Ultimate Vocal Remover GUI 튜토리얼

1. 추천 앙상블 모델 이용하여 음원 + 보컬 분리
2. 1번에서 만든 보컬에 코러스 제거 모델로 코러스 제거
3. 2번에서 만든 코러스 제거된 보컬에 에코 제거 

• CV_8U, 8-bit unsigned integers (0..255)
• CV_8S, 8-bit signed integers (-128..127)
• CV_16U, 16-bit unsigned integers (0..65,535)
• CV_16S, 16-bit signed integers (-32,768..32,767)
• CV_32S, 32-bit signed integers (-2,147,483,648..2,147,483,647)
• CV_32F, 32-bit floating-point numbers
• CV_64F, 64-bit floating-point numbers

1. What is OpenCV?

An abbreviation of Open Source Computer Vision, an open source library that can be used for image/video processing.

OpenCV is released under a BSD license, so it's free for academic and commercial use. Therefore, Even if you make money using OpenCV, many companies or individual developers do not share the source code and pay the license fee.

"The Berkeley Software Distribution (BSD) license is so weak that it can't be called a software license, so the software can be modified and distributed by anyone. However, you don't need for modified versions to be open, so many companies and developers can use it in commercial software."

It also supports a variety of interfaces such as C ++, C, Python, and Java, and supports a variety of operating systems such as Windows, Linux, Mac OS, iOS, and Android.

OpenCV is designed algorithmically with a focus on computational efficiency and real-time applications, so you can create commercial applications that can be processed in real-time by simply coding using the APIs provided by OpenCV. 

In addition, OpenCV supports multi-core processing, so it can be applied to various situations.

It is used in various image processing systems such as interactive art, image stitching, factory defect detection systems and robotics.

2. So what can I do?

Figure 1. Edge Detection

Figure 2. Noise reduction

Figure 3. Panoramic photo synthesis using image stitching

3. Reference

3. 참고문헌

2. 주파수(Frequency)로 왜 표현하는가?

• Visual studio 2015
• CUDA 9.0
• cuDNN 7.3.1
• OpenCV 4.0.1

2. 윈도우 버전 YOLO v3 테스트 실행

• yolov3-openimages.cfg (247 MB COCO Yolo v3) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov3-openimages.weights
• yolov3-spp.cfg (240 MB COCO Yolo v3) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov3-spp.weights
• yolov3.cfg (236 MB COCO Yolo v3) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov3.weights
• yolov3-tiny.cfg (34 MB COCO Yolo v3 tiny) - requires 1 GB GPU-RAM: https://pjreddie.com/media/files/yolov3-tiny.weights
• yolov2.cfg (194 MB COCO Yolo v2) - requires 4 GB GPU-RAM: https://pjreddie.com/media/files/yolov2.weights
• yolo-voc.cfg (194 MB VOC Yolo v2) - requires 4 GB GPU-RAM: http://pjreddie.com/media/files/yolo-voc.weights
• yolov2-tiny.cfg (43 MB COCO Yolo v2) - requires 1 GB GPU-RAM: https://pjreddie.com/media/files/yolov2-tiny.weights
• yolov2-tiny-voc.cfg (60 MB VOC Yolo v2) - requires 1 GB GPU-RAM: http://pjreddie.com/media/files/yolov2-tiny-voc.weights
• yolo9000.cfg (186 MB Yolo9000-model) - requires 4 GB GPU-RAM: http://pjreddie.com/media/files/yolo9000.weights

Mat img(nrows, ncols, type, fillValue);

Mat img(256, 256, CV_8U, Scalar(255));

CV_<bit 수>{U or S or F}C<채널수> 

• CV -> Computer Vision
• bit 수 -> 픽셀이 표현하는 데이터의 비트 수
• U -> Unsigned (-부호가 없는 0을 포함한 자연수를 의미)
• S -> Signed(-포함한 정수를 의미)
• F -> Floating point(실수형 표현을 의미)
• 채널 -> 이미지의 채널 수를 의미

2. 이미지 파일 로드하기

그림 4. 코드 실행 후 화면

3. 비디오 캡처하기

그림 5. 실행화면 (캠이 없어서 버추얼 아웃풋이 나오네요..)

4. 참고문헌