799 results about "Morphological processing" patented technology

The invention discloses a method for quickly and accurately detecting and tracking a human face based on a video sequence, which relates to the technical field of mode identification. The method comprises the following steps of: 1, extracting a video frame image from a video stream; 2, preprocessing the video frame image, namely compensating light rays, extracting skin color areas, performing morphological processing and combining the areas; 3, detecting the human face, namely representing the human face by using Harr-like characteristics and detecting the human face by using a cascaded Adaboost algorithm with an assistant decision function; 4, establishing the characteristics of the human face, namely detecting the area characteristics of the detected human face and the shape characteristics of the edge profile of the human face; 5, tracking the human face, particularly tracking the human face by using a human face area characteristic model when an intersection does not occur in a human face area, and further matching when the intersection occurs according to the shape characteristics of the edge profile of the human face; and 6, extracting the sequence of a human face image. By the technical method, the human face can be detected and tracked quickly and accurately on the basis of the video sequence.

The invention discloses an interactive type image segmentation and fusion method based on a grabucut algorithm. The interactive type image segmentation and fusion method based on a grabucut algorithmcomprises steps of adopting a pyramid down-sampling to reduce a resolution of an image, using few typical pixel points to estimate a GMM parameter, using an interactive type technology to mark a foreground and a background of the image, performing watershed segmentation, performing modification on a mask image obtained from segmentation and transmitting the modified the mask image to a grabucut for fine segmentation, performing morphological processing on the segmented image, continuously performing pixel transformation and morphological processing on a processed image to obtain a tripartite graph, using the trimap graph and a source graph as inputs, using a shared matting algorithm to obtain an alpha channel image of the foreground image, using the alpha channel image, the source image and a new background image as inputs and using an alpha blending transparent mixed algorithm to obtained a fused image.

An information fusion technology based train wheel set tread damage online detection and recognition method comprises the steps of 1 image acquisition, 2 image pre-processing, 3 preliminary damage detection, 4 accurate damage positioning and 5 damage judgment, wherein the step 4 is that an infrared image processing result and a gray image processing result are subjected to data fusion, a tread image is marked and positioned, damaged texture and area are obtained through morphological processing, morphological processing is conducted on tread cracks to obtain the length of the cracks, and the step 5 is that features of a tread damage region are extracted and selected, a BP neural network is designed and trained, the defects of the BP neural network are classified, and reference is provided for operation situation analysis of wheels, locomotives and lines according to train wheel set tread damage information recorded by a terminal processing unit. The information fusion technology based train wheel set tread damage online detection and recognition method has the advantages of being comprehensive in detection, high in automatic degree, high in detection speed and detection accuracy and the like.

The invention discloses a method for real-time monitoring gas heating furnace flame on the basis of ROI average image analysis which belongs to the field of industrial heating furnace flame video monitoring. The method comprises following steps: 1) setting a flame region of interest(ROI) through a human-computer interaction method; 2) extracting a ROI image from a flame monitoring video flow and calculating an average image; 3) pre-treating the ROI average image, including noise smoothing, threshold segmenting, morphological processing, to determine the most probable flame pixel region; 4) extracting flame features from the pre-treated image, comprising flame region area, average brightness, mass center and flame color principal components; 5) synthetically analyzing flame feature, establishing judgment rules, automatically identifying flame burning status and outputting; 6) establishing off-line self-study model by use of historical data, optimizing system parameters, increasing method robustness. The method can be applied for real-time monitoring combustion conditions of gas heating furnace with single-burner or multi-burner and guarantees safety of industrial production.

The invention relates to a the machine vision detection field, and provides a method and a device for detecting magnetic tile surface defects through machine vision technology. The technical scheme of the method comprises the following steps: (1) placing a magnetic tile to be detected on a conveyer belt; (2) starting a CCD image acquisition device, acquiring a magnetic tile surface image and transmitting the image to an image processing unit; (3) processing the image acquired in (2) through image filtering, image segmentation, post-morphological processing, edge detection and the like by the image processing unit, transmitting the processed results to a defect detection unit; (4) performing feature extraction of the image processing results in (3) so as to transform the results into a one-dimensional data signal; (5) training and testing the results obtained in (4) by a probability mode identification unit, dividing magnetic tile surface quality into two classes: good magnetic tile and defective magnetic tile so as to reach the purpose of defect detection. The method and device have simple structures, are easy to maintain and expand, have high detection efficiency and low equipment investment.

