Abstract: There is provided a recognition system adaptable to a portable device or a wearable device. The recognition system senses a body heat using a thermal sensor, and performs functions such as the living body recognition, image denoising and body temperature prompting according to detected results.

Abstract: An image recognition system includes a color conversion module and a target recognition module. The color conversion module is configured to convert a gray-level image into a preset color image according to a conversion function. The target recognition module includes a machine learning algorithm, and the machine learning algorithm includes a plurality of functions and a plurality of parameters. The machine learning algorithm receives the preset color image, and outputs a recognition result according to the functions and the parameters, the recognition result including an existent target or a null target.

Abstract: A portable electronic device to be used as a keyless device of a vehicle includes a controlling circuit which includes a physiological feature detection module and a processing circuit. The physiological feature detection module is used for detecting a physiological feature of a person. The processing circuit is coupled to the physiological feature detection module and used for determining whether the person is an authorized user of the vehicle according to the detected physiological feature of the person, and for opening a car door of the vehicle or starting the vehicle when the person is identified by the processing circuit as the authorized user.

Abstract: A method used for object tracking includes: using a specific object model to generate a first vector of a first ratio object and a second vector of a second ratio object of an image in an object detection bounding box of a specific frame; generating an identity label of an object within the bounding box according to the first vector, the second vector, and M first ratio reference vectors and M second ratio reference vectors stored in an object vector database.

Abstract: An embodiment is method including forming a first die package over a carrier substrate, the first die package comprising a first die, forming a first redistribution layer over and coupled to the first die, the first redistribution layer including one or more metal layers disposed in one or more dielectric layers, adhering a second die over the redistribution layer, laminating a first dielectric material over the second die and the first redistribution layer, forming first vias through the first dielectric material to the second die and forming second vias through the first dielectric material to the first redistribution layer, and forming a second redistribution layer over the first dielectric material and over and coupled to the first vias and the second vias.

Abstract: A method of performing person re-identification includes: obtaining a person feature vector according to an extracted image containing a person; obtaining state information of the person according to a state of the person in the extracted image; comparing the person feature vector with a plurality of registered person feature vectors in a database; when the person feature vector successfully matches a first registered person feature vector of the plurality of registered person feature vectors, identifying the person as a first identity corresponding to the first registered person feature vector; and selectively utilizing the person feature vector to update one of the first registered person feature vector and at least one second registered person feature vector that correspond to the first identity according to the state information.

Abstract: A method and a system for image correction are provided. The system includes an image processor that performs the method for image correction when receiving an input image. In the method, an overexposed area within the image is determined. The channel values of pixels in the overexposed area are applied with corresponding weights. An automatic white balance process is performed on the channel values of pixels in the overexposed area according to an expectation of low saturation in the overexposed area. Besides a first channel value of each of the pixels, a second channel value and a third channel value of the pixel can be estimated according to the channel values of periphery pixels. A correction value overexposed of the first channel value of the current pixel can be calculated according to the corresponding weights of the pixels in the overexposed area.

Abstract: There is provided a recognition system adaptable to a portable device or a wearable device. The recognition system senses a body heat using a thermal sensor, and performs functions such as the living body recognition, image denoising and body temperature prompting according to detected results.

Abstract: A circuitry for image demosaicing and contrast enhancement and an image-processing method thereof are provided. The circuitry includes a storage device that is used to temporarily store an image and is jointly used by circuits that perform color restoration and brightness reconstruction. The circuitry includes a color restoration circuit for performing image interpolation and a global mapping circuit that performs mapping to obtain brightness of an image according to restored red, green and blue information of every pixel. Further, an edge texture feature decision circuit is provided to obtain each pixel's directionality for color restoration. A brightness estimation circuit utilizes green information of the pixels as the brightness for an area. After that, a color image with the color restoration and brightness reconstruction is outputted.

Abstract: The present invention discloses an image data augmentation method that includes the steps outlined below. At least one distortion operation function is retrieved. A plurality of pixels included in the image are twisted according to the distortion operation function to generate at least one augmented image. Object information of each of at least one object included in the image is converted according to the distortion operation function to generate object information conversion result. The augmented image, a class tag of each of the at least one object and the object information conversion result are fed to a machine learning module to generate a machine learning result.

