A fingerprint unlocking method may include receiving a first fingerprint image. The number of target feature points of the first fingerprint image is determined. A target adjustment parameter corresponding to the number of target feature points is acquired according to a preset mapping relation between the number of feature points and adjustment parameters. A second fingerprint image is received according to the target adjustment parameter. A terminal is unlocked when the second fingerprint image matches with a preset fingerprint template. A terminal is also provided.

Fingerprint unlocking method and terminal

The invention discloses a real human body three-dimensional modeling method specific to personalized virtual fitting According to the method, a video is used as input data; and several steps of feature matching, key frame selection, three-dimensional point cloud generation, template mapping, and texture mapping and the like are carried out to obtain a human body surface three-dimensional model Because of the motion recovery structure technology, the reconstruction process is substantially simplified, the burdens of the data collection people and the collected people can be reduced, and the requirements on the instrument and equipment are reduced Meanwhile, a precise reconstruction result can be obtained A complete human body surface model is obtained based on template mapping; and thus the method has high robustness on the human body texture information missing and self-shielding Therefore, only a plurality of control points need to be marked manually before template mapping from the data input to model output and other process is completed automatically The model that is obtained based on reconstruction can be applied to the game and animation design, movie and television special efficacy, and personalized virtual fit and the like

Real human body three-dimensional modeling method specific to personalized virtual fitting

The invention discloses an automatic identification method for the welding seam ultrasonic TOFD-D scanning defect type based on deep learning. Firstly the D scanning image data of welding seam typical defects are acquired through the ultrasonic TOFD-D scanning technology; secondly, a FasterR-CNN deep learning network framework formed by a feature graph extraction convolutional neural network VGG16, a regional proposed network RPN and an FRCN network is established in the MATLAB programming environment; and finally phased training of the Faster R-CNN deep learning network is performed. The network test result displays that the Faster R-CNN network has the capability of efficiently identifying the defect type in the welding seam D scanning image. According to the method, the advantages of the FasterR-CNN identification network for image identification can be fully utilized and applied to welding seam ultrasonic TOFD-D scanning image detection so that the influence of the subjective factors of detection personnel can be avoided, the identification capability and efficiency for the defect type in the TOFD-D scanning image can be effectively enhanced, the method has the advantages of high detection accuracy, great robustness and high anti-interference performance and thus the method can be applied to the intelligent nondestructive test technology.

Automatic identification method for welding seam ultrasonic TOFD-D scanning defect type based on deep learning

A method includes determining object class probabilities of pixels in a first input image by examining the first input image in a forward propagation direction through layers of artificial neurons of an artificial neural network. The object class probabilities indicate likelihoods that the pixels represent different types of objects in the first input image. The method also includes selecting, for each of two or more of the pixels, an object class represented by the pixel by comparing the object class probabilities of the pixels with each other, determining an error associated with the object class that is selected for each pixel of the two or more pixels, determining one or more image perturbations by back-propagating the errors associated with the object classes selected for the pixels of the first input image through the layers of the neural network without modifying the neural network, and modifying a second input image by applying the one or more image perturbations to one or more of the first input image or the second input image prior to providing the second input image to the neural network for examination by the neurons in the neural network for automated object recognition in the second input image.

Image analysis neural network systems

A tunnel disease full-section dynamic rapid detection device based on active panoramic vision comprises a tunnel detection vehicle, an active panoramic vision sensor, an RFID (radio frequency identification) reader, a wireless receiving-transmitting unit, a controller, and a station-level communication system or a central monitor center server; the central monitor center server comprises a full-directional vision sensor calibrating module, an active panoramic vision sensor calibrating database, a Zi-th distance tunnel section panoramic image data reading unit, a full tunnel section panoramic image base, a full-directional plane laser information analysis and point cloud data acquisition unit, a tunnel section panoramic image expansion and splitting unit, a tunnel suspected disease image pretreatment unit, a tunnel suspected disease image treatment unit, a tunnel disease image characteristic index extracting unit, and a tunnel safety status estimating unit. The invention provides a novel tunnel full-section high-speed dynamic health examination method, automatically detecting, judging and estimating various defects present in a tunnel to provide effective technical support for tunnel maintenance and completion acceptance inspection.

