454 results about "Multi feature fusion" patented technology

Uterine cervical cancer Computer-Aided-Diagnosis (CAD) according to this invention consists of a core processing system that automatically analyses data acquired from the uterine cervix and provides tissue and patient diagnosis, as well as adequacy of the examination. The data can include, but is not limited to, color still images or video, reflectance and fluorescence multi-spectral or hyper-spectral imagery, coherent optical tomography imagery, and impedance measurements, taken with and without the use of contrast agents like 3-5% acetic acid, Lugol's iodine, or 5-aminolevulinic acid. The core processing system is based on an open, modular, and feature-based architecture, designed for multi-data, multi-sensor, and multi-feature fusion. The core processing system can be embedded in different CAD system realizations. For example: A CAD system for cervical cancer screening could in a very simple version consist of a hand-held device that only acquires one digital RGB image of the uterine cervix after application of 3-5% acetic acid and provides automatically a patient diagnosis. A CAD system used as a colposcopy adjunct could provide all functions that are related to colposcopy and that can be provided by a computer, from automation of the clinical workflow to automated patient diagnosis and treatment recommendation.

The invention discloses a multi-feature fusion vehicle re-identification method based on deep learning. The method comprises five parts of model training, license plate identification, vehicle identification, similarity measurement and visualization. The method comprises the steps that a large-scale vehicle data set is used for model training, and a multi-loss function-phased joint training policyis used for training; license plate identification is carried out on each vehicle image, and a license plate identification feature vector is generated according to the license plate recognition condition; a trained model is used to extract the vehicle descriptive features and vehicle attribute features of an image to be analyzed and an image in a query library, and the vehicle descriptive features and the license plate identification vector are combined with the unique re-identification feature vector of each vehicle image; in the stage of similarity measurement, similarity measurement is carried out on the image to be analyzed and the re-identification feature vector of the image in the query library; and a search result which meets requirements is locked and visualized.

The invention discloses an Android malicious application detection method and system based on multi-feature fusion. The method comprises the following steps that: carrying out decompilation on an Android application sample to obtain a decompilation file; extracting static features from the decompilation file; operating the Android application sample in an Android simulator to extract dynamic features; carrying out feature mapping on the static features and the dynamic features by the text Hash mapping part of a locality sensitive Hash algorithm, mapping to a low-dimensional feature space to obtain a fused feature vector; and on the basis of the fused feature vector, utilizing a machine learning classification algorithm to train to obtain a classifier, and utilizing the classifier to carry out classification detection. By use of the method, the high-dimensional feature analysis problem of a malicious code rare sample family can be solved, and detection accuracy is improved.

The invention provides a text similarity measuring system based on multi-feature fusion and relates to the field of intelligent information processing. According to the system, the text similarity is measured by fusing multiple features based on word frequencies, word vectors and Wikipedia labels. The invention aims to solve the problem of semantic loss caused by non-considering of contexts in a conventional text similarity measuring system and the problem of low similarity result accuracy caused by larger text length difference. The text similarity measuring system is implemented by the following steps: carrying out preprocessing such as word segmentation and stop word removal on a training text; training corpora of the processed training text as a word vector model; measuring the similarity based on the word frequencies, the similarity based on the word vectors and the similarity based on the Wikipedia labels between input text pairs to be computed, and carrying out weighted summation to obtain a final text semantic similarity measuring result. According to the system, the measurement accuracy of the text similarities can be improved, so that the requirement on intelligent information processing is met.

A method for identity recognition based on multiple feature fusion for an eye image, which comprises steps of registering and recognizing, wherein the step of registering comprises: obtaining a normalized eye image and a normalized iris image, for a given registered eye image, and extracting a multimode feature of an eye image of a user to be registered, and storing the obtained multimode feature of the eye image as registration information in a registration database; and the step of recognizing comprises:obtaining a normalized eye image and a normalized iris image, for a given recognized eye image,extracting a multimode feature of an eye image of a user to be recognized,comparing the extracted multimode feature with the multimode feature stored in the database to obtain a matching score, and obtaining a fusion score by fusing matching scores at score level, and performing the multiple feature fusion identity recognition on the eye image by a classifier. The present invention recognizes identity by fusing multiple features of eye regions on a human face, and thus achieves high recognition accuracy and is suitable for applications of high security level.

