FACE DETECTION AND RECOGNITION USING GOOGLE-NET ARCHITECTURE

Using face detection to secure places is an important application merging with machine vision. This paper reposed a system do and recognition using existing architecture google-net transfer learning let the network learn images based on pre-trained architecture, The design of leads that maximizing accuracy accurately detecting faces are saved database specifying effect weights used within nodes hidden layer which consider most time-consuming task architecture. main characteristics explained as well data set in detail provides Experimental results show epochs 10 100 samples imply 98.37% training whereas other numbers either provide less or consume more time, number can be modified according requirements. Other factors like illumination, color background, rotation scale were discussed impact factors.