Abstract: A method and a system for mental index prediction are provided. The method includes the following steps. A plurality of images of a subject person are obtained. A plurality of emotion tags of the subject person in the images are analyzed. A plurality of integrated emotion tags in a plurality of predetermined time periods are calculated according to the emotion tags respectively corresponding to the images. A plurality of preferred features are determined according to the integrated emotion tags. A mental index prediction model is established according to the preferred features to predict a mental index according to the emotional index prediction model.

Abstract: An intelligent epidemic prevention system includes a calibration device, an access control system, a visible-light camera recording a first calibration device image of the calibration device and a first user image of a user, a thermographic camera recording a second calibration device image of the calibration device and a second user image of the user, and a computing device that calculates a calibration value according to the first and second calibration device images. The computing device determines whether the user wears a mask properly according to the first user image and generates a first result, and determines whether the temperature of the user is greater than or equal to a threshold temperature according to the calibration value and the second user image and generates a second result. The computing device controls the access control system to open or close according to the first and second results.

Abstract: An escalator equipment alert method and an escalator equipment alert system are disclosed. The method includes: activating a camera disposed on an entrance of an escalator equipment; capturing a foot image of a passenger about to board the escalator equipment through the camera; performing an image analyzation on the foot image to detect a danger boarding behavior related to the passenger; and in response to the danger boarding behavior, issuing an alert message matched with the danger boarding behavior through an alert device.

Abstract: A method and a system for mental index prediction are provided. The method includes the following steps. A plurality of images of a subject person are obtained. A plurality of emotion tags of the subject person in the images are analyzed. A plurality of integrated emotion tags in a plurality of predetermined time periods are calculated according to the emotion tags respectively corresponding to the images. A plurality of preferred features are determined according to the integrated emotion tags. A mental index prediction model is established according to the preferred features to predict a mental index according to the emotional index prediction model.

Abstract: A method of forming an electrode array is disclosed, the method comprising: forming an elongate comb structure comprising a plurality of longitudinally-spaced electrode contacts extending from and supported by a spine; electrically connecting each of a plurality of electrically conductive pathways to a respective one of the plurality of electrode contacts; placing the conductive pathways adjacent the contacts; placing silicone over the conductive pathways and contacts; curing the silicone so as to substantially retain the longitudinal spacing between neighboring contacts; and severing the spine from the plurality of electrode contacts.

Abstract: An embodiment of the disclosure provides a customer behavior analyzing method which includes: capturing an image of a target region by at least one camera; analyzing the image by an image recognition module to detect a customer behavior of at least one customer in the target region; and automatically generating customer behavior information according to the customer behavior. The customer behavior information reflects attention of the customer to at least one commodity. Another embodiment of the disclosure provides a customer behavior analyzing system.

Abstract: A method of forming an electrode array is disclosed, the method comprising: forming an elongate comb structure comprising a plurality of longitudinally-spaced electrode contacts extending from and supported by a spine; electrically connecting each of a plurality of electrically conductive pathways to a respective one of the plurality of electrode contacts; placing the conductive pathways adjacent the contacts; placing silicone over the conductive pathways and contacts; curing the silicone so as to substantially retain the longitudinal spacing between neighboring contacts; and severing the spine from the plurality of electrode contacts.

Abstract: A driving notification method and a driving notification system are provided. The driving notification system is disposed on a mobile vehicle, and the driving notification method includes following steps. A surrounding image is captured through an image capturing device. A target object detection is performed to the surrounding image to obtain a target position of an image detection object. A gaze position of a driver is detected through an eye tracking device. Whether the gaze position matches the target position is determined. An alarm device is controlled to activate an alarming operation if the gaze position does not match the target position.

Abstract: A dynamic scale adjustment method for data visualization enhancement comprises calculating statistical data for a data collection section according to data collected in the data collection section, calculating a mean value according to the statistical data corresponding to the data collection section, dividing the statistical data into a plurality of levels, determining an upper threshold and a lower threshold according to the mean value, and assigning a first data of the statistical data to the highest level when the first data exceeds the upper threshold and assigning a second data of the statistical data to the lowest level when the second data is under the lower threshold.

