Abstract: There are provided a liveness detection method and device. The liveness detection method comprises: generating a random action instruction sequence including at least one random action instruction; sequentially sending a random action instruction in the random action instruction sequence; and determining whether the sequentially sent random action instruction in the random action instruction sequence is sequentially executed by a living body based on detection information of at least two sensors, wherein the at least two sensors comprise an image sensor and at least one non-image sensor; and determining that the liveness detection is succeeded if the sequentially sent random action instruction in the random action instruction sequence is sequentially executed by the living body. Accuracy of liveness detection can be improved by adopting the random action sequence and by combining images captured by the image sensor and information detected by the non-image sensor.

Abstract: Provided are an image processing method and a client device, an image authentication method and a server device. The image processing method comprises: photographing an object to obtain a first image; sending a key acquiring request to a server and receiving a key from the server; generating a second image based on the key and the first image; and sending the second image to the server. The image authentication method comprises: receiving a key acquiring request from a client; generating a key and sending the key to the sever in response to the key acquiring request; receiving an image for authentication from the client; and authenticating the image for authentication by using the key.

Abstract: A method for obtaining images for three dimension (3D) reconstruction comprises: controlling brightness of each of at least two light sources which are spatially separated from each other to be changed periodically, wherein, among the at least two light sources, there is at least one light source having a period of brightness change different from those of the other light source(s), or the periods of the brightness change of the at least two light sources are the same, but among the at least two light sources, there is at least one light source having a phase of the brightness change different from those of the other light source(s); and using at least three cameras having different spatial positions to capture the images for the 3D reconstruction, respectively, wherein, among the at least three cameras, there is at least one camera starting exposure at a different time from the other cameras.

Abstract: An object detection method and an object detection apparatus are provided. The object detection method comprises: mapping at least one image frame in an image sequence into a three dimensional physical space to obtain three dimensional coordinates of each pixel in the at least one image frame; extracting a foreground region in the at least one image frame; segmenting the foreground region into a set of blobs; and detecting, for each blob in the set of blobs, an object in the blob through a neural network based on the three dimensional coordinates of at least one predetermined reference point in the blob, to obtain an object detection result.

Abstract: The application provides a liveness detection method capable of implementing liveness detection on a human body, and a liveness detection system that employs the liveness detection method. The liveness detection method comprises: obtaining video data acquired via a video acquisition module; determining, based on the video data, a feature signal of an object to be detected; judging whether the feature signal meets a first predetermined condition, and if the feature signal meets the first predetermined condition, identifying that the object to be detected is a living body, wherein the feature signal is indicative of eye movement of the object to be detected.

Abstract: An information processing method comprises: acquiring an original webpage; parsing the original webpage to determine a set of candidate images; detecting whether at least one candidate image in the set of candidate images contains a face; determining a target face from at least one detected face, and determining a candidate image corresponding to the target face as a target image; analyzing the target face to obtain at least one content feature of the original webpage, wherein the at least one content feature includes at least one of a face attribute feature and a personal identity feature; determining display contents matching the at least one content feature based on the at least one content feature; inserting the display contents into a target area corresponding to the target image in the original webpage in a form of a dialog box to acquire a target webpage; and outputting the target webpage.

Abstract: The instant invention describes macrocyclic compounds having therapeutic activity, and the mechanism and methods of treating disorders such as autoimmune diseases, inflammation, and cancer, tumors and cell proliferation related disorders.

Abstract: An information processing method and an information processing apparatus are provided, the method comprising: acquiring an original web page; resolving the original web page to determine a target image; analyzing at least one of the target image and context associated with the target image, to obtain a content feature of the original web page; determining display content matched with the content feature based on the content feature; inserting the display content into a target region corresponding to the target image, of the original web page, to obtain a target web page; and outputting the target web page.

Abstract: A liveness detection apparatus and a liveness detection method are provided. The liveness detection apparatus may comprise: a specific exhibiting device, for exhibiting a specific identification content; an image acquiring device, for acquiring image data of a target object to be recognized during the exhibition of the identification content; a processor, for determining whether there is a reflective region corresponding to the identification content in the acquired image data, determining a regional feature of the reflective region when there is the reflective region, to obtain a determination result, and recognizing whether the target object is a living body based on the determination result.

Abstract: The present disclosure relates to a video monitoring method and a video monitoring system based on a depth video. The video monitoring method comprises: obtaining video data collected by a video collecting module; determining an object as a monitored target based on pre-set scene information and the video data; extracting characteristic information of the object; and determining predictive information of the object based on the characteristic information, wherein the video data comprises video data including the depth information.

