碼上快樂

相關內容    簡體    繁體

人臉姿態校正算法 附完整C++示例代碼

本文轉載自   查看原文   2018-05-08 21:42   4888    人臉姿態校正/ 人臉傾斜/ 圖像處理/ 人臉矯正/ 表情識別/ 照片傾斜

在一些特殊情況下，經常需要依據圖像中的人臉，對圖片進行傾斜矯正。

 

例如拍照角度幅度過大之類的情況，而進行人工矯正確實很叫人頭大。

那是不是可以有一種算法，可以根據人臉的信息對圖片進行角度的修復呢？

答案肯定是確認的。

 

再次例如，想要通過人臉的特征對人物的表情和情緒進行精准判斷，

那么這個時候如果能確保人臉沒有發現嚴重傾斜，無疑對准確率判斷有一定的幫助。

 

那么假如一張圖片只有一個人臉，其實很好判斷，通過眼睛的位置的坐標，根據兩眼的直線角度，

就可以計算出修正的角度。

然后旋轉圖片到對應角度即可。

但是如果，一張圖片存在多張人臉的時候該怎么辦？

有兩種方法：

1.找到最大的那個人臉，以它為基准

2.找到頻次最高的人臉角度，以頻次為基准

當然在大多數情況，方法1是比較合理的。

這兩個種情況就留給各位看官去實現了。

本人僅僅考慮一張人臉的情況，演示如何實現該功能。

傾斜角度計算的代碼如下:

    float diffEyeX = right_eye_x - left_eye_x;
    float diffEyeY = right_eye_y - left_eye_y;

    float fAngle;
    float M_PI = 3.1415926535897932384626433832795f;
    if (fabs(diffEyeX) < 0.0000001f)
        fAngle = 0.f;
    else
        fAngle = atanf(diffEyeY / diffEyeX) * 180.0f / M_PI;

如果看不明白，需要好好補一下高中數學基礎。

為了節約時間，直接復用《自動紅眼移除算法 附c++完整代碼》的代碼。

增加函數如下:

void RotateBilinear(unsigned char *sourceData, int width, int height, int Channels, int RowBytes,
                    unsigned char *destinationData, int newWidth, int newHeight, float angle, bool keepSize = true,
                    int fillColorR = 255, int fillColorG = 255, int fillColorB = 255) {
    if (sourceData == NULL || destinationData == NULL) return;

    float oldXradius = (float) (width - 1) / 2;
    float oldYradius = (float) (height - 1) / 2;

    float newXradius = (float) (newWidth - 1) / 2;
    float newYradius = (float) (newHeight - 1) / 2;

    double MPI = 3.14159265358979323846;
    double angleRad = -angle * MPI / 180.0;
    float angleCos = (float) cos(angleRad);
    float angleSin = (float) sin(angleRad);

    int srcStride = RowBytes;
    int dstOffset = newWidth * Channels - ((Channels == 1) ? newWidth : newWidth * Channels);

    unsigned char fillR = fillColorR;
    unsigned char fillG = fillColorG;
    unsigned char fillB = fillColorB;

    unsigned char *src = (unsigned char *) sourceData;
    unsigned char *dst = (unsigned char *) destinationData;

    int ymax = height - 1;
    int xmax = width - 1;
    if (Channels == 1) {
        float cy = -newYradius;
        for (int y = 0; y < newHeight; y++) {
            float tx = angleSin * cy + oldXradius;
            float ty = angleCos * cy + oldYradius;

            float cx = -newXradius;
            for (int x = 0; x < newWidth; x++, dst++) {
                float ox = tx + angleCos * cx;
                float oy = ty - angleSin * cx;

                int ox1 = (int) ox;
                int oy1 = (int) oy;

                if ((ox1 < 0) || (oy1 < 0) || (ox1 >= width) || (oy1 >= height)) {
                    *dst = fillG;
                } else {
                    int ox2 = (ox1 == xmax) ? ox1 : ox1 + 1;
                    int oy2 = (oy1 == ymax) ? oy1 : oy1 + 1;
                    float dx1 = 0;
                    if ((dx1 = ox - (float) ox1) < 0)
                        dx1 = 0;
                    float dx2 = 1.0f - dx1;
                    float dy1 = 0;
                    if ((dy1 = oy - (float) oy1) < 0)
                        dy1 = 0;
                    float dy2 = 1.0f - dy1;

                    unsigned char *p1 = src + oy1 * srcStride;
                    unsigned char *p2 = src + oy2 * srcStride;

