Math, asked by bhuvanesh9257, 1 year ago

Improved the minimum squared error algorithm for face recognition by integrating original face imags and the mirror imaages

Answers

Answered by Anonymous
0
In order to improve the accuracy of face recognition and solve the problem of various poses and illuminations, we proposed an improved minimum squared error (IMSE) classification algorithm. Firstly, the mirror faces of the original training faces are generated through row preserved and columns flipped in the left/right direction. Secondly, the minimum squared error (MSE) algorithm is performed on both original faces and the mirror faces. Thirdly, the predicted errors of the test sample and standard class labels are obtained. In addition, the residual between the predicted labels of the test sample and each training sample can also be calculated. At last, the correct class can be determined by fusing the predicted errors and residuals. We also promoted the IMSE algorithm to the kernel MSE algorithm and proposed an improved kernel minimum squared error (IKMSE) algorithm for face recognition. The experimental results show our proposed IMSE and IKMSE algorithm are more robust than the conventional MSE and KMSE algorithm, respectively. In addition, our proposed algorithms improve the accuracy of face recognition effectively.
Answered by Anonymous
0
ANSWER
.......


original faces and the mirror faces.



, the predicted errors of the test sample and standard class labels are obtained. In addition, the residual between the predicted labels of the test sample and each training sample can also be calculated. At



last, the correct class can be determined by fusing the predicted errors and residuals. We also promoted the lMSE



algorithm to the kernel MSE algorithm and proposed an improved kernel minimum squared error (IKMSE) algorithm for face recognition. The experimental results show our proposed



IMSE and lKMSE algorithm are more robust than the conventional MSE and KMSE algorithm, respectively.


In addition, our proposed algorithms improve the accuracy of face


मूल चेहरे और दर्पण चेहरे तीसरा, परीक्षण नमूने और मानक कक्षा लेबल की भविष्यवाणी की गई त्रुटियां प्राप्त की जाती हैं। इसके अलावा, परीक्षण नमूने के पूर्वानुमानित लेबल और प्रत्येक प्रशिक्षण नमूने के बीच अवशिष्ट भी गणना की जा सकती है। आखिरकार, भविष्यवाणी की गई त्रुटियों और अवशिष्टों को फ्यूज़ करके सही वर्ग निर्धारित किया जा सकता है। हमने कर्नेल एमएसई एल्गोरिथम में एलएमएसई एल्गोरिथ्म को भी बढ़ावा दिया और चेहरे की मान्यता के लिए एक बेहतर कर्नेल न्यूनतम स्क्वायर त्रुटि (IKMSE) एल्गोरिदम प्रस्तावित किया। प्रयोगात्मक परिणाम हमारे प्रस्तावित आईएमएसई और एलकेएमएसई एल्गोरिथ्म को क्रमशः पारंपरिक एमएसई और केएमएसई एल्गोरिथ्म से अधिक मजबूत दिखाते हैं। इसके अलावा, हमारे प्रस्तावित अल्गोरिदम चेहरे की सटीकता में सुधार करते हैं
Similar questions