780 results about "Evaluation algorithm" patented technology

A video quality evaluation method based on artificial neural network, which belongs to the field of computer digital video processing. The evaluation algorithm computes damage extent of an image by analyzing spatial characters (blur, entropy, blocking effect, frequency-domain energy analysis, saturation) and time behaviors (frame-to-frame differences). Evaluation effect of the algorithm can be effectively modified by using colour space saturation as one of the parameters for non-reference evaluation algorithm. The system is designed based on artificial neural network, therefore, training process and testing process of the network are included in realization of the algorithm. To the selected training sample (video image sequence), firstly extracts six parameters of the sample, then obtains expected output (subjective evaluation result) in training through subjective evaluation. Characteristic parameters of the training sample and the corresponding subjective evaluation result are inputted to the artificial neural network as training parameters. The experiment shows that evaluation result obtained by the objective evaluation system is highly-consistent with visual sense of human eyes.

The invention discloses a convolutional-neural-network-based reference-free three-dimensional image quality evaluation method. The method comprises the following steps: carrying out pretreatment on a 2D image; to be specific, inputting an image block obtained by pretreatment into a deep convolutional neural network, carrying out convolutional pooling processing to obtain an advanced feature of the image block, and then carrying out BP training by using the neural network based on a mass fraction of an original image so as to obtain a parameter of a base model; obtaining a corresponding basic model according to the parameter of the base model, carrying out centering on a three-dimensional image and carrying out pretreatment identical with that of the 2D image on the left image and the right image, and inputting the image blocks at the same position into the basic module simultaneously to obtain a corresponding advanced feature vector; and carrying out testing under a LIVE 3D database. On the basis of the reference-free evaluation algorithm, a good result better that the existing quality evaluation result can be obtained.

In a method and to an apparatus for evaluating a sequence of medical examination images successively presented at a viewing device using a data processing device operating on software having an evaluation algorithm for determining image regions exhibiting abnormalities, an acoustic signal is emitted by the dependent on the determination result, and/or the presentation time of an image on a monitor is influenced dependent thereon.

The invention discloses a vulnerability scanning system oriented to safety assessment and a processing method thereof. The system provided by the invention comprises a server side and a client side which are of a C/S (client/server) structure; the server side operates on a Unix or Linux platform, and the client side operates on a Windows platform; the server side comprises a client side verification module, a scanning engine service module, a scheduling process module, an invasion detecting module and the like; the client side comprises a server verification module, a scanning configuration module, a pre-warning module, an evaluation algorithm module, a scanning report processing module, a vulnerability expansion and Chinesization module and the like; and according to the invention, the vulnerability scanning system and the invasion detection system are combined, the pre-warning function and scheduling function are introduced, thus the system can carry out vulnerability scanning and safety assessment selectively and purposively according to the requirements of users, and a relatively objective and accurate vulnerability scanning report forms.

The invention discloses a medical clinical quality monitoring and evaluation system based on a single-disease model, and relates to the field of medical quality management. The system comprises a clinical data integration subsystem, a data cleaning and standardization subsystem, a statistic analysis and evaluation algorithm subsystem and a clinical quality management application subsystem. The clinical data integration subsystem is used for sending collected case data in the original diagnosis and treatment process of single diseases into a clinical record database; the data cleaning and standardization subsystem is used for selecting case data from the clinical record database and processing the data to form a single-disease evaluation database; the statistic analysis and evaluation algorithm subsystem is used for performing index calculation and comprehensive evaluation calculation on the received data; the clinical quality management application subsystem is used for displaying a comprehensive evaluation result obtained after the statistic analysis and evaluation algorithm subsystem performs calculation. Through the system, processing and statistic evaluation of the clinical data in clinical quality management are achieved, and a medical quality manager can truly and objectively master the quality of the diagnosis and treatment process of various diseases in various clinical departments in real time in a full-quantized mode.

The invention belongs to the technical field of cross-media information retrieval and particularly relates to face and name aligning method and system based on image characteristics and text content in cross media news retrieval. In the invention, four main algorithms are included, and are name importance assessment algorithm, multimode information discovery algorithm based on web excavation, face set cohesion algorithm and multimode aligning combination optimization algorithm. In the invention, the related image characteristics and text content processing method is used, meanwhile, relative mathematical model is built, optimization to new picture search is performed, and through multi-grade and deep-level text content analyses and effective face-name alignment evaluation mechanism, and combination optimization at the aim of problems can be achieved. According to the invention, a great significance to efficient image retrieval performed under the consideration of high level semantic information of images and on the basis of large-scale and multifarious new image can be played, the retrieval relativity can be enhanced, the user experience is enhanced, and the wide application value is played in the field of medium information retrieval.