                    *dst = (unsigned char) (dy2 * (dx2 * p1[ox1] + dx1 * p1[ox2]) +
                                            dy1 * (dx2 * p2[ox1] + dx1 * p2[ox2]));
                }
                cx++;
            }
            cy++;
            dst += dstOffset;
        }
    } else if (Channels == 3) {
        float cy = -newYradius;
        for (int y = 0; y < newHeight; y++) {
            float tx = angleSin * cy + oldXradius;
            float ty = angleCos * cy + oldYradius;

            float cx = -newXradius;
            for (int x = 0; x < newWidth; x++, dst += Channels) {
                float ox = tx + angleCos * cx;
                float oy = ty - angleSin * cx;

                int ox1 = (int) ox;
                int oy1 = (int) oy;

                if ((ox1 < 0) || (oy1 < 0) || (ox1 >= width) || (oy1 >= height)) {
                    dst[0] = fillR;
                    dst[1] = fillG;
                    dst[2] = fillB;
                } else {
                    int ox2 = (ox1 == xmax) ? ox1 : ox1 + 1;
                    int oy2 = (oy1 == ymax) ? oy1 : oy1 + 1;

                    float dx1 = 0;
                    if ((dx1 = ox - (float) ox1) < 0)
                        dx1 = 0;
                    float dx2 = 1.0f - dx1;
                    float dy1 = 0;
                    if ((dy1 = oy - (float) oy1) < 0)
                        dy1 = 0;
                    float dy2 = 1.0f - dy1;

                    unsigned char *p1 = src + oy1 * srcStride;
                    unsigned char *p2 = p1;
                    p1 += ox1 * Channels;
                    p2 += ox2 * Channels;

                    unsigned char *p3 = src + oy2 * srcStride;
                    unsigned char *p4 = p3;
                    p3 += ox1 * Channels;
                    p4 += ox2 * Channels;

                    dst[0] = (unsigned char) (
                            dy2 * (dx2 * p1[0] + dx1 * p2[0]) +
                            dy1 * (dx2 * p3[0] + dx1 * p4[0]));

                    dst[1] = (unsigned char) (
                            dy2 * (dx2 * p1[1] + dx1 * p2[1]) +
                            dy1 * (dx2 * p3[1] + dx1 * p4[1]));

                    dst[2] = (unsigned char) (
                            dy2 * (dx2 * p1[2] + dx1 * p2[2]) +
                            dy1 * (dx2 * p3[2] + dx1 * p4[2]));
                }
                cx++;
            }
            cy++;
            dst += dstOffset;
        }
    } else if (Channels == 4) {
        float cy = -newYradius;
        for (int y = 0; y < newHeight; y++) {
            float tx = angleSin * cy + oldXradius;
            float ty = angleCos * cy + oldYradius;

            float cx = -newXradius;
            for (int x = 0; x < newWidth; x++, dst += Channels) {
                float ox = tx + angleCos * cx;
                float oy = ty - angleSin * cx;

                int ox1 = (int) ox;
                int oy1 = (int) oy;

                if ((ox1 < 0) || (oy1 < 0) || (ox1 >= width) || (oy1 >= height)) {
                    dst[0] = fillR;
                    dst[1] = fillG;
                    dst[2] = fillB;
                    dst[3] = 255;
                } else {
                    int ox2 = (ox1 == xmax) ? ox1 : ox1 + 1;
                    int oy2 = (oy1 == ymax) ? oy1 : oy1 + 1;