A cityscape image semantic segmentation method based on multi-feature fusion and Boosting decision forest includes the following steps of carrying out super-pixel segmentation on images, carrying out multi-feature extraction, carrying out feature fusion and carrying out training learning and classification recognition. The method effectively integrates 2D features and 3D features and remarkably improves recognition rates of targets. Compared with the prior art, segmentation results are consistent, connectivity is good, edge positioning is accurate, a Boosting decision forest classification mechanism is introduced, and stability of target classification is guaranteed.

The invention discloses a face-shielding detecting method based on multi-feature fusion, which is realized with the support of a digital camera and a digital signal processing chip. The method is characterized by comprising the following steps of: using the digital camera to acquire a digital video and converting the digital video into a digital image; obtaining a face image from the digital image by using a face detecting algorithm; aligning and zooming the face image and specifying the face image to a fixed resolution; then dividing the face image into a plurality of cells; and computing feature vectors of all cells; and circularly judging whether the face is shielded, wherein a shielding judgment rule is that the total number of the shielding cells is over a set threshold, or the number of the adjacent shielding cells is over a set threshold. A classifier is obtained by using a method of fusing a plurality of textural features and using an SVM method to train. The face-shielding detecting method based on multi-feature fusion has good classification performance and robustness, which can be widely applied to various monitoring occasions to judge whether a deliberate shielding behavior exists so as to screen out the suspicious personnel.

The invention relates to a moving object tracking method based on multi-feature fusion, belonging to the field of computer vision. At first, in that first frame image, the target area is initialized,and two position filters are respectively train by using the direction histogram and the color features; secondly, the detection samples of two features are extracted around the target in the subsequent frame, and the correlation scores between the two detection samples and the position filters trained in the previous step are calculated respectively, that is to say, the response diagrams of different features are obtained. Thirdly, according to the peak sidelobe ratios of different characteristic response diagrams, the two characteristic response values are weighted and fused, and the point with the largest response value is selected as the current center position of the target. Then the scale pyramid training scale filter is constructed by using the directional gradient histogram feature, and the maximum response point is obtained as the current scale of the target. Finally, according to the peak-to-side ratio of the final response graph of each frame, whether occlusion occurs or notis judged. In the case of occlusion, the position filter is not updated.

The invention discloses a pedestrian object detection method based on object posture projection and multi-features fusion. The method comprises the following steps: firstly, a moving object is preliminarily extracted based on RGB (Red Green Blue) color space, the lighting mutation influence is suppressed and the shadow in the detection result is removed; secondly, the rectangular frames belonging to the same object are judged from the detection result and combined; and finally, as for the object areas in the rectangular frames, the defect caused by the similarity of the object and the background is repaired through combining a gait detection template based on posture estimation. The method provided by the invention has the benefits that an object template is built through the posture projection, and the original background feature matching in the template range is converted into the object feature matching, so the problem that the background and the object can not be distinguished when the object and the background are similar in visual features is solved, thereby improving both the accuracy and the integrity in object detection.

The invention provides a fire identification method based on multiple-feature fusion for flames, and develops a fire identification system with multiple-feature fusion for flames according to the algorithm of the method. The operation principle is to call the camera video monitoring images through the system, and use the background detection algorithm of the system to process the images. The method comprises the following steps of: combining screening of motion fire pixels through motion detection and screening of flame color pixels through RGB color model as an image preprocessing module, wherein the detection calculation based on the inter-frame difference method is fast and does not contain complex calculations, and it is not necessary to consider factor changes such as darkness since the requirements for environment are not high, and the adopted RGB / HIS color model is reasonably stable; characterizing the flames by the number of flame pixels, the convex hulls and the cusps according to the smoke of the flame, the area change, and the features of shape change; combining mature support vector machines for verification; and issuing an alarm when all the above conditions are met. The fire identification method based on multiple-feature fusion for flames can be applied to a real-time camera monitoring system for public security and so on.