The invention relates to a recognition method of a license plate number of a motor vehicle, and belongs to the technical field of license plate number recognition. The recognition method comprises carrying out median filtering and noise reduction to an input image containing a license plate, locating multiple license plate areas by utilizing a binarization processing method and a morphological processing method, carrying out rotation correction and edge removing processing to the license plate areas one by one, carrying out character cutting by utilizing a vertical projection method, carrying out further edge removing processing to obtained character blocks in a cutting mode, carrying out character recognition by utilizing an enhanced edition template matching method, and therefore achieving fast and accurate license plate recognition. The recognition method improves the precision of license plate location, and fast and precise location of the license plate is achieved. The recognition method can be used in a real-time license place recognition system, and for processing high-speed data flow, meanwhile is high in recognition accuracy, and has certain robustness on illumination variation, influence of rain and mist, indistinct license plates, broken characters and other bad conditions.

The invention discloses a fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering. The fast high-resolution SAR image ship detection method comprises the following steps: on the basis of the back scattering characteristics of each ground object and the prior information of a ship target in an SAR image, positioning a target potential position index map by an Otsu algorithm and range constraint; on the index map, pre-screening to obtain a detection binary segmentation map by a CFAR (constant false alarm rate) algorithm based on a local contrast; carrying out morphological processing to a detection result, and extracting a potential target slice from the SAR image and a detected binary segmentation map according to a processing result; and carrying out K-means clustering to the extracted slice by a designed identification feature to obtain a final identification result. According to the fast high-resolution SAR image ship detection method based on feature fusion and clustering, the data volume of a detection stage is effectively reduced by pre-processing, and point-to-point detection is not needed/the time of point-to-point detection is saved. Meanwhile, a target identification problem under the condition of insufficient training samples at present can be solved by the designed characteristic and a non-supervision clustering method, the target can be effectively positioned, and the size of the target can be estimated.

The invention discloses a vision-based quick LED module brightness uniformity detection method. The method comprises the following steps: S1, a light emitting image of the LED module is acquired, gray processing is carried out on the image, the image is filtered after gray processing, the image after being filtered is subjected to morphological processing, and the image after morphological processing is subjected to histogram equalization processing; S2, each LED lamp point is positioned through block positioning algorithm, the LED lamp point is subjected to gray processing, the LED lamp point after gray processing is subjected to mathematical morphological open operation, and the brightness value of the LED lamp point and an average value are acquired; and S3, after each LED lamp point in the LED module is traversed, the brightness value of each LED lamp point is displayed, and the final processing result is displayed. The method plays an important role in yield detection during the LED lamp production process.

The invention discloses a method for automatically detecting the printing defects of a remote controller panel based on an SURF (Speed-Up Robust Feature) algorithm. The method disclosed by the invention comprises the following steps: carrying out histogram equalization on a to-be-detected sample image by making a remote controller template image, respectively acquiring feature points of the template image and the to-be-detected image through the SURF algorithm, matching the feature points by utilizing a partitioned and accelerated nearest neighbour matching method, acquiring a homography matrix according to a matching result, carrying out affine transformation on the to-be-detected image to obtain a correction image by utilizing the homography matrix, processing difference images of the template image and the correction image superposed with a mask, carrying out binaryzation and morphological processing on a difference image result, judging whether a to-be-detected sample is qualified, if the to-be-detected sample has a defect, locating the position of the defect; if the to-be-detected sample does not have a detect, judging that the to-be-detected sample is qualified, and completing detection. The method disclosed by the invention is capable of effectively detecting defects in the to-be-detected sample and accurately locating the positions of the defects.

The invention discloses a magnetic tile surface defect detection method based on an improved machine vision attention mechanism. The magnetic tile surface defect detection method comprises the following steps: I, inputting a magnetic tile image, and enhancing the overall gray contrast ratio of the image by using a method of combination of morphological top cap and bottom cap conversion; II, uniformly dividing the obtained image into a*b image blocks, and distinguishing defect image blocks and non-defect image blocks according to gray characteristic quantities of the divided image blocks; III, calculating the conspicuousness of an obtained image block by using an improved Itti vision attention mechanism model, and selecting a primary characteristic so as to form a comprehensive saliency map; and IV, thresholding the comprehensive saliency map by using an Ostu threshold method, and extracting a defect area. By virtue of morphological processing, image blocking and vision attention mechanism ideas, problems that the brightness is not uniform, the magnetic tile defect area is relatively small, a magnetic tile has texture interference and the like can be effectively overcome, various magnetic tile defects can be rapidly and effectively extracted, and thus the magnetic tile surface defect detection method is very good in adaptability.

