https://developer.nvidia.com/open-source

Segmentation Lectures

https://medium.com/free-code-camp/mask-r-cnn-explained-7f82bec890e3
https://www.analyticsvidhya.com/blog/2019/07/computer-vision-implementing-mask-r-cnn-image-segmentation/

Image Segmentation using Deep Learning resources

[1] https://www.nature.com/articles/s41699-020-0137-z.pdf

https://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC5729043&blobtype=pdf

https://borda.github.io/pyImSegm/

http://vision.cs.utexas.edu/projects/keysegments/keysegments.html

3D Face reconstruction resources

[1] Python code  https://github.com/YadiraF/face3d
[2] Torch+Lua? https://github.com/AaronJackson/vrn
[3] Complete body https://github.com/vchoutas/smplify-x
[4] https://medium.com/vitalify-asia/create-3d-model-from-a-single-2d-image-in-pytorch-917aca00bb07
[5] Based on ShapeNet https://github.com/nywang16/Pixel2Mesh
[6] https://github.com/microsoft/Deep3DFaceReconstruction

Tools online
[1] 3D Model from single face picture https://cvl-demos.cs.nott.ac.uk/vrn/
[2] Search in github https://github.com/topics/3d-face-reconstruction


Resources
[1] https://paperswithcode.com/task/3d-face-reconstruction

Coffee Rust

Based on Deep Learning

[1] Deep Learning for Classification and Severity Estimation of Coffee Leaf BioticStresshttps://arxiv.org/pdf/1907.11561.pdf



Datasets Coffee Rust
[1] Coffe leaves https://github.com/esgario/lara2018/tree/master/classifier
[2] https://www.digipathos-rep.cnptia.embrapa.br/

DeepHuman: Single image to 3D model

Paper https://www.profillic.com/paper/arxiv:1903.06473
Code https://github.com/ZhengZerong/DeepHuman

Avatar Lectures

Resources:

[1] Avatar SDK https://avatarsdk.com/
     https://webdemo.avatarsdk.com/
[2] https://neurohive.io/en/state-of-the-art/realistic-3d-avatars-from-a-single-image/
[3] https://neurohive.io/en/computer-vision/head-reconstruction-from-internet-photos/
[4] https://neurohive.io/en/state-of-the-art/learning-3d-face-morphable-model-out-of-2d-images/
[5] https://neurohive.io/en/state-of-the-art/method-for-automatic-forensic-facial-reconstruction/
[6] https://sketchfab.com/
[7] https://www.loomai.com/

Mathematic for Surface Reconstruction

Basic Lecture
[1] Plane equation (Esp) https://aga.frba.utn.edu.ar/ecuaciones-del-plano/

[2] Session 69: Flux in 2D,  https://ocw.mit.edu/courses/mathematics/18-02sc-multivariable-calculus-fall-2010/3.-double-integrals-and-line-integrals-in-the-plane/part-c-greens-theorem/session-69-flux-in-2d/

[3] Green's theorem http://www.math.mcgill.ca/jakobson/courses/ma265/green.pdf
[4] Flux, Surface Integral and Gauss' Law http://www.phys.boun.edu.tr/~burcin/Flux.pdf
[5] http://people.csail.mit.edu/tieu/notebook/imageproc/tang82.pdf

Spanish
[1] Cálculo diferencial intranetua.uantof.cl/estudiomat/calculo3/stewart.pdf
     http://intranetua.uantof.cl/estudiomat/calculo3/

TensorFlow Example for learn

Examples:

[1] https://github.com/aymericdamien/TensorFlow-Examples/tree/master/notebooks/3_NeuralNetworks



Tensor decomposition (for read)

[1] https://github.com/Large-Scale-Tensor-Decomposition/tensorD
[2] https://smile-lab-tensord.readthedocs.io/en/latest/guide_decomposition.html

Ubuntu 16 OpenCV 2.4

Problems during compilation:

relocation R_X86_64_32 against `ff_a64_muxer' can not be used when making a shared object

Solution:
recompile ffmpeg-3.4.5 with(2018-11-29):
./configure --enable-nonfree --enable-pic --enable-shared

Download ffmpeg and build 3.4.5, 3.2.12 or 4.0 and try to compile opencv doesn't help, then

Final solution: disable ffmpeg
$cmake  -D WITH_CUDA=OFF -D WITH_FFMPEG=0 ..
$make

That compile opencv 2.4.x and 3.4.x



References:
[1] Error sys/videoio.h not found problem http://yutopapa.hatenadiary.com/entry/2017/06/08/173149

video face fake

Resources:
[1] Original article (pt) https://medium.com/ensina-ai/deep-fakes-ao-vivo-que-tal-entrar-em-uma-video-confer%C3%AAncia-com-o-rosto-de-outra-pessoa-92fc8c2d5726

[2] source code using docker https://github.com/alew3/faceit_live

OpenCV 2.4.9 and 3.4.1 Compiling

2.4.x

CUDA_nppi_LIBRARY  CUDA 7.5 -> 8.0 (was removed)
  -D WITH_CUDA=OFF ..

