Industrial Technology Research Institute

Ulsee Inc.

Cywee Group Limited

Sheng-Wen Jeng

Zhou Ye

Ying-Ko Lu

Shun-Nan Liou

Ming-Jye Tsai

Yi-Chia Hsu

Shih-Ching Huang

Hsin-Wei Hsiao

Po-Lung Chen

Chih-Ming Chang

Duan-Li Liao

Chien-Chun Kuo

Wen-Yang Wang

Shih Wei Liu

Method for automatically measuring pupillary distance includes extracting facial features of face image, a head current center indicator is shown/displayed based on facial feature extraction, elliptical frame and target center indicator are shown, a first distance between head current center indicator and target center indicator is calculated to see if below a threshold range, then allowing head current center indicator, elliptical frame and target center indicator to disappear. Card window based on facial tracking result is shown. Credit card band detection is performed to see if located within card window. Card window then disappear. Elliptical frame of moving head and target elliptical frame are shown. Elliptical frame of the moving head is aligned with the target elliptical frame and maintaining a correct head posture. If elliptical frame of moving head is aligned with target elliptical frame, then allow them to disappear from view, and performing a pupillary distance measurement.

Automatic pupillary distance measurement system and measuring method

A method of 3D morphing driven by facial tracking is provided. First, a 3D model is loaded. After that, facial feature control points and boundary control points are picked up respectively. A configure file 'A.config' including the facial feature control points and boundary control points data that are picked up corresponding to the 3D avatar is saved. Facial tracking algorithm is started, and then 'A.config' is loaded. After that, controlled morphing of a 3D avatar by facial tracking based on &#x201c;A.config&#x201d; is performed in real time by a deformation method having control points. Meanwhile, teeth and tongue tracking of the real-time face image, and scaling, translation and rotation of the real-time 3D avatar image is also provided. In addition, a control point reassignment and reconfiguration method, and a pupil movement detection method is also provided in the method of 3D morphing driven by facial tracking.

Method of 3D model morphing driven by facial tracking and electronic device using the method the same

Method of applying virtual makeup and producing makeover effects to 3D face model driven by facial tracking in real-time includes the steps: capturing static or live facial images of a user; performing facial tracking of facial image, and obtaining tracking points on captured facial image; and producing makeover effects according to tracking points in real time. Virtual makeup can be applied using virtual makeup input tool such as a user's finger sliding over touch panel screen, mouse cursor or an object passing through makeup-allowed area. Makeup-allowed area for producing makeover effects is defined by extracting feature points from facial tracking points and dividing makeup-allowed area into segments and layers; and defining and storing parameters of makeup-allowed area. Virtual visual effects including color series, alpha blending, and/or superposition are capable of being applied. Makeover effect takes into account of lighting condition, facial posture rotation, face size scaling, and face translation, respectively.

Method of virtual makeup achieved by facial tracking

Image-based object tracking system includes at least a controller with two or more color clusters, an input button, a processing unit with a camera, an object tracking algorithm and a display. Camera is configured to capture images of the controller, the processing unit is connected to display to display processed image contents, the controller is directly interacting with displayed processed image content. The controller can have two or three color clusters located on a side surface thereof and two color clusters having concentric circular areas located at a top surface thereof, the color of the first color cluster can be the same as or different from the color of the third color cluster. An object tracking method with or without scale calibration is also provided, which includes color learning and color relearning, image capturing, separating and splitting of the controller and the background, object pairing procedure steps on the controller.

Image-based object tracking system in 3D space using controller having multiple color clusters

A face-tracking method with high accuracy is provided. The face-tracking method includes generating an initial face shape according to the detected face region of an input image and a learned data base, wherein the initial face shape comprises an initial inner shape and an initial outer shape; generating a refined inner shape by refining the initial inner shape according to the input image and the learned data base; and generating a refined outer shape by searching an edge of the refined outer shape from the initial outer shape toward the limit of outer shape.

Face-tracking method with high accuracy

A method of performing facial recognition and tracking of an image captured by an electronic device includes: utilizing a camera of the electronic device to capture an image including at least a face; displaying the image on a display screen of the electronic device; determining a degree of orientation of the electronic device; and adjusting an orientation of scanning lines used to scan the image for performing face detection so that the orientation of the scanning lines corresponds to the orientation of the electronic device.

