關於代價函數

代價函數(常用的有SSD、SAD和SATD):

SAD (Sum of Absolute Difference) = SAE (Sum of Absolute Error),即絕對誤差和

SATD (Sum of Absolute Transformed Difference),即經hadamard變換後再絕對值求和

SSD (Sum of Squared Difference) = SSE (Sum of Squared Error),即差值的平方和

MAD (Mean Absolute Difference) = MAE (Mean Absolute Error),即平均絕對差值

MSD (Mean Squared Difference) = MSE (Mean Squared Error),即平均平方誤差

代價函數總結:
https://blog.csdn.net/juanjuan1314/article/details/78063984

匹配代價函數之SAD:
https://blog.csdn.net/u014493244/article/details/72765748

匹配代價函數之ZNCC:
https://blog.csdn.net/u014493244/article/details/72773645

圖像質量評估算法-SAD SSD MAD MSD SSIM MS-SSIM:
https://blog.csdn.net/u011875342/article/details/78036380

未完待續……

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章