Abstract: An object counting system crops images into multiple split images. When a distance between at least one side of a bounding box being associated with a position of a first object in the first split image and at least one side of a bounding box being associated with a position of a second object in the second split image adjacent to the first split image is less than a tolerance value, the processor combines the adjacent first split image and the second split second split image into a merged image, so that the first object and the second object are merged into a merged object. A processor calculates a prediction number of objects based on the objects contained in these split images and the merged objects in the merged image. The object counting system automatically counts the number of bug eggs, to save manpower and provide an accurate count.

Abstract: An image recognition method includes the following steps. An original image with a first resolution is received, and the first resolution of the original image is reduced to generate a low-resolution image with a second resolution. The first resolution is higher than the second resolution. The position of a target object in the low-resolution image is identified using an object detection model to obtain the target object coordinates in the low-resolution image. A target object image is segmented from the original image according to the target object coordinates in the low-resolution image, and the target object image is input into the image classification model. The target object type that corresponds to the target object image is determined using the image classification model.

Abstract: An image processing apparatus and an image-based test strip identification method are provided. In the method, multiple representative values on a first axis of a test strip image are determined. The test strip image is obtained by capturing a test strip. A second axis parallel to a test line or a control line of the test strip is perpendicular to the first axis. A test result of the test strip is determined according to a difference between a first representative value and a second representative value of the representative values. The test result includes a positive result and a negative result.

Abstract: An object counting system crops images into multiple split images. When a distance between at least one side of a bounding box being associated with a position of a first object in the first split image and at least one side of a bounding box being associated with a position of a second object in the second split image adjacent to the first split image is less than a tolerance value, the processor combines the adjacent first split image and the second split second split image into a merged image, so that the first object and the second object are merged into a merged object. A processor calculates a prediction number of objects based on the objects contained in these split images and the merged objects in the merged image. The object counting system automatically counts the number of bug eggs, to save manpower and provide an accurate count.

Abstract: A living body detection method and a living body detection system are provided. A radio-frequency signal reflected by an experiment living body is received, and raw sampling data of the RF signal are obtained. A feature extraction process is performed to generate initial training features of sampling datasets, wherein the initial training features respectively correspond to feature generation rules. A classification prediction model is established according to a posture of the experiment living body and the initial training features, and correlation feature weightings respectively corresponding to the initial training features are obtained. Preferred features corresponding to at least one of the feature generation rules are selected from the initial training features according to the correlation feature weightings.

Abstract: The disclosure provides an image identifying method and an image identifying device. The method includes: retrieving a first computer tomographic (CT) image including a plurality of first pixels; retrieving a plurality of second pixels from the first pixels, and generating a second CT image based on the second pixels; performing a contrast enhancement algorithm on the second CT image to adjust a contrast of the second CT image; identifying a first image region in the second CT image to generate a third CT image, wherein the first image region includes a first object; dividing the third CT image into a plurality of sub-images, and only reserving a specific image region corresponding to the first object in each sub-image; combining the sub-images into a fourth CT image; and identifying an object type of the first object based on the fourth CT image.

Abstract: A living body detection method and a living body detection system are provided. A radio-frequency signal reflected by an experiment living body is received, and raw sampling data of the RF signal are obtained. A feature extraction process is performed to generate initial training features of sampling datasets, wherein the initial training features respectively correspond to feature generation rules. A classification prediction model is established according to a posture of the experiment living body and the initial training features, and correlation feature weightings respectively corresponding to the initial training features are obtained. Preferred features corresponding to at least one of the feature generation rules are selected from the initial training features according to the correlation feature weightings.

Abstract: The disclosure provides an image identifying method and an image identifying device. The method includes: retrieving a first computer tomographic (CT) image including a plurality of first pixels; retrieving a plurality of second pixels from the first pixels, and generating a second CT image based on the second pixels; performing a contrast enhancement algorithm on the second CT image to adjust a contrast of the second CT image; identifying a first image region in the second CT image to generate a third CT image, wherein the first image region includes a first object; dividing the third CT image into a plurality of sub-images, and only reserving a specific image region corresponding to the first object in each sub-image; combining the sub-images into a fourth CT image; and identifying an object type of the first object based on the fourth CT image.

Abstract: A multi-level state detecting system includes an image capture device for capturing an image of a subject; a site detecting unit for detecting a person in the image; a face recognition unit for detecting a face in the image via a face recognition database; a multi-level state identification unit for determining corresponding state and probability of the subject; a neural network prediction model database storing trained neural network prediction model associated with state classifications, the multi-level state identification unit identifying corresponding state of the subject when the face recognition unit does not detect the face; and a multi-level state updating unit for generating a final state according to a current state and at least one previous state received from the multi-level state identification unit.

Abstract: A multi-level state detecting system includes an image capture device for capturing an image of a subject; a site detecting unit for detecting a person in the image; a face recognition unit for detecting a face in the image via a face recognition database; a multi-level state identification unit for determining corresponding state and probability of the subject; a neural network prediction model database storing trained neural network prediction model associated with state classifications, the multi-level state identification unit identifying corresponding state of the subject when the face recognition unit does not detect the face; and a multi-level state updating unit for generating a final state according to a current state and at least one previous state received from the multi-level state identification unit.