Abstract: A driving notification method and a driving notification system are provided. The driving notification system is disposed on a mobile vehicle, and the driving notification method includes following steps. A surrounding image is captured through an image capturing device. A target object detection is performed to the surrounding image to obtain a target position of an image detection object. A gaze position of a driver is detected through an eye tracking device. Whether the gaze position matches the target position is determined. An alarm device is controlled to activate an alarming operation if the gaze position does not match the target position.

Abstract: An embodiment of the disclosure provides a customer behavior analyzing method which includes: capturing an image of a target region by at least one camera; analyzing the image by an image recognition module to detect a customer behavior of at least one customer in the target region; and automatically generating customer behavior information according to the customer behavior. The customer behavior information reflects attention of the customer to at least one commodity. Another embodiment of the disclosure provides a customer behavior analyzing system.

Abstract: A driving notification method and a driving notification system are provided. The driving notification system is disposed on a mobile vehicle, and the driving notification method includes following steps. A surrounding image is captured through an image capturing device. A target object detection is performed to the surrounding image to obtain a target position of an image detection object. A gaze position of a driver is detected through an eye tracking device. Whether the gaze position matches the target position is determined. An alarm device is controlled to activate an alarming operation if the gaze position does not match the target position.

Abstract: A living body recognition method and an electronic device are provided. The method includes: providing a prompt information, wherein the prompt information is used to instruct a user to make a first action; capturing at least one image corresponding to the user according to the prompt information; determining whether a second action made by the user in the at least one image meets a specific condition according to the prompt information and the image; determining that the user in the at least one image is a living body when the second action made by the user in the at least one image meets the specific condition; and determining that the user in the at least one image is not the living body when the second action made by the user in the at least one image does not meet the specific condition.

Abstract: A method of visual range mapping includes receiving a plurality of eye detection results from at least one eye tracking device and a display range from a display device, generating a visual range according to the plurality of eye detection results; comparing the visual range with the display range to generate a calibration value, and mapping the visual range into the display range according to the calibration value.

Abstract: A visual utility analytic method for an eye tracking system includes dividing each of a plurality of film segments into at least one display area, wherein each of the plurality of film segments corresponds to at least one display target, and the at least one display target respectively corresponds to one of the at least one display area; and comparing the display area corresponding to the at least one display target in the plurality of film segments with a watched area corresponding to each of a plurality of eye tracking detection results to determine a plurality of visual utilities of the at least one display target in the plurality of film segments.

Abstract: A driving notification method and a driving notification system are provided. The driving notification system is disposed on a mobile vehicle, and the driving notification method includes following steps. A surrounding image is captured through an image capturing device. A target object detection is performed to the surrounding image to obtain a target position of an image detection object. A gaze position of a driver is detected through an eye tracking device. Whether the gaze position matches the target position is determined. An alarm device is controlled to activate an alarming operation if the gaze position does not match the target position.

Abstract: A visual utility analytic method for an eye tracking system includes dividing each of a plurality of film segments into at least one display area, wherein each of the plurality of film segments corresponds to at least one display target, and the at least one display target respectively corresponds to one of the at least one display area; and comparing the display area corresponding to the at least one display target in the plurality of film segments with a watched area corresponding to each of a plurality of eye tracking detection results to determine a plurality of visual utilities of the at least one display target in the plurality of film segments.

Abstract: A method of processing image data for a low processing device comprises collecting data, performing a statistical operation on the collected data with the first data collection section as a first processing unit, to obtain a plurality of first statistical data for the first data collection section, and performing the statistical operation on at least two of the plurality of first statistical data with a second data collection section as a second processing unit, to obtain at least a second statistical data for the second data collection section, wherein the second data collection section is the accumulation of at least two first data collection sections.

Abstract: A dynamic scale adjustment method for data visualization enhancement comprises calculating statistical data for a data collection section according to data collected in the data collection section, calculating a mean value according to the statistical data corresponding to the data collection section, dividing the statistical data into a plurality of levels, determining an upper threshold and a lower threshold according to the mean value, and assigning a first data of the statistical data to the highest level when the first data exceeds the upper threshold and assigning a second data of the statistical data to the lowest level when the second data is under the lower threshold.

Abstract: A method of visual range mapping includes receiving a plurality of eye detection results from at least one eye tracking device and a display range from a display device, generating a visual range according to the plurality of eye detection results; comparing the visual range with the display range to generate a calibration value, and mapping the visual range into the display range according to the calibration value.