The invention discloses a rapid license-plate positioning method based on definition and luminance evaluation. The rapid license-plate positioning method includes the following steps: 1, carrying out definition evaluation based on noise and sharpness on an input image; 2, carrying out gradient sharpening processing if the definition is insufficient, and carrying out Gaussian fuzzy processing if the definition is excessively high; 3, converting the RGB image into a grey-scale image; 4, carrying out luminance evaluation on the grey-scale image; 5, carrying out illumination unification processing if the luminance is abnormal; 6, extracting the perpendicular edges in the image through a Scharr operator; 7, carrying out local self-adaption threshold processing; 8, filtering the noise through morphological processing, and fusing the perpendicular edges to form a communicated area; 9, carrying out area marking on the communicated area, carrying out screening according to the characteristics of Chinese license plates, and obtaining a license plate area.

The invention discloses a CNN and selective attention mechanism based SAR image target detection method. An SAR image is obtained; a training data set is expanded; a classification model composed of the CNN is constructed; the expanded training data set is used to train the classification model; significance test is carried out on a test image via a simple attention model (a spectral residual error method) of image visual significance to obtain a significant characteristic image; and morphological processing is carried out on the significant characteristic image, the processed characteristic image is marked with connected domains, target candidate areas corresponding to different mass centers are extracted by taking the mass centers of the connected domains as the centers, and the target candidate areas are translated within pixels in the surrounding to generate an target detection result. According to the invention, the CNN and the selective attention mechanism are applied to SAR image target detection in a combined way, the efficiency and accuracy of SAR image target detection are improved, the method can be applied to target classification and identification, and the problem that detection in the prior art is low in detection efficiency and accuracy is solved mainly.

The invention discloses a mobile platform ground movement object detection method including the steps as follows: (1) respectively calculating SWIFT characteristic description of a (n-m)th frame image, an nth frame image and a (n+m)th frame image of an image sequence; (2) by taking the nth frame image as a reference, respectively registering the (n-m)th frame image and the (n+m)th frame image to obtain registration images; (3) respectively conducting space multiscale movement significance tests on the two registration images with the nth frame image; (4) calculating a difference absolute value image of the nth frame image and the (n-m)th frame registration image, and the difference absolute value image of the nth frame image and the (n+m)th frame registration image; (5) respectively calculating a difference image of the (n-m)th frame and the nth frame as well as a difference image of the nth frame and the (n+m)th frame; (6) mixing the two difference images to obtain a three-frame difference image and then conducting binaryzation; and (7) conducting morphological processing on a binary segmented image and then conducting region marking so as to obtain a final detection result image. The mobile platform ground movement object detection method solves the background compensation problem under the condition of a moving platform and has very good robustness on the light change and background interference in a scene as well as image deformation caused by platform movement.

The invention provides a table recognition method and system, belonging to the technical field of table recognition, which utilizes nonlinear contrast enhancement based on weighted RC threshold iteration and Gaussian Laplacian LoG operator to carry out binarization processing on table images conforming to the format, and utilizes tilt correction algorithm based on perspective change to carry out tilt correction; uses an image morphological processing method to extract table box lines, segmentation of cells, to obtain the smallest cell; establishes the character database of the smallest cell, carries on the neural network training, establishes the form recognition model, carries on the recognition to the form. The invention has the advantages of simple calculation, fast speed, accurate identification of table images with weak contrast, uneven light and dark distribution of images and blurred background. The speed and precision of recognition are improved by establishing special high-frequency characters, training special neural network and template matching. At the same time, the customized neural network is simple in structure and reduces the time and workload of training and tuning.

The invention discloses an image feature-based image subject identification method. According to the method, primary processing of an image is performed firstly, image features are deepened through image enhancement, and a foreground is roughly separated from a background; morphological processing is mainly used for extracting the image features, and a segmentation process is used for dividing the image into elements or target objects; the search on the image feature extraction is that the extracted image elements or target objects are represented in a numerical form suitable for subsequent processing of a computer, and finally features capable of being directly used for a classifier model generated by machine learning are formed; a distributed environment improves search efficiency and parallel computing capability; and the input image is identified through the method to obtain feature data, an image with highest similarity with the input image is searched for and output, and whether the two images are matched or not is judged. The invention provides a stable and feasible image search method. The semanteme of the image is deeply analyzed and learnt, so that the time and speed of a current search algorithm are shortened and increased, the network restrictions are avoided, and the universality is very high.

