Abstract: A device of contactless physiological measurement with error compensation function is disclosed, and comprises a camera and a modular electronic device that is embedded with a face detection unit, a physiological parameter estimating unit, a feature extraction unit, an error compensation unit, and a physiological parameter generating unit therein. The face detection unit detects a face region from a user image, such that the physiological parameter estimating unit extracts an rPPG signal from the face region, so as to calculate a preliminary physiological parameter based on the rPPG signal. Simultaneously, the feature extraction unit extracts an error feature from the face region, such that the error compensation unit generates an error compensation parameter based on the error feature and the preliminary physiological parameter.

Abstract: A system of image processing based emotion recognition is disclosed. The system principally comprises a camera and a main processor. Particularly, there a plurality of function units provided in the main processor, including: face detection unit, feature processing module, feature combination unit, conversion module, facial action judging unit, and emotion recognition unit. According to the present invention, the emotion recognition unit is configured to utilize a facial emotion recognition (FER) model to evaluate or distinguish an emotion state of a user based on at least one facial action, at least one emotional dimension, and a plurality of emotional scores. As a result, the accuracy of the emotion recognition conducted by the emotion recognition unit is significantly enhanced because basis of the emotion recognition comprises basic emotions, emotional dimension(s) and the user's facial action.

Abstract: A contactless physiological measurement device is disclosed. The contactless physiological measurement device is an electronic device comprising a processor and a memory storing an application program. When the application program is executed, the processor controls a front camera and a rear camera of the electronic device to photograph a user, so as to obtain a face image and a hand image. Subsequently, after extracting a first rPPG signal and a second rPPG signal from the face image and the hand image respectively, physiological parameters are calculated by apply a signal process to the first/second rPPG signal. Moreover, a signal parameter difference is also acquired after applying a signal difference calculation to the two rPPG signals. Consequently, an estimation value of blood pressure is outputted by inputting user anthropometric parameter, said signal parameter difference and at least one physiological parameter into a pre-trained blood pressure estimating model.

Abstract: A system of image processing based emotion recognition is disclosed. The system principally comprises a camera and a main processor. Particularly, there a plurality of function units provided in the main processor, including: face detection unit, feature processing module, feature combination unit, conversion module, facial action judging unit, and emotion recognition unit. According to the present invention, the emotion recognition unit is configured to utilize a facial emotion recognition (FER) model to evaluate or distinguish an emotion state of a user based on at least one facial action, at least one emotional dimension, and a plurality of emotional scores. As a result, the accuracy of the emotion recognition conducted by the emotion recognition unit is significantly enhanced because basis of the emotion recognition comprises basic emotions, emotional dimension(s) and the user's facial action.

Abstract: A health management system using contactless physiological measurement technology is disclosed. The health management system principally comprises a camera and a first processor, of which the camera is faced to a user for capturing a user image. The first processor is particularly configured to have a face detection unit and an activity index calculating unit therein. By such arrangement, after receiving the user image from the camera, the first processor detects a face portion from the user image, thereby subsequently extracting a PPG signal from the face portion. Consequently, after completing at least one process of the PPG signal, multiple indexes for describing a user's health activity are generated. The health activity indexes include health index, activity index, stability index, relaxation index, metabolism index, and balance index. Therefore, the first processor achieves an evaluation of the user's health activity state according to the forgoing health activity indexes.

Abstract: A recycling system and a method based on deep-learning and computer vision technology are disclosed. The system includes a trash sorting device and a trash sorting algorithm. The trash sorting device includes a trash arraying mechanism, trash sensors, a trash transfer mechanism and a controller. The trash arraying mechanism is configured to process trash in a batch manner. The controller drives the trash arraying mechanism according to the signals of trash sensors and controls the sorting gates of the trash sorting mechanism to rotate. The trash sorting algorithm makes use of the images of trash, wherein the images are taken by cameras in different directions. The trash sorting algorithm includes a dynamic object detection algorithm, an image pre-processing algorithm, an identification module and a voting and selecting algorithm. The identification module is based on the convolutional neural networks (CNNs) and may at least identify four kinds of trash.

Abstract: An image processing method for image-based physiological measurement, includes converting at least one user's image signal into image data; determining at least one region of interest within the image data; analyzing image information inside the region of interest to generate physiological information of the user; determining a feedback control signal or a control signal to optimize the physiological information of the user; and adjusting an image sensing unit or an image signal processing unit according to the feedback control signal or the control signal.

Abstract: The invention is related to a method of three-dimensional face reconstruction by inputting a single face image to reconstruct a three-dimensional face model, therefore, the human face image is seen at various angles of three-dimensional face through rotating the model images.

Abstract: The invention is related to a method of three-dimensional face reconstruction by inputting a single face image to reconstruct a three-dimensional face model, therefore, the human face image is seen at various angles of three-dimensional face through rotating the model images.

Abstract: A recycling system and a method based on deep-learning and computer vision technology are disclosed. The system includes a trash sorting device and a trash sorting algorithm. The trash sorting device includes a trash arraying mechanism, trash sensors, a trash transfer mechanism and a controller. The trash arraying mechanism is configured to process trash in a batch manner. The controller drives the trash arraying mechanism according to the signals of trash sensors and controls the sorting gates of the trash sorting mechanism to rotate. The trash sorting algorithm makes use of the images of trash, wherein the images are taken by cameras in different directions. The trash sorting algorithm includes a dynamic object detection algorithm, an image pre-processing algorithm, an identification module and a voting and selecting algorithm. The identification module is based on the convolutional neural networks (CNNs) and may at least identify four kinds of trash.

Abstract: The present invention discloses a human identification system by fusion of face recognition and speaker recognition, a method and a service robot thereof. The system fuses results of the face recognition and the speaker recognition, and further uses confidence index to estimate the confidence level of the two recognition results. If only one of the confidence indices of the two recognition results reaches the threshold, then only this result is used as the output. If both confidence indices of the two recognition results reach the threshold, then the two recognition results are fused to output as a final result.

Abstract: The present invention discloses a human identification system by fusion of face recognition and speaker recognition, a method and a service robot thereof. The system fuses results of the face recognition and the speaker recognition, and further uses confidence index to estimate the confidence level of the two recognition results. If only one of the confidence indices of the two recognition results reaches the threshold, then only this result is used as the output. If both confidence indices of the two recognition results reach the threshold, then the two recognition results are fused to output as a final result.