Orientation correction method for electronic device used to perform facial recognition and electronic device thereof

A computing device in a system for motion detection comprises an image processing device to determine a motion of an object of interest, and a graphical user interface (GUI) module to drive a virtual role based on the motion determined by the image processing device. The image processing device comprises a foreground extracting module to extract a foreground image from each of a first image of the object of interest taken by a first camera and a second image of the object of interest taken by a second camera, a feature point detecting module to detect feature points in the foreground image, a depth calculating module to calculate the depth of each of the feature points based on disparity images associated with the each feature point, the depth calculating module and the feature point detecting module identifying a three-dimensional (3D) position of each of the feature points, and a motion matching module to identify vectors associated with the 3D positions of the feature points and determine a motion of the object of interest based on the vectors.

Method and computing device in a system for motion detection

The present invention discloses a system for human and machine interface. The system includes a 3-dimensional (3D) image capture device, for capturing a gesture of a motion object in a period of time; a hand-held inertial device (HHID), for transmitting a control signal; and a computing device. The computing device includes a system integration and GUI module, for compensating the control signal according to an image signal corresponding to the motion object, to generate a compensated control signal.

System and method utilized for human and machine interface

An inertial input apparatus with six-axial detection ability, structured with a gyroscope and an acceleration module capable of detecting accelerations of X, Y, Z axes defined by a 3-D Cartesian coordinates, which is operable either being held to move on a planar surface or in a free space. When the inertial input apparatus is being held to move and operate on a planar surface by a user, a two-dimensional detection mode is adopted thereby that the gyroscope is used for detection rotations of the inertial input apparatus caused by unconscious rolling motions of the user and thus compensating the erroneous rotations, by which the technical disadvantages of prior-art inertial input apparatuses equipped with only accelerometer can be overcame and thus control smoothness of using the input apparatus is enhanced.

Inertial input apparatus with six-axial detection ability and the operating method thereof

An inertial sensing input apparatus is disclosed, which includes: an accelerometer module, capable of detecting accelerations with respect to a Cartesian coordinate system of X-, Y-, and Z-axes; and a gyroscope, used for detecting a rotation measured with respect to the Z-axis. By the aforesaid input apparatus, an input method can be provided which comprises steps of: (a) defining base signals with respect to each of such sensing elements; (b) detecting and determining whether Z-axis accelerations are varying; (c) enabling the input apparatus to enter a surface (2D) operating mode while no acceleration varying is detected along the Z axis; (d) enabling the input apparatus to enter a space (3D) operating mode while acceleration varying is detected along the Z axis.

Inertial sensing input apparatus and method

A pointing device is disclosed in the present invention, which comprises a planar sensing unit, an inertial sensing unit and a controller unit. The planar sensing unit is capable of detecting a movement of the point device moving on a planar surface and generating a planar sensing signal accordingly. The inertial sensing unit is capable of detecting a movement of the point device while it is moving in a free space and thus generating an inertial sensing signal accordingly. The controller unit is coupled to the planar sensing unit and the inertial sensing unit for enabling the same to receive and process the planar sensing signal and the inertial sensing signal. In a preferred aspect, the planar sensing unit is capable of detecting and determining whether the pointing device is operating on a surface or in a free space for selectively enabling the pointing device to operate in a mode of two-dimensional detection or in a mode of three-dimensional detection such that users can apply the pointing device freely without being restricted by a surface or a space, and thus not only the usage convenience of the pointing device is enhanced, but also the applications thereof are broadened.

Pointing device

A multi-trail spot click-event detection method is disclosed, which uses a camera to capture a plurality of consecutive images from a display screen. The camera is connected to a host and sends the consecutive images to the host for determining if a click-event occurs. Firstly, pixels of each difference image with the brightness difference in a pre-determined range are selected to form blobs. Next, possible spots of the blobs in each difference image are found. Then, the possible spots found are assigned to a specific trail. Finally, when a spot of the specific trail is absent at a next time point immediately after the spot is presented, occurrence of a click-event is detected.

Multi-trail spot click-event detection method

The present invention relates to an iris extraction method. In the method, two searching regions are defined in a face image. A deformable template match algorithm and an energy function are used to measure the energy of each pixel with different hypothetical circular templates within the searching region. Pixels with the same hypothetical radius having energies greater than a predetermined threshold are recorded as iris candidates, wherein the pixel having the maximal energy is recorded as first iris candidate. Further, it detects associated iris pairs from iris candidates in each searching region, records the lower iris candidate having the maximal energy of iris pairs as second iris candidate, and selects the best iris candidate from first iris candidate and second iris candidate. Finally, it designates the best iris candidate having the maximal energy of all best iris candidates with different hypothetical radius as the iris in the face image.

Growing community of inventors

Tainan, Taiwan

Sheng-Wen Jeng