c++ 6 fatal error: stdlib.h: No such file or directory

 export CC=path_of_gcc/gcc-version
 export CXX=path_of_g++/g++-version
 cmake  path_of_project_contain_CMakeList.txt
 make 

OR

 #Current version is 6, but we need to compile using another version (installed for sure)

$CC="gcc-4.9" CXX="g++-4.9" cmake /CMakeLists.txt 

OR$cmake -G "Unix Makefiles" -DCMAKE_CXX_COMPILER=/usr/bin/g++ CMAKE_C_COMPILER=/usr/bin/gcc -DCMAKE_BUILD_TYPE=RELEASE -DCMAKE_INSTALL_PREFIX=/usr/local -DWITH_TBB=ON -DBUILD_NEW_PYTHON_SUPPORT=ON -DWITH_V4L=ON -DINSTALL_C_EXAMPLES=ON -DINSTALL_PYTHON_EXAMPLES=ON -DBUILD_EXAMPLES=ON -DWITH_QT=ON -DWITH_OPENGL=ON -DBUILD_FAT_JAVA_LIB=ON -DINSTALL_TO_MANGLED_PATHS=ON -DINSTALL_CREATE_DISTRIB=ON -DINSTALL_TESTS=ON -DENABLE_FAST_MATH=ON -DWITH_IMAGEIO=ON -DBUILD_SHARED_LIBS=OFF -DWITH_GSTREAMER=ON -DWITH_OPENMP=OFF -DWITH_CUDA=OFF -DBUILD_opencv_gpu=OFF ..

3.4.x

Unknown CMake command "ocv_append_source_files_cxx_compiler_options".

This happened when the opencv_contrib version is no compatible with your current version.

cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D WITH_TBB=ON -D BUILD_NEW_PYTHON_SUPPORT=ON -D WITH_V4L=ON -D INSTALL_C_EXAMPLES=ON -D INSTALL_PYTHON_EXAMPLES=ON -D BUILD_EXAMPLES=ON -D WITH_QT=ON -D WITH_OPENGL=ON -D OPENCV_EXTRA_MODULES_PATH=../../opencv_contrib/modules/ ..


$make
$sudo make install
$sudo ldconfig

After installation, if doesn't compile, check the files opencv.conf and opencv.pc:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
#/etc/ld.so.conf.d/opencv.conf
/usr/local/lib
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
#/usr/local/lib/pkgconfig/opencv.pc

prefix=/usr/local
exec_prefix=${prefix}
libdir=${exec_prefix}/lib
includedir_old=${prefix}/include/opencv
includedir_new=${prefix}/include

Name: OpenCV
Description: Open Source Computer Vision Library
Version: 2.4.13.6
Libs: -L${exec_prefix}/lib -lopencv_contrib -lopencv_legacy -lopencv_stitching -lopencv_nonfree -lopencv_superres -lopencv_ocl -lopencv_objdetect -lopencv_ml -lopencv_ts -lopencv_videostab -lopencv_video -lopencv_photo -lopencv_calib3d -lopencv_features2d -lopencv_highgui -lopencv_imgproc -lopencv_flann -lopencv_core -L/usr/lib/x86_64-linux-gnu -lIlmThread -lHalf -lIex -lIlmImf -lImath -ljasper -ltiff -lpng -ljpeg -lavutil -lswscale -lswresample -lavcodec -lz -llzma -lxcb-shape -lxcb-render -lxcb-xfixes -lxcb-shm -lxcb -lavformat -lv4l2 -lv4l1 -ldc1394 -lGL -lGLU -latomic -ltbb -lrt -lpthread -lm -ldl -lstdc++
Cflags: -I${includedir_old} -I${includedir_new}

 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -


Resources:

[1] opencv github (choice right branch) https://github.com/opencv/opencv

[1] opencv_contrib is just from 3.0 .. https://github.com/opencv/opencv_contrib/releases
[2] Steps for install () http://karytech.blogspot.com/2012/05/opencv-24-on-ubuntu-1204.html
[3] Script for install under ubuntu16 https://gist.github.com/fortunto2/20a9696c7fc23ef18f8cfc50e371fe5f
[4] Some variables http://daveaubin.com/index.php/how-to-build-and-install-opencv-2-4-9-on-raspberry-pi/

Ubuntu 16 OpenCV 2.4.x disable ffmpeg and jpeg

cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D WITH_TBB=ON -D BUILD_NEW_PYTHON_SUPPORT=ON -D WITH_V4L=ON -D INSTALL_C_EXAMPLES=ON -D INSTALL_PYTHON_EXAMPLES=ON -D BUILD_EXAMPLES=ON -D WITH_QT=ON -D WITH_OPENGL=ON -D WITH_FFMPEG=OFF -D WITH_JPEG=OFF ..

Lectures Neural Networks

Colour and Texture, but fail for shape.

Generative Adversarial Networks
https://arxiv.org/pdf/1406.2661.pdf

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks https://junyanz.github.io/CycleGAN/