Disclosed is a wavelength conversion film including at least two or more dyes and absorbing irradiation light to emit light at a longer wavelength than that of the irradiation light. The wavelength conversion film includes a first dye having a maximum absorption wavelength in a red light region, and a second dye absorbing excitation energy of the first dye to emit light in a near infrared region.

A neural network in multi-task deep learning paradigm for machine vision includes an encoder that further includes a first, a second, and a third tier. The first tier comprises a first-tier unit having one or more first-unit blocks. The second tier receives a first-tier output from the first tier at one or more second-tier units in the second tier, a second-tier unit comprises one or more second-tier blocks, the third tier receives a second-tier output from the second tier at one or more third-tier units in the third tier, and a third-tier block comprises one or more third-tier blocks. The neural network further comprises a decoder operatively the encoder to receive an encoder output from the encoder as well as one or more loss function layers that are configured to backpropagate one or more losses for training at least the encoder of the neural network in a deep learning paradigm.

A method, system, apparatus, and/or device for adjusting a task or a task flow in an augmented reality environment. The method, system, apparatus, and/or device may include: identifying a first task in a task flow to collect data associated with a user performing the first task; collecting a first set of data associated with the user performing the first task; comparing an amount of time the user expends to perform the first task to a first threshold amount of time; and in response to the amount of time the user expends to perform the first task exceeding the first threshold amount of time displaying a notification to the user or another device.

A photographing apparatus includes an irradiation unit configured to irradiate a living body with beams of light having a plurality of wavelengths different from one another, a photographing unit configured to photograph the living body irradiated by the irradiation unit to generate image data of the living body, an image processing module configured to generate, based on the image data generated by the photographing unit, a plurality of pieces of wavelength separation image data, by separation into the plurality of wavelengths, and a control module configured to control, based on the image data and on the plurality of pieces of wavelength separation image data generated by the image processing module, irradiation light amounts of the beams of light having the plurality of wavelengths.

There is provided an electronic device capable of improving the difficulty of breaking a digital electronic lock and the accuracy of gesture control. The electronic device is unlocked according to gestures of a single hand or two hands, an operation hand, a gesture position, a staying time of gesture and a gesture variation of a user. The electronic device further improves the accuracy of gesture control in conjunction with an accessory pattern, temperature sensing and space information of a wearable device. The present disclosure further provides an electronic device that identifies legitimacy of moving the electronic device according to a variation sequence of 3-axis accelerations of an accelerometer.

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.

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.

The present teaching relates to detecting palm liveness. When an image is received with visual information claimed to represent a palm of a person, an initial region of interests (ROI) is identified from the image that corresponds to the palm and an initial dimension thereof is determined. When the initial dimension is smaller than a specified dimension, the initial ROI is extended in some respective directions to some expansion region with certain expansion dimension to generate an ROI using the visual information in the ROI from the image. A plurality of decisions are obtained with respect to the ROI, each of which is made individually on whether the ROI represents a specific type of fake palm. The decisions are then combined to derive a liveness detection decision on whether the palm captured in the image is live.

The present application discloses a person re-identification method and apparatus based on a deep learning network, a device, and a medium. The method includes: obtaining an initial person re-identification network; creating a homogeneous training network corresponding to the initial person re-identification network, where the homogeneous training network comprises a plurality of homogeneous branches with a same network structure; training the homogeneous training network by using a target loss function, and determining a final weight parameter of each network layer in the homogeneous training network; and loading the final weight parameter by using the initial person re-identification network to obtain a final person re-identification network, to perform a person re-identification task by using the final person re-identification network.

A pair of input images acquired using a first modality and a second modality is processed using a multi-classifier trained to determine classification data indicative of whether the pair is normal or abnormal. A pair may be deemed abnormal if one or both input images are obscured or inconsistent with one another. Training data comprising normal and abnormal images are used to train the multi-classifier. During training, the multi-classifier uses an objective function that includes cross entropy loss, distance loss, and discrepancy loss to process the training data. During use, the trained multi-classifier processes a pair of input images. If the resulting classification data indicates the pair of input images are normal, the pair of input images may be processed to assert an identity.