A method and a device for detecting, determining and documenting damage to painted surfaces, especially parts of the bodywork of vehicles, utilizes light from at least one heavily focusing light source directed to a test surface in a grid-type or raster-type manner to produce a surface image on a screen with the light reflected on the test surface of the vehicle, the image being detected by a capturing, evaluating and signal processing device. The surface damage therein is then determined according to a specific evaluation algorithm and outputted for objective documentation of the damage. Results are achieved by coordinated, controlled displacement and/or pivoting between the light source and screen and by means of a rotational and/or displacement and or pivoting movement of the vehicle, which is controlled in accordance with the displacement and/or pivoting, around or along the longitudinal and/or vertical axis thereof inside a load-bearing structure, wherein the respective surface area to be sensed is brought towards the light source in the reflection position and the screen and the capturing device are brought towards the reflected light in an imaging position and the movements of the light source, screen, capturing device and vehicle are controlled by a processor unit.

The invention discloses an evaluation method for health degree of multidimensional wireless network, the method comprises the steps as follows: confirming the dimension impacting health degree of the current wireless network in each classified source data through Hadoop, and the index parameter being corresponding to each dimension, combining the dimension and index parameter of the dimension for building the evaluation algorithm model of multidimensional health degree, comparing the obtained synthesis score to obtain the health state of wireless network and storing the health state of wireless network in the result list of the vertica database. The administrator and optimization personnel can conveniently and effectively master the network health state meeting the development trend of the current wireless network.

The invention discloses a full-reference image quality evaluation method based on image distortion types. The distortion types of distorted images are predicted by construction of a convolutional neural network model; the quality of the distorted images to be evaluated is evaluated respectively through the four classical full-reference image quality evaluation methods (the PSNR, the SSIM, the JNDand the VIF); corresponding evaluation reference values in four aspects are obtained from each distorted image; evaluation scores obtained by the four different evaluation algorithms are fitted by a nonlinear fitting function; training is carried out according to different distortion types of the images, so that fitting parameters corresponding to each distortion type are obtained; and, for imagesto be detected, corresponding fitting parameters are selected according to the distortion types of the images, so that the final evaluation results of the distortion images are obtained by the fitting function. Compared with the prior art, different theories of image quality evaluation models of the four classical algorithms (the PSNR, the SSIM, the JND and the VIF) are fused; the advantages of each model are exerted; and thus, the performance of the new method is better.

In a method and magnetic resonance system for generating a homogenous, radio-frequency excitation field in a spatial examination volume of the magnetic resonance system for a subject examination, the magnetic resonance system having a body coil comprised of N resonator segments or groups and a control and evaluation device for the separate activation of the individual resonator segments electromagnetically decoupled from one another, separate excitation of each individual resonator segment using defined excitation parameters ensue with an examination subject located in the magnetic resonance system and the respective segment-specific or group specific magnetic field distributions in the examination volume are determined. The segment-specific or group-specific magnetic field distributions are computationally superimposed to determine a overall field distribution in the examination volume. The homogeneity of the overall field distribution is evaluated using an evaluation algorithm and a change of one or more excitation parameters of one or more resonator segments or segment groups to compensate for a known field inhomogeneity is determined. The resonator segments or segment groups are excited with the determined parameter change to acquire an a diagnostic image of the subject.

Methods of identifying rock properties in real-time during drilling, are provided. An example of such a method includes connecting a downhole sensor subassembly between a drill bit and a drill string, operably coupling acoustic sensors to a downhole data interface, and operably coupling a surface computer to the downhole data interface. The method can also include receiving raw acoustic sensor data generated real-time as a result of rotational contact of the drill bit with rock during drilling, transforming the raw data into the frequency domain, filtering the transformed data, and deriving a plurality of acoustic characteristics from the filtered data. This can be performed by a petrophysical properties analyzing program stored in memory of the computer. The method can also include deriving petrophysical properties from the filtered data utilizing a petrophysical properties evaluation algorithm employable to predict one or more petrophysical properties of rock undergoing drilling.

The invention provides a camera image quality evaluation method and device, and belongs to the technical field of image quality evaluation. According to the method, a natural scene statistical model and local resolution features formed by three sets of features are utilized. As for the first set of features, four features are extracted by utilizing the linear relation between free energy and a structure degradation model. As for the second set of features, the statistical features of natural images are utilized, and generalized Gaussian distribution is utilized to measure deviation of distortion images and the natural scene statistical model so as to extract four features. As for the third set of features, three features are extracted by utilizing discrete wavelet decomposition to measure resolution of the images. The previous two sets of features measure naturalness of the images and are different in focus, wherein the first set of feature consider local autoregression, and the second set of features consider global histogram statistics. Finally, the quality score of the camera images is obtained by the result of the evaluation algorithm through the machine learning tool of a support vector machine, and the quality of the camera images is evaluated according to the quality score.