The invention discloses a hand gesture recognition method based on multi-feature fusion and fingertip detecting. The method comprises a training process and a recognition process. In the training process, for a complex hand gesture, reasonable hand gesture features are selected, a multi-feature fusion feature extracting algorithm is used, the hand gesture is subjected to support vector machine training, and a training model is formed. In the recognition process, for an input video image sequence, hand gesture detecting is carried out first, then multi-feature extracting and fusion are carried out, and multiple features are input into the support vector machine to obtain a recognition results. Meanwhile, the hand gesture is subjected to fingertip detecting based on defects, through a defect screener, the positions of fingertips of fingers are located, then two-time recognition and detecting results are subjected to synthesized, and the final hand gesture recognition results are obtained. The problem that in a complex scene, the hand gesture recognition rate is not high can be effectively solved, the requirement of real-time performance is met, and the method can be well used in human-machine interaction.

The present invention provides a wireless capsule endoscopy redundant image screening method based on multi-feature fusion. The method comprises the steps of extracting the color feature vector and the texture feature vector of an image through an HSV color feature histogram and a gray level co-occurrence matrix, a step of calculating the color feature normalized mutual information amount of an adjacent image and a texture feature mean square error value as similarity measurement, a step of considering the robustness of the method, a step of proposing the mean value method setting adaptive similarity determination threshold based on a W parameter, a step of dividing an WCE image with certain time correlation and color-texture similarity into a same sub image segment through comparing the similarity measurement value of the adjacent WCE image and a judgment threshold value orderly, and a step of using an adaptive K-means clustering algorithm to carry out key frame extraction on each sub image clip to achieve the purpose of filtering a redundant image. According to the method, the redundant image can be effectively filtered, and thus the efficiency of doctors is improved.

An intelligent house purchasing assistant based on a dialogue robot is provided. The invention discloses a multi-feature fusion unsupervised semantic matching algorithm model and an intelligent housepurchase dialogue robot system based on the model. The multi-feature fusion unsupervised semantic matching algorithm model considers the relevance and semantic relevance of statistical information, and the similarity calculation is carried out from both the statistical and semantic perspective. Finally, the similarity calculation results are more accurate and reliable, and the recall and matchingprocess of user problems and knowledge base problems can be quickly realized by using the fusion method to further improve the effect. The intelligent house purchasing dialogue robot system can realize the question-answer interaction, discard the existing house purchasing information acquisition mode of searching, save time, improve the user experience, and actively display the supporting facilities around the house property and the future trend of the house price for the user according to the user question-answer semantics, so that the user can further understand the house property information.

The invention discloses a slow denial of service (LDoS) attack detection method based on multi-feature fusion and a convolutional neural network (CNN) algorithm, and belongs to the field of network security. The method comprises the following steps: obtaining related data messages in a network key routing node in unit time to form a training sample and a test sample; Performing feature calculationon the training sample and the test sample, and generating a corresponding feature map; Using the feature map of the training sample to train a CNN model, enabling the CNN model to learn and memorizethe features of the slow denial of service attack, and finally obtaining a model which can be used for detecting the slow denial of service attack; And detecting the feature map of the test sample byusing the trained CNN model, and judging whether a slow denial of service attack occurs in a unit time corresponding to the feature map according to a judgment criterion. The detection method based on multi-feature fusion and the CNN algorithm provided by the invention can detect the slow denial of service attack in the network in a high-precision and self-adaptive manner.

The invention discloses an infrared human body target recognition method based on multi-feature fusion and multi-core transfer learning. Firstly, based on the special imaging mechanism of infrared image, an improved CLBP feature is extracted from the target in the infrared scene, MSF-CLBP is used to express the texture information, and an improved local HOG feature-HOG-FV is used to express the shape information. In order to explore the effective features in the target; secondly, for the two heterogeneous features extracted above, the method of tandem fusion is used for feature fusion, so thatthe description of the target feature information is more objective and comprehensive. Finally, a classifier combining multi-core classification and TrAdaBoost migration learning framework is designed, which effectively solves the problem of insufficient image of labeled infrared samples, and enhances the distinguishability of the data to be classified to obtain better recognition results. The method starts from the improvement of feature extraction and the design of classifier, improves the expression of feature information, and improves the performance of infrared target recognition in complex background.

