In mobile, many applications provide services to the users based on the photos provided by the user.Certain applications, client users take a photo of a certain spot and send it to a server, the server identifies the spot with an image recognizer and returns its related information to the users.It can cause a privacy issue because image recognition results are sometimes privacy sensitive.To overcome the problems of existing approaches, proposed an Encryption-Free framework for Privacy preserving Image Recognition, called Enfpire.InEnfPire, the server cannot identify the client users current location, its candidates can only be presented. In proposed thefeature extraction with CNN algorithm help to collect the unique and accurate features from input image and also used Duplicate Detection process to detect images with same features present within same index.In proposed approach user transform the extracted image feature x into y on the user server and sends it to the public server.With the transformation , the effectiveness of the original feature x is degraded so that the public server cannot uniquely recognize the spot-ID of user from y.It only retrives the relevant spot ID’s.The unique spot ID will identify and information regarding the spot and relevant images will be given to the user.