Tunnel disease full-section dynamic rapid detection device based on active panoramic vision

The invention discloses a tunnel full-section high-speed dynamic health detection device based on an active panoramic vision. Hardware of the device comprises a tunnel detection trolley, an active panoramic vision sensor, an RFID reader and a processor. System software comprises an omnibearing face laser information analysis and point cloud data obtaining unit, a tunnel center axis extracting unit, a noise reducing and adjustment processing unit, a three-dimensional modeling and deformation analyzing unit, a full tunnel all-section cross section benchmark database, a full tunnel longitudinal section splicing unit, a displacement monitoring and sedimentation monitoring unit, a full tunnel health examination result database and a tunnel longitudinal section variable shift amount three-dimensional visualization unit. Transverse and longitudinal deformation of a tunnel are analyzed and recognized by carrying out machine vision processing on laser scanning fracture surface slice images of the inner wall of the tunnel. The invention further provides a tunnel full-section high-speed dynamic health detection method based on the active panoramic vision, and effective technology support is provided for daily maintenance of tunnels of metros and high-speed rails.

Tunnel full-section high-speed dynamic health detection device and method based on active panoramic vision

A welding visual detection method based on a convolutional neural network includes the following steps that firstly, at the training stage, a training sample is input into the convolutional neural network, and the connection weight and offset value of the convolutional neural network are obtained; secondly, at the testing state, a welding picture is read in and preprocessed with the digital picture processing technology, and a region of interest is extracted and then subjected to picture size normalization processing to serve as input of the convolutional neural network. The invention further provides a welding visual detection device based on the convolutional neural network. The welding visual detection device based on the convolutional neural network comprises a crawling mechanism, a power transmission mechanism, visual detection equipment and a weld defect detection and analysis system. By means of the welding visual detection method and device based on the convolutional neural network, the automaton and intelligence level is improved, the detection precision is effectively improved, and the detection speed is effectively increased.

Welding visual detection method and device based on convolutional neural network

The invention discloses an active-omni-directional-vision-based pipeline inside functional defect detection device. The active-omni-directional-vision-based pipeline inside functional defect detection device comprises a camera shooting creeping system, a control cable and a detection analysis core operating system, wherein the detection analysis core operating system comprises a coordinated action control unit, a creeping system control unit, an image receiving unit, a functional defect and structural defect qualitative and quantitative analysis judgment module and a storage unit; and a pipeline inside omni-directional image and a laser scanning cross section slice image are subjected to machine vision processing analysis and the functional defect and the structural defect of the pipeline can be recognized. The invention also discloses an active-omni-directional-vision-based pipeline inside functional defect detection method. A brand new automatic pipeline health checking method is provided and can provide effective technical support for underground pipeline maintenance and completion acceptance.

Active-omni-directional-vision-based pipeline inside functional defect detection device and detection method

The invention discloses a panoramic image CNN based tunnel disease automatic identification device. According to the device, firstly, a panoramic image of a tunnel inner wall is quickly acquired with a panoramic vision sensor; then the panoramic image is processed mainly by panorama unrolling, image preprocessing, binarization processing and the like to extract suspected disease region; and finally, the disease is subjected to automatic detection and classification identification by adopting a convolutional neural network. According to the scheme, the structure of the detection device in extracting a tunnel inner wall panoramic image is greatly simplified, and various tunnel disease characteristics can be automatically extracted, detected and identified by the end-to-end convolutional neural network, and an effective technical support is provided to tunnel maintenance and completion acceptance.

Tang Yiping

Papers

Tunnel full-section high-speed dynamic health detection device and method based on active panoramic vision

Welding visual detection method and device based on convolutional neural network

Active-omni-directional-vision-based pipeline inside functional defect detection device and detection method

Tunnel disease full-section dynamic rapid detection device based on active panoramic vision

Panoramic image CNN based tunnel disease automatic identification device