Abstract: An access control system and a data processing method for the access control system are provided. The access control system includes: a collection device set corresponding to the access passage, for collecting a real-time information data of a target object; an identification device for identifying the target object based on the collected real-time information data and an user registration information of the access control system, and obtaining an identification result; a system control device for carrying out decision logic based on the identification result to generate a control instruction; an access operation device for controlling an operation of the access passage based on the control instruction generated by the system control device.

Abstract: A disclosed facial recognition system (and method) includes face parsing. In one approach, the face parsing is based on hierarchical interlinked multiscale convolutional neural network (HIM) to identify locations and/or footprints of components of a face image. The HIM generates multiple levels of image patches from different resolution images of the face image, where image patches for different levels have different resolutions. Moreover, the HIM integrates the image patches for different levels to generate interlinked image patches for different levels, where interlinked image patches for different levels have different resolutions. Furthermore, the HIM combines the interlinked image patches to identify refined locations and/or footprints of components.

Abstract: Face hallucination using a bi-channel deep convolutional neural network (BCNN), which can adaptively fuse two channels of information. In one example, the BCNN is implemented to extract high level features from an input image. The extracted high level features are combined with low level details in the input image to produce the higher resolution image. Preferably, a proper coefficient is obtained to adaptively combine the high level features and the low level details.

Abstract: The present invention overcomes the limitations of the prior art by performing facial landmark localization in a coarse-to-fine manner with a cascade of neural network levels, and enforcing geometric constraints for each of the neural network levels. In one approach, the neural network levels may be implemented with deep convolutional neural network. One aspect concerns a system for localizing landmarks on face images. The system includes an input for receiving a face image, and an output for presenting landmarks identified by the system. Neural network levels are coupled in a cascade from the input to the output for the system. Each neural network level produces an estimate of landmarks. The estimate of landmarks is more refined than an estimate of landmark of a previous neural network level.

Abstract: A deep learning framework jointly optimizes the compactness and discriminative ability of face representations. The compact representation can be as compact as 32 bits and still produce highly discriminative performance. In another aspect, based on the extreme compactness, traditional face analysis tasks (e.g. gender analysis) can be effectively solved by a Look-Up-Table approach given a large-scale face data set.

Abstract: Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy to implement. While numerous hand-crafted and learning-based representations have been proposed, considerable room for improvement is still present. A very easy-to-implement deep learning framework for face representation is presented. The framework bases on pyramid convolutional neural network (CNN). The pyramid CNN adopts a greedy-filter-and-down-sample operation, which enables the training procedure to be very fast and computation efficient. In addition, the structure of Pyramid CNN can naturally incorporate feature sharing across multi-scale face representations, increasing the discriminative ability of resulting representation.

Abstract: A disclosed face detection system (and method) is based on a structure of a convolutional neural network (CNN). One aspect concerns a method for automatically training a CNN for face detection. The training is performed such that balanced number of face images and non-face images are used for training by deriving additional face images from the face images. The training is also performed by adaptively changing a number of trainings of a stage according to automatic stopping criteria. Another aspect concerns a system for performing image detection by integrating data at different scales (i.e., different image extents) for better use of data in each scale. The system may include CNNs automatically trained using the method disclosed herein.

Abstract: Some implementations provide techniques and arrangements to address intrapersonal variations encountered during facial recognition. For example, some implementations transform at least a portion of an image from a first intrapersonal condition to a second intrapersonal condition to enable more accurate comparison with another image. Some implementations may determine a pose category of an input image and may modify at least a portion of the input image to a different pose category of another image for comparing the input image with the other image. Further, some implementations provide for compression of data representing at least a portion of the input image to decrease the dimensionality of the data.

Abstract: A disclosed facial recognition system (and method) includes face parsing. In one approach, the face parsing is based on hierarchical interlinked multiscale convolutional neural network (HIM) to identify locations and/or footprints of components of a face image, The HIM generates multiple levels of image patches from different resolution images of the face image, where image patches for different levels have different resolutions. Moreover, the HIM integrates the image patches for different levels to generate interlinked image patches for different levels, where interlinked image patches for different levels have different resolutions. Furthermore, the HIM combines the interlinked image patches to identify refined locations and/or footprints of components.

Abstract: Systems and methods for generating structured light are provided. In some embodiments, systems for generating structured light are provided, the systems comprising: a light source that produces light; a scanner that reflects the light onto a scene; and a hardware processor that controls a scanning speed of the scanner, wherein the scanning speed of the scanner is controlled to provide variable light distributions. In some embodiments, methods for generating structured light are provided, the methods comprising: producing light using a light source; reflecting the light onto a scene using a scanner; and controlling a scanning speed of the scanner using a hardware processor, wherein the scanning speed of the scanner is controlled to provide variable light distributions.