US Patent Application 18313152. LOW-RESOLUTION FACE RECOGNITION DEVICE AND LOW-RESOLUTION FACE RECOGNIZER LEARNING DEVICE AND METHOD simplified abstract
LOW-RESOLUTION FACE RECOGNITION DEVICE AND LOW-RESOLUTION FACE RECOGNIZER LEARNING DEVICE AND METHOD
Organization Name
ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
Inventor(s)
LOW-RESOLUTION FACE RECOGNITION DEVICE AND LOW-RESOLUTION FACE RECOGNIZER LEARNING DEVICE AND METHOD - A simplified explanation of the abstract
This abstract first appeared for US patent application 18313152 titled 'LOW-RESOLUTION FACE RECOGNITION DEVICE AND LOW-RESOLUTION FACE RECOGNIZER LEARNING DEVICE AND METHOD
Simplified Explanation
The present disclosure describes a low-resolution face recognition device that can accurately identify faces using both high-resolution and low-resolution images.
- The device includes a high-resolution face image inputter and a low-resolution face image inputter to capture different quality images of faces.
- A high-resolution face feature extractor is used to extract detailed features from the high-resolution and low-resolution face images.
- A face quality feature extractor is used to assess the quality of the face images.
- A feature combiner combines the high-resolution face feature and the face quality feature to detect the high-resolution and low-resolution face features.
- A feature adaptation network extracts high-resolution and low-resolution face feature maps using the detected features.
- A consistency meter measures the consistency of the face feature maps to determine a face ID, ensuring accurate face recognition.
Original Abstract Submitted
The present disclosure relates to a low-resolution face recognition device, which includes a high-resolution face image inputter; a low-resolution face image inputter; a high-resolution face feature extractor configured to extract a high-resolution face feature by using high-resolution and low-resolution face images; a face quality feature extractor configured to extract face quality features by using the high-resolution and low-resolution face images; a feature combiner configured to detect the high-resolution and low-resolution face features by concatenating the high-resolution face feature and the face quality feature; a feature adaptation network configured to extract a high-resolution face feature map and a low-resolution face feature map by using the detected high-resolution and low-resolution face features, respectively; and a consistency meter configured to determine a face ID by measuring consistency of a face feature map by using the extracted high-resolution and low-resolution face feature maps.