Abstract: The present disclosure relates to an electronic apparatus executing auto-crawling based on artificial intelligence, including: a crawling unit acquiring images including a target using an artificial intelligence model; a target identifying unit identifying a target matching the acquired image; and a processor controlling operations of the crawling unit and the target identifying unit. The processor classifies and searches for images including the target, among images stored in a predetermined area, according to crawling levels, and performs vision processing of the automatically searched images including the target to identify the target, and transmits the target and information on the target to a server or stores the target and information on the target in a memory.

Abstract: Disclosed are a system and a method for providing nutritional information based on image analysis using artificial intelligence. The system includes: at least one imaging device acquiring at least one image including at least one dish or at least one food contained in each dish; a service providing apparatus for detecting at least one food included in the at least one image when the at least one image is received, confirming the name of each detected food on the basis of a learning model, mapping food information included in pre-stored food information on the basis of the confirmed name, and generating nutritional information using the mapped food information; and a user terminal for visualizing and displaying the nutritional information when the nutritional information is received.

Abstract: Disclosed are a system and a method for measuring dish size and providing nutritional information using image recognition and augmented reality based on artificial intelligence. The system includes: at least one imaging device acquiring at least one image including at least one dish or at least one food contained in each dish; a service providing apparatus for detecting the at least one dish and the at least one food from the at least one image when the at least one image is received, confirming the name of each detected food on the basis of a learning model, predicting the size of each detected dish, predicting the volume of each detected food using the predicted size of the dish, and generating nutritional information using the predicted volume of each food and pre-stored food information; and a user terminal for visualizing and displaying the nutritional information when the nutritional information is received.

Abstract: A method in which a server recognizes and determines an object in an image may include calculating a feature map including an object feature point within the image by learning the image based on a first model, calculating compression feature information by compressing the feature map based on a first filter, inputting the compression feature information for each at least one layer and calculating respective prediction information by learning the compression feature information for each layer based on a second model, and calculating prediction result information by determining whether the respective prediction information sequentially exceeds a predetermined threshold value in order from a top layer.