berak

#include <iostream>
#include <fstream>
#include "opencv2/opencv.hpp"
#include "opencv2/ximgproc.hpp"
using namespace cv;
using namespace cv::ximgproc;
using std::cout;
using std::endl;

// https://ieeexplore.ieee.org/document/8015123

berak

// Sample of using Halide backend in OpenCV deep learning module.
// Based on caffe_googlenet.cpp.

#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
using namespace cv;
using namespace cv::dnn;
using namespace std;

berak

/*******************************************************************************
* MKCFup										Version 1.0
* Copyright 2018 Bin Yu, UCAS&NLPR, Beijing.	[yubin2017@ia.ac.cn]
* Paper [High-speed Tracking with Multi-kernel Correlation Filters]
*******************************************************************************/
#include <fftw3.h>
#include <opencv2\opencv.hpp>
#include <opencv2\tracking.hpp>
#include <stdio.h>
#include <stdlib.h>

berak

C:\data\mdl>ls -l lbfmodel.yaml
-rw-r--r-- 1 ppp 197121 56375857 Jun 14 12:27 lbfmodel.yaml

C:\data\mdl>head -c 1000 lbfmodel.yaml
%YAML:1.0
---
stages_n: 5
tree_n: 6
tree_depth: 5
n_landmarks: 68

berak

benchmark --gt=david.gt.txt --video=david.webm --start=300 --plot CSRT,MOSSE,MEDIAN_FLOW,BACF,CMT,MIL,BOOSTING,TLD
==========
CSRT
       Overlap > 0                   100%                 469
       Overlap > 0.5              80.597%                 378
           Precision              80.597%
           Recall                 80.597%
           f-measure              80.597%
                 AUC            0.438657
         Performance             103.987 ms/frame             9.61663 fps

berak

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.opencv.core.Core;
import org.opencv.core.*;
import org.opencv.core.MatOfFloat;
import org.opencv.core.MatOfByte;
import org.opencv.core.Scalar;

berak

C:\p\ocv\dnn>dnn_print -m=C:\p\ocv\PCN-FaceDetection-FaceAlignment-master\code\model\PCN.caffemodel -p=C:\p\ocv\PCN-FaceDetection-FaceAlignment-master\code\model\PCN-1.
prototxt -W=24 -H=24 -i=C:\p\ocv\PCN-FaceDetection-FaceAlignment-master\imgs\1.jpg -v=3
_input                                   i[1, 3, 24, 24]  o[1, 3, 24, 24]
conv1_1              Convolution         i[1, 3, 24, 24]  o[1, 16, 11, 11]  w[16, 3, 3, 3]  w[16, 1]
relu1_1              ReLU                i[1, 16, 11, 11]  o[1, 16, 11, 11]
conv2_1              Convolution         i[1, 16, 11, 11]  o[1, 32, 5, 5]  w[32, 16, 3, 3]  w[32, 1]
relu2_1              ReLU                i[1, 32, 5, 5]  o[1, 32, 5, 5]
conv3_1              Convolution         i[1, 32, 5, 5]  o[1, 64, 2, 2]  w[64, 32, 3, 3]  w[64, 1]
relu3_1              ReLU                i[1, 64, 2, 2]  o[1, 64, 2, 2]
fc4_1                Convolution         i[1, 64, 2, 2]  o[1, 128, 1, 1]  w[128, 64, 2, 2]  w[128, 1]

berak

#include "brisque.h"
#include "libsvm/svm.h"

/*
float computescore(char* imagename){


    float qualityscore;

    char* filename = "test.txt";

berak

#include "brisque.h"


//function definitions
static void AGGDfit(const cv::Mat & structdis, double& lsigma_best, double& rsigma_best, double& gamma_best)
{
    cv::Mat_<double> Imarr(structdis);
    long int poscount=0, negcount=0;
    double possqsum=0, negsqsum=0, abssum=0;
    for (int i=0;i<structdis.rows;i++)

berak

:- use_module(library(socket)).

irc :-
    NICK="cvtail",
    CHAN="#p4p4p4",
    Adress = 'irc.freenode.net':6667,
    tcp_socket(Socket),
    tcp_connect(Socket, Adress, Read, Write),
    write_list(Write,["PASS i_am_",NICK]),
    write_list(Write,["USER ",NICK," 12 * ",NICK]),