The invention provides a fault feature screening method based on weighted multi-feature fusion and SVM classification. The method comprises the following steps of 1, obtaining the time series data; 2,extracting a time domain (T), a frequency domain (P), the energy (E) and an entropy feature (S), and forming a high-dimensional feature set (Q); 3, screening out the features (Q1) with the diagnosisrate greater than 50%, carrying out the correlation analysis, and removing the features (Q2) with the similarity greater than 85%; 4, selecting a feature with the highest score through PCA and a loadscoring method to form a new sub-feature set (T3, P3, E3, S3); 5, carrying out SVM diagnosis on the T3, the P3, the E3 and the S3, and obtaining a weight Wi according to the diagnosis rate Ri; 6, performing the weighted fusion of the features; and 7, inputting the fused features into a classifier for diagnosis. Through the above steps, a group of optimal features capable of maintaining the fault intrinsic information is obtained, the original failure information represented by the features is ensured, the fault diagnosis accuracy is improved, and the method is of great significance to the efficient mechanical fault diagnosis.

The invention discloses a random ferns multi-feature fusion-based safety helmet detection method. The method comprises the steps of extracting an HSI color histogram feature, an HOG feature and an HOFfeature of a sample; then performing training for a random ferns classifier of each type and each histogram feature; according to YOLOv2 of deep learning, obtaining a human body target to serve as the to-be-detected sample; and based on fusion of random ferns classifiers of multiple features, establishing a safety helmet detection framework. According to the method, a human body target region isquickly and accurately detected based on deep learning, so that the accuracy and speed of safety helmet position locating are improved; and according to a random ferns classifier algorithm, multiple feature training classifiers are fused, so that the classification accuracy is improved. The method is simple and effective, is good in timeliness, and has very good application prospects.

The invention relates to a video analysis technology, in particular to a pedestrian retrieval method for carrying out multi-feature fusion on the basis of a neural network. Pedestrian calculation features detected in a video are stored into a feature database of a set of pedestrians to be detected, and then, features are calculated for a pedestrian to be detected and are compared with a feature database to obtain a retrieval result which ranks top and is high in similarity. Through the calculation of various retrieval features and feature distances, an optimal distance weight W is used for carrying out integration, so that the retrieval result is similar to the upper part of the body and the lower part of the body of the pedestrian to be inquired, and one feature distance is used for carrying out sorting to improve retrieval convenience. The method has the characteristics of wide applicable range, high accuracy and convenience in application. By use of the method, the problems of low accuracy and retrieval similarity in pedestrian detection based on a surveillance video are solved, and the problems that various detection methods and feature distances can not be favorably combined, the applicable range is narrow and application is complex can be overcome.

The invention provides an automatic oral English marking method based on feature fusion. A multi-feature fusion method is used for marking intonation tests in a test of oral English in large scale. A continuous speech signal and a speech recognition text are used as research objects, and the intonation tests in the test of oral English are analyzed from two different angles consisting of speech and text. On the one hand, input speech is analyzed, and a speech feature is extracted and matched and compared with a reference standard; on the other hand, the speech recognition text is compared with the reading text via a text alignment method, and a marking mechanism gives assessment and a mark according to a similarity level. Experimental results show that the method is relatively low in algorithm complexity, and a marking result accords with subjective sensation of people.

The invention discloses a false comment identification method based on rolling type cooperative training, and relates to the technical field of false comment identification. The method comprises the steps: obtaining a comment text, and determining the content features of the comment text according to the comment text; obtaining reviewer information corresponding to the comment text, and determining reviewer behavior characteristics according to the reviewer information; performing false comment identification according to the comment text content characteristics and the reviewer behavior characteristics; outputting false comment recognition results. According to the false comment recognition method, unlabeled samples are effectively utilized to assist model learning, multiple features suchas emotion and text representation are fused at the same time, the recognition performance of the model is improved through multi-feature fusion collaborative training, and the accuracy is improved by 3.5% compared with a traditional false comment recognition method.