                    float dx1 = 0;
                    if ((dx1 = ox - (float) ox1) < 0)
                        dx1 = 0;
                    float dx2 = 1.0f - dx1;
                    float dy1 = 0;
                    if ((dy1 = oy - (float) oy1) < 0)
                        dy1 = 0;
                    float dy2 = 1.0f - dy1;

                    unsigned char *p1 = src + oy1 * srcStride;
                    unsigned char *p2 = p1;
                    p1 += ox1 * Channels;
                    p2 += ox2 * Channels;

                    unsigned char *p3 = src + oy2 * srcStride;
                    unsigned char *p4 = p3;
                    p3 += ox1 * Channels;
                    p4 += ox2 * Channels;

                    dst[0] = (unsigned char) (
                            dy2 * (dx2 * p1[0] + dx1 * p2[0]) +
                            dy1 * (dx2 * p3[0] + dx1 * p4[0]));

                    dst[1] = (unsigned char) (
                            dy2 * (dx2 * p1[1] + dx1 * p2[1]) +
                            dy1 * (dx2 * p3[1] + dx1 * p4[1]));

                    dst[2] = (unsigned char) (
                            dy2 * (dx2 * p1[2] + dx1 * p2[2]) +
                            dy1 * (dx2 * p3[2] + dx1 * p4[2]));
                    dst[3] = 255;
                }
                cx++;
            }
            cy++;
            dst += dstOffset;
        }
    }
}

void facialPoseCorrection(unsigned char *inputImage, int Width, int Height, int Channels, int left_eye_x, int left_eye_y,
                    int right_eye_x, int right_eye_y) {
    float diffEyeX = right_eye_x - left_eye_x;
    float diffEyeY = right_eye_y - left_eye_y;

    float fAngle;
    float M_PI = 3.1415926535897932384626433832795f;
    if (fabs(diffEyeX) < 0.0000001f)
        fAngle = 0.f;
    else
        fAngle = atanf(diffEyeY / diffEyeX) * 180.0f / M_PI;
    size_t numberOfPixels = Width * Height * Channels * sizeof(unsigned char);
    unsigned char *outputImage = (unsigned char *) malloc(numberOfPixels);
    if (outputImage != nullptr) {
        RotateBilinear(inputImage, Width, Height, Channels, Width * Channels, outputImage, Width, Height, fAngle);
        memcpy(inputImage, outputImage, numberOfPixels);
        free(outputImage);
    }
}

上效果圖片。

原圖：

紅眼修復+傾斜矯正:

項目地址:

https://github.com/cpuimage/MTCNN

命令行參數:

mtcnn 模型文件路徑 圖片路徑

例如: mtcnn ../models ../sample.jpg

 

用cmake即可進行編譯示例代碼，詳情見CMakeLists.txt。

 

若有其他相關問題或者需求也可以郵件聯系俺探討。

郵箱地址是: 
gaozhihan@vip.qq.com


免責聲明！

本站轉載的文章為個人學習借鑒使用，本站對版權不負任何法律責任。如果侵犯了您的隱私權益，請聯系本站郵箱yoyou2525@163.com刪除。



猜您在找 聲音變調算法PitchShift(模擬湯姆貓) 附完整C++算法實現代碼 音頻增益響度分析 ReplayGain 附完整C代碼示例 基於RNN的音頻降噪算法 (附完整C代碼) 磨皮美顏算法 附完整C代碼 音頻增益響度分析 ReplayGain 附完整C代碼示例【轉】 3D Lut 電影級調色算法 附完整C代碼 C# 人臉姿態估計(HeadPoseEstimation) 一次雪花算法使用總結，附C++實現代碼 C/C++ 開源庫及示例代碼 【算法】禁忌搜索算法(Tabu Search，TS)超詳細通俗解析附C++代碼實例
 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM