Abstract: A method and system for processing an image operates by: filtering a first real image to obtain a first feature map therefor with performances of image features improved; upscaling the obtained first feature map to improve a resolution thereof, the feature map with improved resolution forming a second feature map; and constructing, from the second feature map, a second real image having enhanced performances and a higher resolution than that of the first real image.

Abstract: A method for identifying social relation of persons in an image, including: generating face regions for faces of the persons in the image; determining at least one spatial cue for each of the faces; extracting features related to social relation for each face from the face regions; determining a shared facial feature from the extracted features and the determined spatial cue, the determined feature being shared by multiple the social relation inferences; and predicting the social relation of the persons from the shared facial feature.

Abstract: Disclosed is a method for generating a semantic image labeling model, comprising: forming a first CNN and a second CNN, respectively; randomly initializing the first CNN; inputting a raw image and predetermined label ground truth annotations to the first CNN to iteratively update weights thereof so that a category label probability for the image, which is output from the first CNN, approaches the predetermined label ground truth annotations; randomly initializing the second CNN; inputting the category label probability to the second CNN to correct the input category label probability so as to determine classification errors of the category label probabilities; updating the second CNN by back-propagating the classification errors; concatenating the updated first and second CNNs; classifying each pixel in the raw image into one of general object categories; and back-propagating classification errors through the concatenated CNN to update weights thereof until the classification errors less than a predetermined

Abstract: The present invention discloses a system and a method for decoding QR codes in complex scenes, a system and a method for generating multi-layer color QR codes and applications enabled by the systems and methods. The method for decoding a QR code may include detecting rough locations of the QR code by a learning-based QR code detector which is pre-trained off-line; localizing finder patterns and alignment patterns within each detected location; correcting geometric distortion of each QR code, based on the localized finder patterns and alignment patterns; restoring a color of each data module within each corrected QR code by a learning-based classifier; and decoding the QR code from each restored QR code. The application also discloses a system and a method to determine the optimal setting parameters for creating a multi-layer QR code to fulfill the user's requirements. Some applications enabled by these systems and methods are also disclosed.

Abstract: The present invention discloses a system and a method for decoding QR codes in complex scenes, a system and a method for generating multi-layer color QR codes and applications enabled by the systems and methods. The method for decoding a QR code may include detecting rough locations of the QR code by a learning-based QR code detector which is pre-trained off-line; localizing finder patterns and alignment patterns within each detected location; correcting geometric distortion of each QR code, based on the localized finder patterns and alignment patterns; restoring a color of each data module within each corrected QR code by a learning-based classifier; and decoding the QR code from each restored QR code. The application also discloses a system and a method to determine the optimal setting parameters for creating a multi-layer QR code to fulfill the user's requirements. Some applications enabled by these systems and methods are also disclosed.