The invention discloses an image classification method and system based on an image salient region. The method includes offline training and online test. The offline training comprises: performing ultra-pixel segmentation on an image to obtain multidimensional segmentation blocks, and calculating the characteristic contrast of the segmentation blocks to obtain a target salient map; performing threshold segmentation on the target salient map to obtain a binary image, performing morphological processing on the binary image, and performing automatic segmentation extraction on the target salient map by employing a segmentation algorithm to obtain the salient region; and inputting the salient region to a convolutional neural network for training to obtain an image classifier based on the image salient region. The online test includes: performing automatic segmentation extraction of the salient region on a test image, inputting a salient region image of the test image to the trained image classifier, and performing image classification to obtain an image class mark. According to the method and system, the segmentation result is guaranteed, the workload of artificial interaction is reduced, and the accuracy of image classification is improved.

The invention belongs to the field of image recognition processing. The invention relates to a self-adaptive intelligent document recognition and input device and a use method thereof. A data acquisition module acquires a paper text of a client into a picture file through scanning or shooting, the preprocessing module carries out block processing on the text in an image by utilizing a morphological processing algorithm, lattices in each line or table are made into unequal cell blocks, and the character recognition module carries out binary processing on each cell block; Then, the correlation analysis module performs correlation analysis according to a pre-configured keyword and a pre-configured rule; According to the technical scheme, the relation between text blocks is analyzed, a data extraction module is guided to extract needed field content, a deviation rectification module can perform verification and automatic correction on the extracted content according to previous identification and deviation rectification historical data, and finally a result is stored and returned to a calling party. The system is ingenious in design concept, safe and convenient to use, high in intelligent degree, high in recognition accuracy, friendly to application environment and wide in market prospect.

The invention discloses a fake plate detection method based on license plate identification and vehicle feature matching. The method comprises the following steps that: extracting a monitoring equipment frame image, and carrying out graying on a source image; adopting Sobel edge detection to position a license plate; adopting a morphological processing image to enable regions to be communicated soas to bring convenience for extracting the outline of the license plate; setting an aspect ratio to accurately extract areas; through hough transformation and vertical projection, carrying out license plate correction and character segmentation; using a neural network to identify segmented characters to obtain license plate information; migrating an AlexNet neural network frame, and carrying outclassification through the identification of the depth feature of the color; and applying a KNN (K-Nearest Neighbor) algorithm to be combined with database system information to detect a fake plate situation. By use of the method, vehicle identification accuracy is guaranteed, a high-accuracy convolutional neural network is directly migrated to serve as a basic framework, cost and expenditure aresmall, the method can be quickly realized on a computer platform, cost is small for arranging a license plate identification and vehicle identification system on a large scale, and feasibility is high.

The invention relates to a Fourier descriptor and gait energy image fusion feature-based gait identification method. The method comprises the steps of performing graying preprocessing on a single frame of image, updating a background in real time by using a Gaussian mixture model, and obtaining a foreground through a background subtraction method; performing binarization and morphological processing on each frame, obtaining a minimum enclosing rectangle of a moving human body, performing normalization to a same height, and obtaining a gait cycle and key 5 frames according to cyclic variation of a height-width ratio of the minimum enclosing rectangle; extracting low-frequency parts of Fourier descriptors of the key 5 frames to serve as features I; centralizing all frames in the cycle to obtain a gait energy image, and performing dimension reduction through principal component analysis to serve as features II; and fusing the features I and II and performing identification by adopting a support vector machine. According to the method, the judgment whether a current human behavior is abnormal or not can be realized; the background is accurately modeled by using the Gaussian mixture model, and relatively good real-time property is achieved; and the used fused feature has strong representability and robustness, so that the abnormal gait identification rate can be effectively increased.

The invention discloses a method for detecting, tracking and identifying an object abandoning/stealing event, which comprises the following steps of: 1) the detection of a moving object, namely, establishing an adaptive background model, extracting the moving object by utilizing a background difference and performing morphological processing and shadow processing to obtain a more complete and more accurate state of the moving object; 2) the tracking of the moving object, namely, realizing the inter-frame matching of the moving object through a recursion process of estimating, observing and correcting the state of the moving object, and tracking a moving track of the moving object; and 3) event identification, namely, giving a clear definition to the object abandoning/stealing event, judging the occurrence of the event according to the characteristics and the moving track of the moving object, if the event occurs, distinguishing an object abandoning event from an object stealing event, capturing evidence pictures for the identified abandoning and stealing events and giving an audible alarm.

