摘要 |
A method processes an input image securely. An input image I is acquired in a client. A set of m random images, H<SUB>1</SUB>, . . . , H<SUB>m</SUB>, and a coefficient vector, a=[a<SUP>1</SUP>, . . . , a<SUB>m</SUB>], are generated such that the input image I is I=Sigma<SUB>i=1</SUB><SUP>m</SUP>alpha<SUB>i </SUB>H<SUB>j</SUB>. The set of the random images is transferred to a server including a weak classifier. In the server, a set of m convolved random images H' are determined, such that {H<SUB>I</SUB>'=pi<SUB>1</SUB>(H<SUB>1</SUB>*y}<SUB>i.1</SUB><SUP>m</SUP>, where * is a convolution operator and pi<SUB>1 </SUB>is a first random pixel permutation. The set of convolved images is transferred to the client. In the client, a set of m permuted images I' is determined, such that I'=pi<SUB>2</SUB>(Sigma<SUB>i=1</SUB><SUP>m</SUP>alpha<SUB>i </SUB>H<SUB>1</SUB>'), where pi<SUB>2 </SUB>is a second random pixel permutation. The set of permuted image is transferred to the server. In the server, a test image {overscore (I such that {overscore (I=alpha∫(I') is determined and a true signal is returned to the client if there exists a pixel q in the test image such that {overscore (I(q)>0, otherwise return a false signal is returned to the client to indicate whether or not the input image contains an object.
|