Abstract: A calibration method for a first accelerometer is disclosed. The first accelerometer is installed together with a second accelerometer in a device. The calibration method includes the second accelerometer measuring a first set of X, Y, Z accelerations in a Cartesian coordinate system, the first accelerometer measuring a second set of X, Y, Z accelerations in the Cartesian coordinate system, indicating to rotate the device, the second accelerometer measuring a third set of X, Y, Z accelerations in the Cartesian coordinate system, the first accelerometer measuring a fourth set of X, Y, Z accelerations in the Cartesian coordinate system, and calibrating X, Y, Z acceleration values measured by the first accelerometer based on the first, second, third and fourth sets of X, Y, Z accelerations.

Abstract: A calibration method for calibrating a simulated motion trace is disclosed. The calibration method includes measuring an acceleration, an inclination angle and an azimuth of a terminal of a sports equipment, computing the simulated motion trace of the terminal according to the acceleration, the inclination angle and the azimuth, estimating a trace surface on which the simulated motion trace locates according to the simulated motion trace, computing a rotational angle between the trace surface and a display surface, projecting the simulated motion trace onto the display surface according to the rotational angle to generate a calibrated trace, and displaying the calibrated trace.

Abstract: A calibration method for a first accelerometer is disclosed. The first accelerometer is installed together with a second accelerometer in a device. The calibration method includes the second accelerometer measuring a first set of X, Y, Z accelerations in a Cartesian coordinate system, the first accelerometer measuring a second set of X, Y, Z accelerations in the Cartesian coordinate system, indicating to rotate the device, the second accelerometer measuring a third set of X, Y, Z accelerations in the Cartesian coordinate system, the first accelerometer measuring a fourth set of X, Y, Z accelerations in the Cartesian coordinate system, and calibrating X, Y, Z acceleration values measured by the first accelerometer based on the first, second, third and fourth sets of X, Y, Z accelerations.

Abstract: A calibration method for calibrating a simulated motion trace is disclosed. The calibration method includes measuring an acceleration, an inclination angle and an azimuth of a terminal of a sports equipment, computing the simulated motion trace of the terminal according to the acceleration, the inclination angle and the azimuth, estimating a trace surface on which the simulated motion trace locates according to the simulated motion trace, computing a rotational angle between the trace surface and a display surface, projecting the simulated motion trace onto the display surface according to the rotational angle to generate a calibrated trace, and displaying the calibrated trace.

Abstract: The invention introduces a method for generating and manipulating grouped photos, executed by a processing unit, which contains at least the following steps. Photos shot in a geometric region are selected from a storage unit, and shooting dates thereof are read. Time intervals between every two adjacent shooting dates are calculated, and CDFGs (Continuous Data-time Fragment Groupings) are generated accordingly. For each CDFG comprising two or more shooting dates, a total number of photos associated with each shooting date is obtained, and one or more groups are generated accordingly. Information regarding the groups is displayed in a map to help a user to search and browse photos.

Abstract: An electronic device and a method for displaying a target object thereof are provided. The method includes following steps. Relative position information between the target object and the electronic device is detected. An object display region is calculated according to the relative position information. Whether the object display region overlaps with at least part of a display region on a display unit is determined to obtain a determined result. Tag information of the target object is displayed on a region overlapped by the display region on the display unit and the object display region.

Abstract: Video previewing methods for electronic devices with a touch-sensitive display unit for providing preview of a video to be played are provided. First, a resolution of the touch-sensitive display unit of the electronic device is detected. Thereafter, a preview screen is generated on the touch-sensitive display unit according to the resolution of the touch-sensitive display unit, wherein the preview screen includes M level frame bars and each of the M level frame bars displays N video frames, and N for each of the M level frame bars is determined based on the resolution of the touch-sensitive display unit, where M?1 and N?1.

Abstract: A stereoscopic image system is provided. The stereoscopic image system comprises: a depth detection unit, for receiving a two-dimensional image and a corresponding depth image, and generating a depth level map according to the two-dimensional image and the corresponding depth image; a stereoscopic image generator, for generating a stereoscopic image pair corresponding to the two-dimensional image according to the two-dimensional image and the depth level map; and a stereoscopic image adjusting apparatus, for generating a depth level range map according to the depth level map, and performing a pixel shifting process and an interpolation process to objects within a plurality of depth levels in the stereoscopic image pair to generate an output stereoscopic image pair according to the stereoscopic image pair and the depth level range map.

Abstract: The invention introduces a method for generating and manipulating grouped photos, executed by a processing unit, which contains at least the following steps. Photos shot in a geometric region are selected from a storage unit, and shooting dates thereof are read. Time intervals between every two adjacent shooting dates are calculated, and CDFGs (Continuous Data-time Fragment Groupings) are generated accordingly. For each CDFG comprising two or more shooting dates, a total number of photos associated with each shooting date is obtained, and one or more groups are generated accordingly. Information regarding the groups is displayed in a map to help a user to search and browse photos.

Abstract: Video previewing methods for electronic devices with a touch-sensitive display unit for providing preview of a video to be played are provided. First, a resolution of the touch-sensitive display unit of the electronic device is detected. Thereafter, a preview screen is generated on the touch-sensitive display unit according to the resolution of the touch-sensitive display unit, wherein the preview screen includes M level frame bars and each of the M level frame bars displays N video frames, and N for each of the M level frame bars is determined based on the resolution of the touch-sensitive display unit, where M?1 and N?1.