The invention discloses a three-dimensional carotid artery ultrasonic image blood vessel wall segmentation method based on deep learning. The method comprises the following steps: (1) obtaining a three-dimensional ultrasonic image; (2) obtaining a two-dimensional ultrasonic image of a carotid artery cross section, and performing manual marking; (3) dynamically and finely adjusting the convolutional neural network model by utilizing the manually marked image block; (4) fitting vascular adventitia-tunica media boundary initial contour; (5) using the dynamically adjusted convolutional neural network model to carry out vascular adventitia-tunica media boundary contour segmentation; (6) obtaining a vascular cavity ROI region; (7)using U-Net network to divide the vascular cavity, and extractingthe vascular cavity-tunica media boundary contour through morphological processing. According to the method, the contours of vascular adventitia-tunica media boundary MAB and vascular cavity-tunica media boundary LIB can be accurately segmented out; the workload of doctors is greatly reduced, and the vascular wall volume (VWV), the vascular wall thickness (VWT) and the vascular wall thickness change (VWT-Change) can be calculated based on the segmentation result of the method.

The invention discloses a microalgae automatic counting method based on digital image processing. Digitalized processing is conducted on a preprocessed picture through a matlab image processing method to extract a binary image, morphological processing is conducted on the image, and the amount of microalgae is calculated. The problems of heavy labor and measurement errors caused by manual counting of microalgae microscopic images at present are solved. Meanwhile, the reliable counting method and the reliable counting steps are provided for the difficult problem that due to the fact that the microalgae microscopic images are easily affected by illumination impurity interference, light-background dark objects and cytoadherence, the microalgae can not be accurately counted, and the microalgae automatic counting method has important significance in microalgae growth monitoring.

The invention relates to a method for counting passengers taking a bus based on video stream processing and discloses a method for counting a people stream based on a security and protection video image. The method comprises the steps that 1) an original image is preprocessed; 2) a background model is established through the difference algorithm; 3) according to a background image, a foreground is obtained through differentiation and morphological processing is conducted on the foreground so that a moving object zone can be obtained; 4) the size of the moving object zone is judged, if the moving object zone is overlarge, a high-density passenger stream state is considered, a plurality of head zone moving objects are determined through the method that head features are matched, each head zone moving object is tracked so that the number of people getting on the bus and getting off the bus can be obtained through counting, and otherwise, the step 5) is conducted; 5), complementation is conducted on the moving object zone obtained through the original image, so that the background image is updated; 6) the moving object zone is divided, the divided moving objects are tacked, and whether the moving objects get on the bus or gets off the bus is determined according to the sequence of collision between the upper boundaries and a counting line and collision between the lower boundaries and the counting line of the moving objects, so that the passenger stream is counted.

The application discloses a lesion detection method and apparatus of an eye fundus image. The method comprises the following steps: carrying out pretreatment on a to-be-detected eye fundus image; carrying out optic disk positioning on the eye fundus image after pretreatment and determining an optic disk region; carrying out morphological processing on the eye fundus image after pretreatment to obtain a healthy background image; and according to the healthy background image and the optic disk region, determining an effusion region in the eye fundus image after pretreatment. Therefore, the detection speed of the eye fundus image can be increased and accuracy of positioning of a lesion region can be improved.

The invention discloses an SVM (support vector machine)-based medical image blood vessel recognition method. The method includes the following steps that: since an SVM classifier is obtained after cross validation and optimization are performed on an SVM model trained by samples automatically selected by an FCM by using an SVM model which is trained by samples obtained through the manual segmentation of experts, segmentation results are more accurate; the SVM is adopted to segment a blood vessel, namely, pixels are divided into a foreground (blood vessels) and a background (other parts), and the blood vessel part is extracted out; morphological processing and thresholding are performed, and therefore, a blood vessel network can be enhanced, the branches and intersections of the blood vessels are reserved; and an obtained image is converted into a binary image, so that blood vessel distribution can be reflected more directly. According to the method of the invention, the FCM, the SVM and the morphological image processing are combined together, so that a recognition effect is better.

The invention discloses a moving object detection method capable of automatically adapting to complex scenes, which comprises the steps of 1) carrying out illumination compensation on a video image; 2) acquiring a background image of each frame of the video image by using a mixed Gaussian background modeling method; 3) acquiring an absolute difference image of each frame by using a background difference method principle; 4) acquiring an optimal segmentation threshold of a gray probability model of each absolute difference image by adopting a maximum entropy segmentation principle; 5) carrying out binarization processing on each absolute difference image by using the optimal segmentation threshold so as to acquire a foreground image; 6) carrying out morphological processing by adopting modules with different structures; and 7) carrying out region calibration on each foreground image by using a connected domain calibration algorithm, and locking a calibrated moving object by using a rectangular frame. The moving object detection method disclosed by the invention has good moving object adaptive detection accuracy and robustness in different complex scenes such as drastic changes in global illumination, background disturbance, relative movement and the like, and can improve the performance of object detection.