본문 바로가기
728x90
반응형

코드9

[face recognition] Adaface : Quality Adaptive Margin for Face Recognition https://github.com/mk-minchul/AdaFace.git GitHub - mk-minchul/AdaFaceContribute to mk-minchul/AdaFace development by creating an account on GitHub.github.compaper : https://arxiv.org/abs/2204.00964 AdaFace: Quality Adaptive Margin for Face RecognitionRecognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss function.. 2024. 3. 11.
[matlab] Andrea Fusiello, Rectification of Stereo Images 스테레오 이미지 정류 알고리즘 function [T1,T2,Pn1,Pn2] = rectify(Po1,Po2) % RECTIFY compute rectification matrices % % [T1,T2,Pn1,Pn2] = rectify(Po1,Po2) computes the % rectifying projection matrices "Pn1", "Pn2", and % the rectifying transformation of the retinal plane % "T1", "T2" (in homogeneous coordinate). The arguments % are the two old projection matrices "Po1" and "Po2". % focal lenght % (extp(a,b) is external produc.. 2023. 4. 4.
[matlab] 이미지 리사이즈 코드 file = dir(fullfile('\.\*.jpg')); for i = 1 : length(file) img = imread(strcat(file(i).folder,'\',file(i).name)); img = imresize(img,[800 800]); % 800 800 대신 변경하고자 하는 값 입력 imshow(img) imwrite(img,strcat(file(i).folder,'\',file(i).name)); end 2023. 3. 20.
[python] 이미지 증강 코드 data augmentaion import random import numpy as np import os import cv2 import glob from PIL import Image import PIL.ImageOps #다음 변수를 수정하여 새로 만들 이미지 갯수를 정합니다. num_augmented_images = 50 file_path = '.\.\\' file_names = os.listdir(file_path) total_origin_image_num = len(file_names) augment_cnt = 1 for i in range(1, num_augmented_images): change_picture_index = random.randrange(1, total_origin_image_num-1) print(cha.. 2023. 3. 20.
728x90
반응형

티스토리툴바