Face Recognition Based On Intensity And Gradient Local Directional Pattern

How to obtain facial feature information effectively has always been the focus of face recognition research.Local Directional Pattern has become one of the most popular face recognition algorithms because of its strong robustness to illumination,occlusion and noise.However,there are still some flaws.Therefore,the LDP algorithm is studied in depth and several corresponding improved algorithms are proposed.The main research contents of the paper are as follows:(1)A method of face recognition based on Double Space Local Directional Pattern is proposed.First,each 3 × 3 neighborhood pixel of the facial image gains eight edge response values by convolving the local neighborhood with eight Kirsch template operators.Eight Kirsch masks represent the eight directions of the eight sides,i.e.,east,west,south,and north corresponding to the linear edge and northeast,northwest,southwest,and southeast corresponding to the line edge.Then,the difference of each pair of neighboring edge response values is calculated to form eight new difference directions.DSLDP utilizes the direction of the largest absolute value edge gradient value of each sub-neighborhood.The two directions are encoded into a double-digit octal number to produce the DSLDP code.Finally,the face descriptor is represented using the global concatenated histogram based on the DSLDP map extracted from the face image,which is divided into several sub-blocks.Sub-blocks are weighted by information entropy.The face dimensions are reduced by principal component analysis.The nearest neighbor classifier is used to classify the faces.Then,the identification results are obtained.(2)A method of face recognition based Double Difference Local Directional Pattern is proposed.Firstly,The radius of 1 and 2 of 3×3 neighborhood pixel of facial image gains the two groups of eight edge response values by convolving the local neighborhood with eight Kirsch template operators.Then,The neighboring difference value is calculated by the counterclockwise direction,which is the edge response values of the radius of 1.Meanwhile,The edge response difference values of different radius is also calculated.Finally,The DDLDP just utilizes take the maximum edge response difference values between the two groups corresponding to the direction of the subscript.These two subscript are encoded into a double-digit octal number to produce the DDLDP code.(3)A method of face recognition based Orthogonal Gradient Difference Local Directional Pattern is proposed,Firstly,The3×3and 5×5 neighborhood pixel of facial image gains the two groups of eight edge response values by convolving the local neighborhood with eight Kirsch template operators.Then,The edge response difference values of the3×3and 5×5 neighborhood pixel is also calculated.Meanwhile,The neighboring difference value is calculated by the counterclockwise direction,which is the edge response values of the 3x3 neighborhood pixel.Finally,The OGDLDP just utilizes take the maximum edge response difference values between the two orthogonal groups corresponding to the direction of the subscript.These two subscript are encoded into a double-digit octal number to produce the OGDLDP code.The experimental results show that the OGDLDP algorithm improves the recognition rate.and has better robustness to the change of illumination,expression and shelter.