The invention relates to the field of intelligent video image processing, and discloses a face tracking method and system based on multi-feature fusion, and the method comprises the steps of obtaininga current frame target image; predicting face trajectory frame position coordinates of all stored face trajectories in the current frame of target image by using a Kalman filtering method; judging whether the frame number of the current frame of target image is a multiple of the detection interval; judging whether a human face is detected or not; performing feature extraction on the face rectangular frame by using a feature extraction algorithm to obtain face features of all faces; carrying out face feature matching; carrying out secondary matching on the face which fails to be matched and the face track which fails to be matched; updating a Kalman filter and track information; determining whether to end face tracking. By setting the face detection interval, the processing speed of the system is high; the matching accuracy is high by fusing the depth features and the HOG features; and feature matching and IOU matching are used cooperatively, so that face ID switching is reduced, the continuity of tracking is ensured, and the accuracy of tracking is improved.

The invention provides an image retrieval method based on multi-feature fusion. The image retrieval method is used for solving the problem that an image retrieval method based on a single feature cannot meet the query requirement of a user. The method comprises the steps of performing noise reduction processing on a to-be-retrieved image by utilizing a filtering method; performing feature quantification by utilizing the improved HSV color space to extract global features of the to-be-retrieved image; performing multi-scale morphological gradient extraction on the denoised image to extract local features of the to-be-retrieved image; performing adaptive fusion on the global features and the local features to obtain an adaptive fusion image; carrying out hash coding on the self-adaptive fusion image, calculating the similarity between the to-be-retrieved image and all the images in the database through Hash codes, and selecting the first several images with the highest similarity with the to-be-retrieved image as retrieval results of the to-be-retrieved image. According to the method, the feature points of the image are fully extracted, and the edge information of the image is protected more comprehensively in the local feature extraction process, so that the retrieval accuracy is improved, and the retrieval time is shortened.

The invention provides a multi-scale and multi-feature fusion feature pyramid network blind restoration method, which is used for solving the technical problems of poor restoration performance and poor robustness of an existing restoration method. The method comprises the following steps: firstly, acquiring N groups of clear images and blurred images from a data set; secondly, constructing a generative adversarial network model of a feature pyramid network and a dual-scale discriminator network; alternately training the feature pyramid network and the discriminator network by using N groups ofclear images and blurred images, and obtaining a final generative adversarial network model after a balance point is reached; and finally, inputting the blurred image to be processed into the final generative adversarial network model, and outputting a clear image. According to the method, the feature pyramid network is combined with the dual-scale discriminator, detail information loss is greatly avoided while the training speed is increased, finally, a multi-scale structure similarity loss function is introduced to further restrain image generation, and stable and high-quality restoration of the complex blurred image is achieved.

The invention discloses a mechanical rotating part performance degradation tracking method based on multi-feature fusion, and relates to a mechanical rotating part performance degradation tracking method. The objective of the invention is to solve the problems that an existing performance degradation tracking method cannot comprehensively and accurately describe all state information of a mechanical rotating part and cannot provide effective reference data for performance degradation of the mechanical rotating part. The method comprises the following steps: 1, acquiring degradation data of a mechanical rotating part; 2, extracting a plurality of features from the original vibration signal of the mechanical rotating part; 3, calculating the correlation, monotonicity, robustness and comprehensive indexes of the extracted features, and screening eight features with the highest comprehensive index value to form a sensitive feature data set; and step 4, constructing an LSTM network, inputting the sensitive feature data set screened in the step 4 into the LSTM network, and performing multi-feature fusion to obtain a fusion feature LSTM-HI which is the health factor. The method is used for mechanical rotating part performance degradation tracking.

The invention relates to a pedestrian clothing attribute recognition method based on depth attitude estimation and multi-feature fusion. The method comprises the following steps: firstly, selecting apart of retrieval results for subsequent attribute recognition through appearance feature matching; then, through an SSD-based depth human body posture estimation method, a foreground region belongingto a pedestrian in the image can be effectively positioned, and background factor interference can be well eliminated; and finally, fusing analysis results of multiple modes, and combining an iterative smoothing process to enhance the correlation between an attribute tag and a pixel by adopting a maximum posterior probability distribution mode to obtain a final attribute analysis recognition result. According to the method, the problems of inaccurate label recognition, pixel analysis area deviation and the like under a single analysis mode are solved. The method is simple and flexible, and has high practical applicability.