The invention discloses a variable-weight hydropower unit deterioration evaluation system and an evaluation method. The system comprises an evaluation data layer, an evaluation index layer, an evaluation algorithm layer and a man-machine interaction layer, which are connected in sequence. The method is a variable-weight multi-factor unit deterioration evaluation algorithm and comprises: performing unified processing on various evaluation data by adopting a data integration technology of the evaluation data layer; integrating and inputting evaluation data to the evaluation index layer; calculating deterioration degree of each index; reading a weight parameter of each index at the same time; and finally performing weighted calculation to obtain an overall health state result of a unit and outputting the overall health state result to a man-machine interface. By utilizing the system and the method, the unit can be subjected to deterioration evaluation and online operation monitoring and state repair guidance are provided; and an effective solution can be provided for constructing a state repair and deterioration evaluation system for hydropower units in different hydropower plants, different periods and different states, and efficient and practical decision-making services are provided for device deterioration analysis of the hydropower plants, so that reliable support is provided for implementation of state repair.

The invention discloses a method for evaluating an arterial green wave coordination effect based on a mobile terminal, and the method can output evaluation indexes on line in real time by adopting a green wave coordination effect evaluation algorithm and utilizing the intelligent mobile terminal. The method can obtain single-vehicle traveling data in real time through the intelligent terminal and realize real-time online evaluation of a green wave coordination effect of a single-vehicle test road segment in combination with a data processing algorithm and the green wave coordination control evaluation algorithm, and meanwhile, the evaluation method mainly has two evaluation modes which are drawing of a trajectory space-time diagram and output of the evaluation indexes respectively. Compared with existing common methods such as a manual research method, a single-vehicle test method, a floating vehicle method and the like, the method for evaluating the arterial green wave coordination effect based on the mobile terminal has the advantages of low manpower and material resource consumption, capability of giving out the effect evaluation indexes and optimization suggestions on line in real time, and the like, thereby having very high practicality and a wide application prospect.

Methods of identifying rock properties in real-time during drilling, are provided. An example of method includes connecting a downhole sensor subassembly between a drill bit and a drill string, operably coupling acoustic sensors to a downhole processor, operably coupling a borehole telemetry system, downhole and surface data transmitting interfaces, and a surface computer to the downhole data transmitting interface. The method also includes receiving raw acoustic sensor data resulting from rotational contact of the drill bit with rock by the downhole processor, transforming the raw acoustic sensor data into the frequency domain, filtering the transformed data, and deriving acoustic characteristics from the filtered data. The method also includes the surface computer receiving the acoustic characteristics and deriving petrophysical properties from the acoustic characteristics directly or by utilizing a petrophysical properties evaluation algorithm.

The invention discloses a device for on-line monitoring and evaluating state of an air blower. The device comprises a data collection and operation module, a master controller module and a communication interface module, wherein the data collection and operation module is used for collecting parameter information of vibration of the air blower, temperature, voltage, electrical current, pressure, and the like; vibration signals of the air flow are decomposed by adopting a method of multiwavelet; early failure characteristic signals are extracted; performance evaluation is performed by adopting state performance evaluation algorithm based on a cloud model; the collected signals of the temperature, the pressure, and the like are distinguished and displayed by the master controller; and the device is equipped with a plurality of communication interfaces, so that data exchange between information and factory control net and manufacturing execution system can be realized. Through adoption of the device, performance state of the air flow can be evaluated accurately, so that reasonable maintenance for the air flow is realized.

The present invention discloses a virtual dance teaching method and system. The method comprises the steps of: performing choreographer professional action capture; performing construction of an action library; according to the action library, and driving a coach model to perform dance teaching. The action of a professional choreographer is captured to determine the standard action of the professional dance, the standard action is subjected to skeleton alignment to perform coding of an XML mode, and the coach action library is constructed after the basic action is determined through optimization, a virtual dance role is constructed to perform sampling of the choreographers and students to perform three-dimensional model geometric construction, the action data of the standard action libraryis employed to drive the coach model to drive a student model in real time through Kinect and perform visualization showing of the dance action for the students to study, and finally, the dance action is evaluated through an evaluation algorithm (cosine feature value Euclidean distance) to allow the students to perform introspection. The virtual dance teaching method and system are simple and effective for dance teaching and feedback, and save the cost.

The invention discloses a method for objectively evaluating the image quality based on region weight and visual characteristics of human eyes, which comprises the following steps: (1) acquiring images which are distributed according to the region weight; (2) applying modified human eyes to process images of sensitive functions; and (3) applying gradient information similarity to evaluate the images. The method is combined with the visual characteristics of the human eyes, so that the image processing result of the method is quite close to a human eye visual system, and the quality evaluation value according with the visual characteristics of the human eyes can be obtained as long as a reference image and an evaluation image are inputted. The method can be applied in the aspects of image compression, storage, transmission, reconstruction and the like, and quickly measures the image quality. Moreover, the method can be applied to iteration ending in the image restoration process, and the optimum restoration image obtained by using an evaluation algorithm to end an iteration algorithm is quite close to the optimum restoration image obtained by the evaluation of the human eyes.