Abstract: An electronic package structure and a chip thereof are provided. The electronic package structure includes a supporting element, a chip, an internal bonding wire, and a plurality of external bonding wires. The supporting element has a chip arrangement portion. The chip has a first surface and a second surface opposite to the first surface. The chip is arranged on the chip arrangement portion with the second surface facing toward the supporting element. The chip includes a first common pad and an individual core pad that are disposed on the first surface. The internal bonding wire is connected between the first common pad and the individual core pad. The external bonding wires are connected between the chip and the supporting element, in which a first external bonding wire of the external bonding wires and the internal bonding wire are jointly connected to the first common pad.

Abstract: A device includes a conductive feature, a first dielectric layer, a via, an etch stop layer, a second dielectric layer, and a conductive line. The first dielectric layer is above the conductive feature. The via is in the first dielectric layer and above the conductive feature. The etch stop layer is above the first dielectric layer. A side surface of the etch stop layer is coterminous with a sidewall of the via. The second dielectric layer is above the etch stop layer. The conductive line is in the second dielectric layer and over the via. The conductive line is in contact with the side surface of the etch stop layer and a top surface of the etch stop layer.

Abstract: A method for determining deblur filter coefficients includes the following steps: generating an edge profile according to the data of a blurred image; estimating a blur kernel according to the edge profile, wherein the blur kernel indicates how an imaging process blurs original image data and thereby generates blurred image data; and determining coefficients of a deblur filter to make a process result of the deblur filter processing the blurred image data approach the original image data.

Abstract: A character recognition method includes the following operations: determining that the image of character to be identified corresponds to a matching character of several registered characters according to several vector distances to be identified between a vector of an image of character to be identified and several vectors of several registered character images of several registered characters, and storing a matching vector distance between the vector of the image of character to be identified and a vector of the matching character by a processor; and storing a data of the matching character according to the image of character to be identified when the matching vector distance is less than a vector distance threshold by the processor.

Abstract: An object detection model training apparatus, method and non-transitory computer readable storage medium thereof are provided. The apparatus performs a first object detection on a plurality of training images to generate a piece of first label information corresponding to each of the training images by a first teacher model. The apparatus trains a student model based on the training images and the first label information. The apparatus performs a second object detection on the training images to generate a piece of second label information corresponding to each of the training images by a second teacher model. The apparatus trains the student model based on the training images and the second label information.

Abstract: An echo cancelling system includes a data transmitter circuit and an echo canceller circuit. The data transmitter circuit is configured to receive a first transmitted signal. The first transmitted signal has a first sampling rate. The echo canceller circuit is configured to generate a second transmitted signal according to the first transmitted signal. The second transmitted signal has a second sampling rate. The second sampling rate is greater than the first sampling rate. The echo canceller circuit is further configured to generate an echo cancelling signal according to the second transmitted signal. The data transmitter circuit is further configured to generate an output signal according to a received signal and the echo cancelling signal.

Abstract: An electronic system including a display device, an image sensor, a face detection engine, an eye detection engine and an eye protection engine is provided. The image sensor captures an image. The face detection engine recognizes a user face in the image. The eye detection engine recognizes user eyes in the image. The eye protection engine turns off the display device when the user eyes are recognized in the image but the user face is not recognized in the image.

Abstract: There is provided a recognition system adaptable to a portable device or a wearable device. The recognition system senses a body heat using a thermal sensor, and performs functions such as the living body recognition, image denoising and body temperature prompting according to detected results.

Abstract: The present invention discloses a signal gain tuning circuit having adaptive mechanism. An amplifier receives an analog signal to generate a tuned analog signal to an ADC circuit to further generate a digital signal. A gain control capacitor array and the amplifier together determine a gain of the tuned analog signal. The control circuit receives an actual level of the digital signal to determine an offset of the digital signal and an estimated level to generate a tuning control signal. Each of coarse-tuning capacitors of a coarse-tuning capacitor array corresponds to a first tuning amount relative to a maximal gain. Each of fine-tuning capacitors of a fine-tuning capacitor array corresponds to a second tuning amount relative to the maximal gain. A tuning capacitor enabling combination of the coarse-tuning and fine-tuning capacitor arrays are determined according to the tuning control signal to tune the gain and decrease the offset.

Abstract: A method for training a deep learning network for face recognition includes: utilizing a face landmark detector to perform face alignment processing on at least one captured image, thereby outputting at least one aligned image; inputting the at least one aligned image to a teacher model to obtain a first output vector; inputting the at least one captured image a student model corresponding to the teacher module to obtain a second output vector; and adjusting parameter settings of the student model according to the first output vector and the second output vector.