The invention provides an image segmentation method for enhancing edge and detail information by utilizing feature fusion, and relates to the technical field of computer vision. The method comprises the steps of extracting features of an input image by using a convolutional neural network; inputting the extracted features into a decoding structure added with more feature fusion, and enriching theedge and detail information while recovering the image resolution to obtain a dense feature map; outputting maximum values of different classifications through a normalization method; and calculatinga cross entropy loss function, and updating the weight in the network by using a random gradient descent method. According to the method, the position and boundary detail information lost in the encoding stage can be recovered while the resolution of the feature map is recovered, the information of the picture is enriched, the dense feature map is obtained, the sparse feature map brought by directup-sampling is compensated, the segmented boundary and details are clearer, and the segmentation effect on detail small objects is improved.

The invention relates to an audio and video speech recognition technology, and provides a cross-modal multi-feature fusion audio and video speech recognition method and system in consideration of thesituation that speech interaction is easily affected by complex environmental noise, and facial motion information is acquired through a video and is relatively stable in an actual robot application environment. According to the method, speech information, visual information and visual motion information are fused through an attention mechanism, and the speech content expressed by a user is acquired more accurately by using the relevance among different modes, so that the speech recognition precision under the condition of complex background noise is improved, the speech recognition performance in human-computer interaction is improved, and the problem of low pure-speech recognition accuracy in a noise environment is effectively solved.

The invention discloses an encrypted malicious traffic detection method. According to the method, a Wreshark tool is utilized to process a traffic packet; filtering out invalid IP checksums, preprocessing the sample set and marking malicious / benign tags; performing preliminary feature extraction on the preprocessed traffic packet; constructing three feature subsets for the preliminarily extracted features, and standardizing and encoding the three feature subsets; carrying out feature dimension reduction on each type of feature subsets by adopting a machine learning or principal component analysis method; respectively establishing a random forest, an XGBoost classifier model and a Gaussian naive Bayes classifier model for the three feature subsets; the three classifier models are combined according to a Stacking strategy to form a DMMFC detection model; performing stream fingerprint fusion on the three feature subsets to form a sample set, dividing the sample set into a training set and a test set, and training a model; testing the model, and evaluating the test effect of the DMMFC model by using the evaluation indexes of the accuracy rate, the F1 score and the false alarm rate; encrypted malicious traffic detection is performed by adopting a method of combining multi-feature fusion and a Stacking strategy, and the method has relatively high detection capability.

The invention relates to a shaking detection algorithm based on multi-feature fusion. The algorithm comprises the following steps of: initializing an undistorted video frame and a video frame to be detected; then, sequentially extracting a brightness similarity factor, a contrast similarity factor and a structure similarity factor to obtain a similarity metric function, wherein the contrast similarity factor is obtained after the average brightness is removed; and meanwhile, judging that the video frame of a signal to be detected does not shake, or judging that the video frame of the signal to be detected shakes. According to the shaking detection algorithm, the brightness similarity factor, the contrast similarity factor and the structure similarity factor of the video frame of a reference signal and the video frame of the signal to be detected are sequentially extracted, the similarities of the three kinds of extracted variable information are compared, and finally, the three comparison results are combined, so that a similarity index is obtained and used as an evaluation criterion for image quality, i.e., indicating whether shaking happens or not.

The invention discloses a method and a device for detecting a human-object interaction relationship in a video, and the method comprises the steps: extracting a space-time track of a subject and an object in the video through target track detection, recognizing a human-object interaction relationship HOI through interaction joint reasoning based on a result of target track detection, and extracting multimode features from a target space-time track through interaction joint reasoning, performing joint reasoning by using a multi-feature fusion mode according to human and object fusion semantic features, human body behavior visual description features and human and object space-time relative motion features, and predicting human and object interaction actions on a video segment to obtain a predicted interaction category label, namely a human and object interaction relationship. The invention provides a time-space domain-based human-object interaction detection method, which successfully discovers, locates and classifies human-object pairs and interaction relationships between the human-object pairs in a video by capturing advanced semantic information of a scene from a complex video vision scene.